Search results for: robustness

Authors: Jacqueline Y. Thompson, Sam Watson, Lee Middleton, Karla Hemming

Abstract:

Introduction: The odds ratio (estimated via logistic regression) is a well-established and common approach for estimating covariate-adjusted binary treatment effects when comparing a treatment and control group with dichotomous outcomes. Its popularity is primarily because of its stability and robustness to model misspecification. However, the situation is different for the relative risk and risk difference, which are arguably easier to interpret and better suited to specific designs such as non-inferiority studies. So far, there is no equivalent, widely acceptable approach to estimate an adjusted relative risk and risk difference when conducting clinical trials. This is partly due to the lack of a comprehensive evaluation of available candidate methods. Methods/Approach: A simulation study is designed to evaluate the performance of relevant candidate methods to estimate relative risks to represent conditional and marginal estimation approaches. We consider the log-binomial, generalised linear models (GLM) with iteratively weighted least-squares (IWLS) and model-based standard errors (SE); log-binomial GLM with convex optimisation and model-based SEs; log-binomial GLM with convex optimisation and permutation tests; modified-Poisson GLM IWLS and robust SEs; log-binomial generalised estimation equations (GEE) and robust SEs; marginal standardisation and delta method SEs; and marginal standardisation and permutation test SEs. Independent and identically distributed datasets are simulated from a randomised controlled trial to evaluate these candidate methods. Simulations are replicated 10000 times for each scenario across all possible combinations of sample sizes (200, 1000, and 5000), outcomes (10%, 50%, and 80%), and covariates (ranging from -0.05 to 0.7) representing weak, moderate or strong relationships. Treatment effects (ranging from 0, -0.5, 1; on the log-scale) will consider null (H0) and alternative (H1) hypotheses to evaluate coverage and power in realistic scenarios. Performance measures (bias, mean square error (MSE), relative efficiency, and convergence rates) are evaluated across scenarios covering a range of sample sizes, event rates, covariate prognostic strength, and model misspecifications. Potential Results, Relevance & Impact: There are several methods for estimating unadjusted and adjusted relative risks. However, it is unclear which method(s) is the most efficient, preserves type-I error rate, is robust to model misspecification, or is the most powerful when adjusting for non-prognostic and prognostic covariates. GEE estimations may be biased when the outcome distributions are not from marginal binary data. Also, it seems that marginal standardisation and convex optimisation may perform better than GLM IWLS log-binomial.

Keywords: binary outcomes, statistical methods, clinical trials, simulation study

Procedia PDF Downloads 115

Authors: Soumava Boral, Sanjay K. Chaturvedi, Ian Howard, Kristoffer McKee, V. N. A. Naikan

Abstract:

Due to strict regulations from government to enhance the possibilities of sustainability practices in industries, and noting the advances in sustainable manufacturing practices, it is necessary that the associated processes are also sustainable. Maintenance of large scale and complex machines is a pivotal task to maintain the uninterrupted flow of manufacturing processes. Appropriate maintenance practices can prolong the lifetime of machines, and prevent associated breakdowns, which subsequently reduces different cost heads. Selection of the best maintenance strategies for such machines are considered as a burdensome task, as they require the consideration of multiple technical criteria, complex mathematical calculations, previous fault data, maintenance records, etc. In the era of the fourth industrial revolution, organizations are rapidly changing their way of business, and they are giving their utmost importance to sensor technologies, artificial intelligence, data analytics, automations, etc. In this work, the effectiveness of several maintenance strategies (e.g., preventive, failure-based, reliability centered, condition based, total productive maintenance, etc.) related to a large scale and complex gearbox, operating in a steel processing plant is evaluated in terms of economic, social, environmental and technical criteria. As it is not possible to obtain/describe some criteria by exact numerical values, these criteria are evaluated linguistically by cross-functional experts. Fuzzy sets are potential soft-computing technique, which has been useful to deal with linguistic data and to provide inferences in many complex situations. To prioritize different maintenance practices based on the identified sustainable criteria, multi-criteria decision making (MCDM) approaches can be considered as potential tools. Multi-Attributive Ideal Real Comparative Analysis (MAIRCA) is a recent addition in the MCDM family and has proven its superiority over some well-known MCDM approaches, like TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) and ELECTRE (ELimination Et Choix Traduisant la REalité). It has a simple but robust mathematical approach, which is easy to comprehend. On the other side, due to some inherent drawbacks of Intuitionistic Fuzzy Sets (IFS) and Pythagorean Fuzzy Sets (PFS), recently, the use of Fermatean Fuzzy Sets (FFSs) has been proposed. In this work, we propose the novel concept of FF-MAIRCA. We obtain the weights of the criteria by experts’ evaluation and use them to prioritize the different maintenance practices according to their suitability by FF-MAIRCA approach. Finally, a sensitivity analysis is carried out to highlight the robustness of the approach.

Keywords: Fermatean fuzzy sets, Fermatean fuzzy MAIRCA, maintenance strategy selection, sustainable manufacturing, MCDM

Procedia PDF Downloads 139

Authors: A. Saravanan, B. R. Huang, C. J. Yeh, K. C. Leou, I. N. Lin

Abstract:

A new class of ultra-nano diamond-graphite nano-hybrid (DGH) composite materials containing nano-sized diamond needles was developed at low temperature process. Such kind of diamond- graphite nano-hybrid composite nanowires exhibit high electrical conductivity and excellent electron field emission (EFE) properties. Few earlier reports mention that addition of N2 gas to the growth plasma requires high growth temperature (800°C) to trigger the dopants to generate the conductivity in the films. High growth temperature is not familiar with the Si-based device fabrications. We have used a novel process such as bias-enhanced-grown (beg) MPECVD process to grow diamond films at low substrate temperature (450°C). We observed that the beg-N/UNCD films thus obtained possess high conductivity of σ=987 S/cm, ever reported for diamond films with excellent Electron field emission (EFE) properties. TEM investigation indicated that these films contain needle-like diamond grains about 5 nm in diameter and hundreds of nanometers in length. Each of the grains was encased in graphitic layers about tens of nano-meters in thickness. These materials properties suitable for more specific applications, such as high conductivity for electron field emitters, high robustness for microplasma cathodes and high electrochemical activity for electro-chemical sensing. Subsequently, other hand, the highly conducting DGH films were coated on vertically aligned ZnO nanorods, there is no prior nucleation or seeding process needed due to the use of BEG method. Such a composite structure provides significant enhancement in the field emission characteristics of the cold cathode was observed with ultralow turn on voltage 1.78 V/μm with high EFE current density of 3.68 mA/ cm2 (at 4.06V/μm) due to decoration of DGH material on ZnO nanorods. The DGH/ZNRs based device get stable emission for longer duration of 562min than bare ZNRs (104min) without any current degradation because the diamond coating protects the ZNRs from ion bombardment when they are used as the cathode for microplasma devices. The potential application of these materials is demonstrated by the plasma illumination measurements that ignited the plasma at the minimum voltage by 290 V. The photoresponse (Iphoto/Idark) behavior of the DGH/ZNRs based photodetectors exhibits a much higher photoresponse (1202) than bare ZNRs (229). During the process the electron transport is easy from ZNRs to DGH through graphitic layers, the EFE properties of these materials comparable to other primarily used field emitters like carbon nanotubes, graphene. The DGH/ZNRs composite also providing a possibility of their use in flat panel, microplasma and vacuum microelectronic devices.

Keywords: bias-enhanced nucleation and growth, ZnO nanorods, electrical conductivity, electron field emission, photo-detectors

Procedia PDF Downloads 370

Authors: Yan Torres, Fernanda Simoes, Francisco Petrucci-Fonseca, Freddie-Jeanne Richard

Abstract:

The non-invasive samples are an alternative of collecting genetic samples directly. Non-invasive samples are collected without the manipulation of the animal (e.g., scats, feathers and hairs). Nevertheless, the use of non-invasive samples has some limitations. The main issue is degraded DNA, leading to poorer extraction efficiency and genotyping. Those errors delayed for some years a widespread use of non-invasive genetic information. Possibilities to limit genotyping errors can be done using analysis methods that can assimilate the errors and singularities of non-invasive samples. Genotype matching and population estimation algorithms can be highlighted as important analysis tools that have been adapted to deal with those errors. Although, this recent development of analysis methods there is still a lack of empirical performance comparison of them. A comparison of methods with dataset different in size and structure can be useful for future studies since non-invasive samples are a powerful tool for getting information specially for endangered and rare populations. To compare the analysis methods, four different datasets used were obtained from the Dryad digital repository were used. Three different matching algorithms (Cervus, Colony and Error Tolerant Likelihood Matching - ETLM) are used for matching genotypes and two different ones for population estimation (Capwire and BayesN). The three matching algorithms showed different patterns of results. The ETLM produced less number of unique individuals and recaptures. A similarity in the matched genotypes between Colony and Cervus was observed. That is not a surprise since the similarity between those methods on the likelihood pairwise and clustering algorithms. The matching of ETLM showed almost no similarity with the genotypes that were matched with the other methods. The different cluster algorithm system and error model of ETLM seems to lead to a more criterious selection, although the processing time and interface friendly of ETLM were the worst between the compared methods. The population estimators performed differently regarding the datasets. There was a consensus between the different estimators only for the one dataset. The BayesN showed higher and lower estimations when compared with Capwire. The BayesN does not consider the total number of recaptures like Capwire only the recapture events. So, this makes the estimator sensitive to data heterogeneity. Heterogeneity in the sense means different capture rates between individuals. In those examples, the tolerance for homogeneity seems to be crucial for BayesN work properly. Both methods are user-friendly and have reasonable processing time. An amplified analysis with simulated genotype data can clarify the sensibility of the algorithms. The present comparison of the matching methods indicates that Colony seems to be more appropriated for general use considering a time/interface/robustness balance. The heterogeneity of the recaptures affected strongly the BayesN estimations, leading to over and underestimations population numbers. Capwire is then advisable to general use since it performs better in a wide range of situations.

Keywords: algorithms, genetics, matching, population

Procedia PDF Downloads 143

Authors: Saul Estrin, Ute Stephan, Suncica Vujic

Abstract:

Background and research question: Gender differences in pay are present at all organisational levels, including at the very top. One possible way for women to circumvent organizational norms and discrimination is to engage in entrepreneurship because, as CEOs of their own organizations, entrepreneurs largely determine their own pay. While commercial entrepreneurship plays an important role in job creation and economic growth, social entrepreneurship has come to prominence because of its promise of addressing societal challenges such as poverty, social exclusion, or environmental degradation through market-based rather than state-sponsored activities. This opens the research question whether social entrepreneurship might be a form of entrepreneurship in which the pay of men and women is the same, or at least more similar; that is to say there is little or no gender pay gap. If the gender gap in pay persists also at the top of social enterprises, what are the factors, which might explain these differences? Methodology: The Oaxaca-Blinder Decomposition (OBD) is the standard approach of decomposing the gender pay gap based on the linear regression model. The OBD divides the gender pay gap into the ‘explained’ part due to differences in labour market characteristics (education, work experience, tenure, etc.), and the ‘unexplained’ part due to differences in the returns to those characteristics. The latter part is often interpreted as ‘discrimination’. There are two issues with this approach. (i) In many countries there is a notable convergence in labour market characteristics across genders; hence the OBD method is no longer revealing, since the largest portion of the gap remains ‘unexplained’. (ii) Adding covariates to a base model sequentially either to test a particular coefficient’s ‘robustness’ or to account for the ‘effects’ on this coefficient of adding covariates might be problematic, due to sequence-sensitivity when added covariates are correlated. Gelbach’s decomposition (GD) addresses latter by using the omitted variables bias formula, which constructs a conditional decomposition thus accounting for sequence-sensitivity when added covariates are correlated. We use GD to decompose the differences in gaps of pay (annual and hourly salary), size of the organisation (revenues), effort (weekly hours of work), and sources of finances (fees and sales, grants and donations, microfinance and loans, and investors’ capital) between men and women leading social enterprises. Database: Our empirical work is made possible by our collection of a unique dataset using respondent driven sampling (RDS) methods to address the problem that there is as yet no information on the underlying population of social entrepreneurs. The countries that we focus on are the United Kingdom, Spain, Romania and Hungary. Findings and recommendations: We confirm the existence of a gender pay gap between men and women leading social enterprises. This gap can be explained by differences in the accumulation of human capital, psychological and social factors, as well as cross-country differences. The results of this study contribute to a more rounded perspective, highlighting that although social entrepreneurship may be a highly satisfying occupation, it also perpetuates gender pay inequalities.

Keywords: Gelbach’s decomposition, gender gap, returns to social entrepreneurship, values and preferences

Procedia PDF Downloads 244

Authors: Alessandro Balbo, Gianvito Colucci, Matteo Nicoli, Laura Savoldi

Abstract:

Hydrogen is expected to become an undisputed player in the ecological transition throughout the next decades. The decarbonization potential offered by this energy vector provides various opportunities for the so-called “hard-to-abate” sectors, including industrial production of iron and steel, glass, refineries and the heavy-duty transport. In this regard, Italy, in the framework of decarbonization plans for the whole European Union, has been considering a wider use of hydrogen to provide an alternative to fossil fuels in hard-to-abate sectors. This work aims to assess and compare different options concerning the pathway to be followed in the development of the future Italian energy system in order to meet decarbonization targets as established by the Paris Agreement and by the European Green Deal, and to infer a techno-economic analysis of the required asset alternatives to be used in that perspective. To accomplish this objective, the Energy System Optimization Model TEMOA-Italy is used, based on the open-source platform TEMOA and developed at PoliTo as a tool to be used for technology assessment and energy scenario analysis. The adopted assessment strategy includes two different scenarios to be compared with a business-as-usual one, which considers the application of current policies in a time horizon up to 2050. The studied scenarios are based on the up-to-date hydrogen-related targets and planned investments included in the National Hydrogen Strategy and in the Italian National Recovery and Resilience Plan, with the purpose of providing a critical assessment of what they propose. One scenario imposes decarbonization objectives for the years 2030, 2040 and 2050, without any other specific target. The second one (inspired to the national objectives on the development of the sector) promotes the deployment of the hydrogen value-chain. These scenarios provide feedback about the applications hydrogen could have in the Italian energy system, including transport, industry and synfuels production. Furthermore, the decarbonization scenario where hydrogen production is not imposed, will make use of this energy vector as well, showing the necessity of its exploitation in order to meet pledged targets by 2050. The distance of the planned policies from the optimal conditions for the achievement of Italian objectives is be clarified, revealing possible improvements of various steps of the decarbonization pathway, which seems to have as a fundamental element Carbon Capture and Utilization technologies for its accomplishment. In line with the European Commission open science guidelines, the transparency and the robustness of the presented results is ensured by the adoption of the open-source open-data model such as the TEMOA-Italy.

Keywords: decarbonization, energy system optimization models, hydrogen, open-source modeling, TEMOA

Procedia PDF Downloads 73

Authors: Atilola O. Abidemi-Iromini, Oluayo A. Bello-Olusoji, Immanuel A. Adebayo

Abstract:

Ecological studies were carried out in Asejire Reservoir (AR) and Lagos Lagoon (LL), Southwest Nigeria from January 2012 to December 2013 to determine the health status of Chrysichthys nigrodigitatus (CN) and Oreochromis niloticus (ON). The fish species samples were collected every month, these were separated into sexes, and growth pattern {length, (cm); weight (g), Isometric index, condition factor} were measured. Heavy metals (lead (Pb), iron (Fe), zinc (Zn), copper (Cu), and chromium (Cr) in ppm concentrations were also determined while bacteria occurrence(s), (load and prevalence) on fish skins, gills and intestine in the two ecological zones were determined. The fish ratio collected is in range with normal aquatic (1: 1+) male: female ratio. Growth assessment determined revealed no significant difference in length and weight in O. niloticus between locations, but a significant difference in weight occurred in C. nigrodigitatus between locations, with a higher weight (196.06 ±0.16 g) from Lagos Lagoon. Highest condition factor (5.25) was recorded in Asejire Reservoir O. niloticus, (ARON); and lowest condition factor (1.64) was observed in Asejire Reservoir C. nigrodigitatus (ARCN); as this indicated a negative allometric value which is normal in Bagridae species because it increases more in Length to weight gain than for the Cichlidae growth status. Normal growth rate (K > 1) occurred between sexes, with the male species having higher K - factors than female species within locations, between locations, between species, and within species, except for female C. nigrodigitatus having higher condition factor (K = 1.75) than male C. nigrodigitatus (K = 1.54) in Asejire Reservoir. The highest isometric value (3.05) was recorded in Asejire Reservoir O. niloticus and lowest in Lagos Lagoon C. nigrodigitatus. Male O. niloticus from Asejire Reservoir had highest isometric value, and O. niloticus species had higher condition factor which ranged between isometric (b ≤ 3) and positive allometric (b > 3), hence, denoted robustness of fish to grow more in weight than in length; while C. nigrodigitatus fish has negative allometric (b < 3) indicating fish add more length than in weight on growth. The status of condition factors and isometric values obtained is species-specific, and environmental influence, food availability or reproduction factor may as well be contributing factors. The concentrations of heavy metals in fish flesh revealed that Zn (6.52 ±0.82) had the highest, while Cr (0.01±0.00) was ranked lowest; for O. niloticus in Asejire Reservoir. In Lagos Lagoon, heavy metals concentration level revealed that O. niloticus flesh had highest in Zn (4.71±0.25) and lowest in Pb (0.01±0.00). Lagos Lagoon C. nigrodigitatus heavy metal concentration level revealed Zn (9.56±0.96) had highest, while Cr (0.06±0.01) had lowest; and Asejire Reservoir C. nigrodigitatus heavy metal level revealed that Zn (8.26 ±0.74) had highest, and Cr (0.08±0.00) had lowest. In all, Zinc (Zn) was top-ranked in level among species.

Keywords: Oreochromis niloticus, growth status, Chrysichthys nigrodigitatus, environments, heavy metals

Procedia PDF Downloads 116

Authors: Gema M. Rodado, Jose M. Olavarrieta

Abstract:

Hydrogen fuel cell technologies have experienced a great boost in the last decades, significantly increasing the production of these devices for both stationary and portable (mainly automotive) applications; these are influenced by two main factors: environmental pollution and energy shortage. A fuel cell is an electrochemical device that converts chemical energy directly into electricity by using hydrogen and oxygen gases as reactive components and obtaining water and heat as byproducts of the chemical reaction. Fuel cells, specifically those of Proton Exchange Membrane (PEM) technology, are considered an alternative to internal combustion engines, mainly because of the low emissions they produce (almost zero), high efficiency and low operating temperatures (< 373 K). The introduction and use of fuel cells in the automotive market requires the development of standardized and validated procedures to test and evaluate their performance in different environmental conditions including vibrations and freeze-thaw cycles. These situations of vibration and extremely low/high temperatures can affect the physical integrity or even the excellent operation or performance of the fuel cell stack placed in a vehicle in circulation or in different climatic conditions. The main objective of this work is the development and validation of vibration and freeze-thaw cycling test procedures for fuel cell stacks that can be used in a vehicle in order to consolidate their safety, performance, and durability. In this context, different experimental tests were carried out at the facilities of the National Hydrogen Centre (CNH2). The experimental equipment used was: A vibration platform (shaker) for vibration test analysis on fuel cells in three axes directions with different vibration profiles. A walk-in climatic chamber to test the starting, operating, and stopping behavior of fuel cells under defined extreme conditions. A test station designed and developed by the CNH2 to test and characterize PEM fuel cell stacks up to 10 kWe. A 5 kWe PEM fuel cell stack in off-operation mode was used to carry out two independent experimental procedures. On the one hand, the fuel cell was subjected to a sinusoidal vibration test on the shaker in the three axes directions. It was defined by acceleration and amplitudes in the frequency range of 7 to 200 Hz for a total of three hours in each direction. On the other hand, the climatic chamber was used to simulate freeze-thaw cycles by defining a temperature range between +313 K and -243 K with an average relative humidity of 50% and a recommended ramp up and rump down of 1 K/min. The polarization curve and gas leakage rate were determined before and after the vibration and freeze-thaw tests at the fuel cell stack test station to evaluate the robustness of the stack. The results were very similar, which indicates that the tests did not affect the fuel cell stack structure and performance. The proposed procedures were verified and can be used as an initial point to perform other tests with different fuel cells.

Keywords: climatic chamber, freeze-thaw cycles, PEM fuel cell, shaker, vibration tests

Procedia PDF Downloads 117

Authors: Konstantinos Kottikas, Vlasis Stathakopoulos, Ioannis G. Theodorakis, Efthymia Kottika

Abstract:

Theorists have argued that Market Orientation is comprised of two facets, namely the Market Driven and the Market Driving components. The present theoretical paper centers on the latter, which to date has been notably under-investigated. The term Market Driving (MD) pertains to influencing the structure of the market, or the behavior of market players in a direction that enhances the competitive edge of the firm. Presently, the main objectives of the paper are the specification of key antecedents and outcomes of Market Driving behavior. Market Driving firms behave proactively, by leading their customers and changing the rules of the game rather than by responding passively to them. Leading scholars were the first to conceptually conceive the notion, followed by some qualitative studies and a limited number of quantitative publications. However, recently, academicians noted that research on the topic remains limited, expressing a strong necessity for further insights. Concerning the key antecedents, top management’s Transformational Leadership (i.e. the form of leadership which influences organizational members by aligning their values, goals and aspirations to facilitate value-consistent behaviors) is one of the key drivers of MD behavior. Moreover, scholars have linked the MD concept with Entrepreneurship. Finally, the role that Employee’s Creativity plays in the development of MD behavior has been theoretically exemplified by a stream of literature. With respect to the key outcomes, it has been demonstrated that MD Behavior positively triggers firm Performance, while theorists argue that it empowers the Competitive Advantage of the firm. Likewise, researchers explicate that MD Behavior produces Radical Innovation. In order to test the robustness of the proposed theoretical framework, a combination of qualitative and quantitative methods is proposed. In particular, the conduction of in-depth interviews with distinguished executives and academicians, accompanied with a large scale quantitative survey will be employed, in order to triangulate the empirical findings. Given that it triggers overall firm’s success, the MD concept is of high importance to managers. Managers can become aware that passively reacting to market conditions is no longer sufficient. On the contrary, behaving proactively, leading the market, and shaping its status quo are new innovative approaches that lead to a paramount competitive posture and Innovation outcomes. This study also exemplifies that managers can foster MD Behavior through Transformational Leadership, Entrepreneurship and recruitment of Creative Employees. To date, the majority of the publications on Market Orientation is unilaterally directed towards the responsive (i.e. the Market Driven) component. The present paper further builds on scholars’ exhortations, and investigates the Market Driving facet, ultimately aspiring to conceptually integrate the somehow fragmented scientific findings, in a holistic framework.

Keywords: entrepreneurial orientation, market driving behavior, market orientation

Procedia PDF Downloads 384

Authors: Natalia V. Beloglazova, Pieterjan Lenain, Martin Hedstrom, Dietmar Knopp, Sarah De Saeger

Abstract:

In recent years polycyclic aromatic hydrocarbons (PAHs), which represent a hazard to humans and entire ecosystem, have been receiving an increased interest due to their mutagenic, carcinogenic and endocrine disrupting properties. They are formed in all incomplete combustion processes of organic matter and, as a consequence, ubiquitous in the environment. Benzo(a)pyrene (BaP) is on the priority list published by the Environmental Agency (US EPA) as the first PAH to be identified as a carcinogen and has often been used as a marker for PAHs contamination in general. It can be found in different types of water samples, therefore, the European Commission set up a limit value of 10 ng L–1 (10 ppt) for BAP in water intended for human consumption. Generally, different chromatographic techniques are used for PAHs determination, but these assays require pre-concentration of analyte, create large amounts of solvent waste, and are relatively time consuming and difficult to perform on-site. An alternative robust, stand-alone, and preferably cheap solution is needed. For example, a sensing unit which can be submerged in a river to monitor and continuously sample BaP. An affinity sensor based on capacitive transduction was developed. Natural antibodies or their synthetic analogues can be used as ligands. Ideally the sensor should operate independently over a longer period of time, e.g. several weeks or months, therefore the use of molecularly imprinted polymers (MIPs) was discussed. MIPs are synthetic antibodies which are selective for a chosen target molecule. Their robustness allows application in environments for which biological recognition elements are unsuitable or denature. They can be reused multiple times, which is essential to meet the stand-alone requirement. BaP is a highly lipophilic compound and does not contain any functional groups in its structure, thus excluding non-covalent imprinting methods based on ionic interactions. Instead, the MIPs syntheses were based on non-covalent hydrophobic and π-π interactions. Different polymerization strategies were compared and the best results were demonstrated by the MIPs produced using electropolymerization. 4-vinylpyridin (VP) and divinylbenzene (DVB) were used as monomer and cross-linker in the polymerization reaction. The selectivity and recovery of the MIP were compared to a non-imprinted polymer (NIP). Electrodes were functionalized with natural receptor (monoclonal anti-BaP antibody) and with MIPs selective towards BaP. Different sets of electrodes were evaluated and their properties such as sensitivity, selectivity and linear range were determined and compared. It was found that both receptor can reach the cut-off level comparable to the established ML, and despite the fact that the antibody showed the better cross-reactivity and affinity, MIPs were more convenient receptor due to their ability to regenerate and stability in river till 7 days.

Keywords: antibody, benzo(a)pyrene, capacitive sensor, MIPs, river water

Procedia PDF Downloads 303

Authors: Stefanie M. Vanneste, Stijn Goeminne

Abstract:

This paper studies the effect of political characteristics of 308 Flemish municipalities on their budget balance in the period 1995-2011. All local governments experience the same economic and financial setting, however some governments have high budget balances, while others have low budget balances. The aim of this paper is to explain the differences in municipal budget balances by a number of economic, socio-demographic and political variables. The economic and socio-demographic variables will be used as control variables, while the focus of this paper will be on the political variables. We test four hypotheses resulting from the literature, namely (i) the partisan hypothesis tests if left wing governments have lower budget balances, (ii) the fragmentation hypothesis stating that more fragmented governments have lower budget balances, (iii) the hypothesis regarding the power of the government, higher powered governments would resolve in higher budget balances, and (iv) the opportunistic budget cycle to test whether politicians manipulate the economic situation before elections in order to maximize their reelection possibilities and therefore have lower budget balances before elections. The contributions of our paper to the existing literature are multiple. First, we use the whole array of political variables and not just a selection of them. Second, we are dealing with a homogeneous database with the same budget and election rules, making it easier to focus on the political factors without having to control for the impact of differences in the political systems. Third, our research extends the existing literature on Flemish municipalities as this is the first dynamic research on local budget balances. We use a dynamic panel data model. Because of the two lagged dependent variables as explanatory variables, we employ the system GMM (Generalized Method of Moments) estimator. This is the best possible estimator as we are dealing with political panel data that is rather persistent. Our empirical results show that the effect of the ideological position and the power of the coalition are of less importance to explain the budget balance. The political fragmentation of the government on the other hand has a negative and significant effect on the budget balance. The more parties in a coalition the worse the budget balance is ceteris paribus. Our results also provide evidence of an opportunistic budget cycle, the budget balances are lower in pre-election years relative to the other years to try and increase the incumbents reelection possibilities. An additional finding is that the incremental effect of the budget balance is very important and should not be ignored like is being done in a lot of empirical research. The coefficients of the lagged dependent variables are always positive and very significant. This proves that the budget balance is subject to incrementalism. It is not possible to change the entire policy from one year to another so the actions taken in recent past years still have an impact on the current budget balance. Only a relatively small amount of research concerning the budget balance takes this considerable incremental effect into account. Our findings survive several robustness checks.

Keywords: budget balance, fragmentation, ideology, incrementalism, municipalities, opportunistic budget cycle, panel data, political characteristics, power, system GMM

Procedia PDF Downloads 299

Authors: Oluwafunmibi Omotayo Fasanya, Augustine Kena Adjei

Abstract:

Effective management of hypertension remains a critical public health challenge, particularly among racially and ethnically diverse populations. This study employs sophisticated statistical models to rigorously investigate the predictors of poor blood pressure (BP) control, with a specific focus on demographic, socioeconomic, and clinical risk factors. Leveraging a large sample of 19,253 adults drawn from the National Health and Nutrition Examination Survey (NHANES) across three distinct time periods (2013-2014, 2015-2016, and 2017-2020), we applied multivariable logistic regression and generalized estimating equations (GEE) to account for the clustered structure of the data and potential within-subject correlations. Our multivariable models identified significant associations between poor BP control and several key predictors, including race/ethnicity, age, gender, body mass index (BMI), prevalent diabetes, and chronic kidney disease (CKD). Non-Hispanic Black individuals consistently exhibited higher odds of poor BP control across all periods (OR = 1.99; 95% CI: 1.69, 2.36 for the overall sample; OR = 2.33; 95% CI: 1.79, 3.02 for 2017-2020). Younger age groups demonstrated substantially lower odds of poor BP control compared to individuals aged 75 and older (OR = 0.15; 95% CI: 0.11, 0.20 for ages 18-44). Men also had a higher likelihood of poor BP control relative to women (OR = 1.55; 95% CI: 1.31, 1.82), while BMI ≥35 kg/m² (OR = 1.76; 95% CI: 1.40, 2.20) and the presence of diabetes (OR = 2.20; 95% CI: 1.80, 2.68) were associated with increased odds of poor BP management. Further analysis using GEE models, accounting for temporal correlations and repeated measures, confirmed the robustness of these findings. Notably, individuals with chronic kidney disease displayed markedly elevated odds of poor BP control (OR = 3.72; 95% CI: 3.09, 4.48), with significant differences across the survey periods. Additionally, higher education levels and better self-reported diet quality were associated with improved BP control. College graduates exhibited a reduced likelihood of poor BP control (OR = 0.64; 95% CI: 0.46, 0.89), particularly in the 2015-2016 period (OR = 0.48; 95% CI: 0.28, 0.84). Similarly, excellent dietary habits were associated with significantly lower odds of poor BP control (OR = 0.64; 95% CI: 0.44, 0.94), underscoring the importance of lifestyle factors in hypertension management. In conclusion, our findings provide compelling evidence of the complex interplay between demographic, clinical, and socioeconomic factors in predicting poor BP control. The application of advanced statistical techniques such as GEE enhances the reliability of these results by addressing the correlated nature of repeated observations. This study highlights the need for targeted interventions that consider racial/ethnic disparities, clinical comorbidities, and lifestyle modifications in improving BP control outcomes.

Keywords: hypertension, blood pressure, NHANES, generalized estimating equations

Procedia PDF Downloads 12

Authors: Ben Otange, Wolfgang Parak, Florian Schulz, Michael Alexander Rubhausen

Abstract:

The feasibility of extending the usage of molecular imprinting technique in complex biomolecules is demonstrated in this research. This technique is promising in diverse applications in areas such as drug delivery, diagnosis of diseases, catalysts, and impurities detection as well as treatment of various complications. While molecularly imprinted polymers MIP remain robust in the synthesis of molecules with remarkable binding sites that have high affinities to specific molecules of interest, extending the usage to complex biomolecules remains futile. This work reports on the successful synthesis of MIP from complex proteins: BSA, Transferrin, and MUC1. We show in this research that despite the heterogeneous binding sites and higher conformational flexibility of the chosen proteins, relying on their respective epitopes and motifs rather than the whole template produces highly sensitive and selective MIPs for specific molecular binding. Introduction: Proteins are vital in most biological processes, ranging from cell structure and structural integrity to complex functions such as transport and immunity in biological systems. Unlike other imprinting templates, proteins have heterogeneous binding sites in their complex long-chain structure, which makes their imprinting to be marred by challenges. In addressing this challenge, our attention is inclined toward the targeted delivery, which will use molecular imprinting on the particle surface so that these particles may recognize overexpressed proteins on the target cells. Our goal is thus to make surfaces of nanoparticles that specifically bind to the target cells. Results and Discussions: Using epitopes of BSA and MUC1 proteins and motifs with conserved receptors of transferrin as the respective templates for MIPs, significant improvement in the MIP sensitivity to the binding of complex protein templates was noted. Through the Fluorescence Correlation Spectroscopy FCS measurements on the size of protein corona after incubation of the synthesized nanoparticles with proteins, we noted a high affinity of MIPs to the binding of their respective complex proteins. In addition, quantitative analysis of hard corona using SDS-PAGE showed that only a specific protein was strongly bound on the respective MIPs when incubated with similar concentrations of the protein mixture. Conclusion: Our findings have shown that the merits of MIPs can be extended to complex molecules of higher biomolecular mass. As such, the unique merits of the technique, including high sensitivity and selectivity, relative ease of synthesis, production of materials with higher physical robustness, and higher stability, can be extended to more templates that were previously not suitable candidates despite their abundance and usage within the body.

Keywords: molecularly imprinted polymers, specific binding, drug delivery, high biomolecular mass-templates

Procedia PDF Downloads 55

Authors: Jack L. Harris, Marya L. Doerfel, Hyunsook Youn, Minkyung Kim, Kautuki Sunil Jariwala

Abstract:

Organizational resilience refers to the ability to sustain business or general work functioning despite wide-scale interruptions. We focus on organization and businesses as a pillar of their communities and how they attempt to sustain work when a natural disaster impacts their surrounding regions and economies. While it may be more common to think of resilience as a trait possessed by an organization, an emerging area of research recognizes that for organizations and businesses, resilience is a set of processes that are constituted through communication, social networks, and organizing. Indeed, five processes, robustness, rapidity, resourcefulness, redundancy, and external availability through social media have been identified as critical to organizational resilience. These organizing mechanisms involve multi-level coordination, where individuals intersect with groups, organizations, and communities. Because the nature of such interactions are often networks of people and organizations coordinating material resources, information, and support, they necessarily require some way to coordinate despite being displaced. Little is known, however, if physical and digital spaces can substitute one for the other. We thus are guided by the question, is digital space sufficient when disaster creates a scarcity of physical space? This study presents a cross-case comparison based on field research from four different regions of the United States that were impacted by Hurricanes Katrina (2005), Sandy (2012), Maria (2017), and Harvey (2017). These four cases are used to extend the science of resilience by examining multi-level processes enacted by individuals, communities, and organizations that together, contribute to the resilience of disaster-struck organizations, businesses, and their communities. Using field research about organizations and businesses impacted by the four hurricanes, we code data from interviews, participant observations, field notes, and document analysis drawn from New Orleans (post-Katrina), coastal New Jersey (post-Sandy), Houston Texas (post-Harvey), and the lower keys of Florida (post-Maria). This paper identifies an additional organizing mechanism, networked gathering spaces, where citizens and organizations, alike, coordinate and facilitate information sharing, material resource distribution, and social support. Findings show that digital space, alone, is not a sufficient substitute to effectively sustain organizational resilience during a disaster. Because the data are qualitative, we expand on this finding with specific ways in which organizations and the people who lead them worked around the problem of scarce space. We propose that gatherings after disaster are a sixth mechanism that contributes to organizational resilience.

Keywords: communication, coordination, disaster management, information and communication technologies, interorganizational relationships, resilience, work

Procedia PDF Downloads 171

Authors: Ignitia Motjolopane

Abstract:

Small and medium enterprises (SMEs) play an important role in economies by contributing to economic growth and employment. In the fourth industrial revolution, the convergence of technologies and the changing nature of work created pressures on economies globally. Generative artificial intelligence (AI) may support SMEs in exploring, exploiting, and transforming business models to align with their growth aspirations. SMEs' growth aspirations fall into four categories: subsistence, income, growth, and speculative. Subsistence-oriented firms focus on meeting basic financial obligations and show less motivation for business model innovation. SMEs focused on income, growth, and speculation are more likely to pursue business model innovation to support growth strategies. SMEs' strategic goals link to distinct business model innovation paths depending on whether SMEs are starting a new business, pursuing growth, or seeking profitability. Integrating generative artificial intelligence in start-up SME business model innovation enhances value creation, user-oriented innovation, and SMEs' ability to adapt to dynamic changes in the business environment. The existing literature may lack comprehensive frameworks and guidelines for effectively integrating generative AI in start-up reiterative business model innovation paths. This paper examines start-up business model innovation path with generative artificial intelligence. A theoretical approach is used to examine start-up-focused SME reiterative business model innovation path with generative AI. Articulating how generative AI may be used to support SMEs to systematically and cyclically build the business model covering most or all business model components and analyse and test the BM's viability throughout the process. As such, the paper explores generative AI usage in market exploration. Moreover, market exploration poses unique challenges for start-ups compared to established companies due to a lack of extensive customer data, sales history, and market knowledge. Furthermore, the paper examines the use of generative AI in developing and testing viable value propositions and business models. In addition, the paper looks into identifying and selecting partners with generative AI support. Selecting the right partners is crucial for start-ups and may significantly impact success. The paper will examine generative AI usage in choosing the right information technology, funding process, revenue model determination, and stress testing business models. Stress testing business models validate strong and weak points by applying scenarios and evaluating the robustness of individual business model components and the interrelation between components. Thus, the stress testing business model may address these uncertainties, as misalignment between an organisation and its environment has been recognised as the leading cause of company failure. Generative AI may be used to generate business model stress-testing scenarios. The paper is expected to make a theoretical and practical contribution to theory and approaches in crafting a robust business model innovation path with generative artificial intelligence in start-up SMEs.

Keywords: business models, innovation, generative AI, small medium enterprises

Procedia PDF Downloads 71

Authors: Sara Rejeb, Catherine Duveau, Tabea Rebafka

Abstract:

To monitor the production process of turbofan aircraft engines, multiple measurements of various geometrical parameters are systematically recorded on manufactured parts. Engine parts are subject to extremely high standards as they can impact the performance of the engine. Therefore, it is essential to analyze these databases to better understand the influence of the different parameters on the engine's performance. Self-organizing maps are unsupervised neural networks which achieve two tasks simultaneously: they visualize high-dimensional data by projection onto a 2-dimensional map and provide clustering of the data. This technique has become very popular for data exploration since it provides easily interpretable results and a meaningful global view of the data. As such, self-organizing maps are usually applied to aircraft engine condition monitoring. As databases in this field are huge and complex, they naturally contain multiple missing entries for various reasons. The classical Kohonen algorithm to compute self-organizing maps is conceived for complete data only. A naive approach to deal with partially observed data consists in deleting items or variables with missing entries. However, this requires a sufficient number of complete individuals to be fairly representative of the population; otherwise, deletion leads to a considerable loss of information. Moreover, deletion can also induce bias in the analysis results. Alternatively, one can first apply a common imputation method to create a complete dataset and then apply the Kohonen algorithm. However, the choice of the imputation method may have a strong impact on the resulting self-organizing map. Our approach is to address simultaneously the two problems of computing a self-organizing map and imputing missing values, as these tasks are not independent. In this work, we propose an extension of self-organizing maps for partially observed data, referred to as missSOM. First, we introduce a criterion to be optimized, that aims at defining simultaneously the best self-organizing map and the best imputations for the missing entries. As such, missSOM is also an imputation method for missing values. To minimize the criterion, we propose an iterative algorithm that alternates the learning of a self-organizing map and the imputation of missing values. Moreover, we develop an accelerated version of the algorithm by entwining the iterations of the Kohonen algorithm with the updates of the imputed values. This method is efficiently implemented in R and will soon be released on CRAN. Compared to the standard Kohonen algorithm, it does not come with any additional cost in terms of computing time. Numerical experiments illustrate that missSOM performs well in terms of both clustering and imputation compared to the state of the art. In particular, it turns out that missSOM is robust to the missingness mechanism, which is in contrast to many imputation methods that are appropriate for only a single mechanism. This is an important property of missSOM as, in practice, the missingness mechanism is often unknown. An application to measurements on one type of part is also provided and shows the practical interest of missSOM.

Keywords: imputation method of missing data, partially observed data, robustness to missingness mechanism, self-organizing maps

Procedia PDF Downloads 151

Authors: Sardorbek Numonov, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Dongeun Choi, Byung-Woo Hong

Abstract:

The detection of curvilinear structures often plays an important role in the analysis of images. In particular, it is considered as a crucial step for the diagnosis of chronic respiratory diseases to localize the fissures in chest CT imagery where the lung is divided into five lobes by the fissures that are characterized by linear features in appearance. However, the characteristic linear features for the fissures are often shown to be subtle due to the high intensity variability, pathological deformation or image noise involved in the imaging procedure, which leads to the uncertainty in the quantification of anatomical or functional properties of the lung. Thus, it is desired to enhance the linear features present in the chest CT images so that the distinctiveness in the delineation of the lobe is improved. We propose a recursive diffusion process that prefers coherent features based on the analysis of structure tensor in an anisotropic manner. The local image features associated with certain scales and directions can be characterized by the eigenanalysis of the structure tensor that is often regularized via isotropic diffusion filters. However, the isotropic diffusion filters involved in the computation of the structure tensor generally blur geometrically significant structure of the features leading to the degradation of the characteristic power in the feature space. Thus, it is required to take into consideration of local structure of the feature in scale and direction when computing the structure tensor. We apply an anisotropic diffusion in consideration of scale and direction of the features in the computation of the structure tensor that subsequently provides the geometrical structure of the features by its eigenanalysis that determines the shape of the anisotropic diffusion kernel. The recursive application of the anisotropic diffusion with the kernel the shape of which is derived from the structure tensor leading to the anisotropic scale-space where the geometrical features are preserved via the eigenanalysis of the structure tensor computed from the diffused image. The recursive interaction between the anisotropic diffusion based on the geometry-driven kernels and the computation of the structure tensor that determines the shape of the diffusion kernels yields a scale-space where geometrical properties of the image structure are effectively characterized. We apply our recursive anisotropic diffusion algorithm to the detection of curvilinear structure in the chest CT imagery where the fissures present curvilinear features and define the boundary of lobes. It is shown that our algorithm yields precise detection of the fissures while overcoming the subtlety in defining the characteristic linear features. The quantitative evaluation demonstrates the robustness and effectiveness of the proposed algorithm for the detection of fissures in the chest CT in terms of the false positive and the true positive measures. The receiver operating characteristic curves indicate the potential of our algorithm as a segmentation tool in the clinical environment. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: anisotropic diffusion, chest CT imagery, chronic respiratory disease, curvilinear structure, fissure detection, structure tensor

Procedia PDF Downloads 233

Authors: Elizabeth M. Annoni, Elena G. Tolkacheva

Abstract:

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia that is a known prognostic marker for stroke, heart failure and death. Reentrant mechanisms of rotor formation, which are stable electrical sources of cardiac excitation, are believed to cause AF. No existing commercial mapping systems have been demonstrated to consistently and accurately predict rotor locations outside of the pulmonary veins in patients with persistent AF. There is a clear need for robust spatio-temporal techniques that can consistently identify rotors using unique characteristics of the electrical recordings at the pivot point that can be applied to clinical intracardiac mapping. Recently, we have developed four new signal analysis approaches – Shannon entropy (SE), Kurtosis (Kt), multi-scale frequency (MSF), and multi-scale entropy (MSE) – to identify the pivot points of rotors. These proposed techniques utilize different cardiac signal characteristics (other than local activation) to uncover the intrinsic complexity of the electrical activity in the rotors, which are not taken into account in current mapping methods. We validated these techniques using high-resolution optical mapping experiments in which direct visualization and identification of rotors in ex-vivo Langendorff-perfused hearts were possible. Episodes of ventricular tachycardia (VT) were induced using burst pacing, and two examples of rotors were used showing 3-sec episodes of a single stationary rotor and figure-8 reentry with one rotor being stationary and one meandering. Movies were captured at a rate of 600 frames per second for 3 sec. with 64x64 pixel resolution. These optical mapping movies were used to evaluate the performance and robustness of SE, Kt, MSF and MSE techniques with respect to the following clinical limitations: different time of recordings, different spatial resolution, and the presence of meandering rotors. To quantitatively compare the results, SE, Kt, MSF and MSE techniques were compared to the “true” rotor(s) identified using the phase map. Accuracy was calculated for each approach as the duration of the time series and spatial resolution were reduced. The time series duration was decreased from its original length of 3 sec, down to 2, 1, and 0.5 sec. The spatial resolution of the original VT episodes was decreased from 64x64 pixels to 32x32, 16x16, and 8x8 pixels by uniformly removing pixels from the optical mapping video.. Our results demonstrate that Kt, MSF and MSE were able to accurately identify the pivot point of the rotor under all three clinical limitations. The MSE approach demonstrated the best overall performance, but Kt was the best in identifying the pivot point of the meandering rotor. Artifacts mildly affect the performance of Kt, MSF and MSE techniques, but had a strong negative impact of the performance of SE. The results of our study motivate further validation of SE, Kt, MSF and MSE techniques using intra-atrial electrograms from paroxysmal and persistent AF patients to see if these approaches can identify pivot points in a clinical setting. More accurate rotor localization could significantly increase the efficacy of catheter ablation to treat AF, resulting in a higher success rate for single procedures.

Keywords: Atrial Fibrillation, Optical Mapping, Signal Processing, Rotors

Procedia PDF Downloads 324

Authors: Gabriela R. Silveira, Claudia S. Rocha, Lais S. Vitti, Jeane L. Borges, Helen B. Durgante

Abstract:

Emerging adulthood occurs after adolescence in a period that maybe be marked by experimentation, identity reconfigurations, labor life demands, and insertion in the work environment, which tends to generate stress and emotional instability. Health promotion programs for the development of strengths and virtues, based on Positive Psychology, for emerging adults are sparse in Brazil. The aim of this study was to evaluate the preliminary effects of an online multi-component Positive Psychology program for the health promotion of emerging adults based on Cognitive Behavioural Therapy and Positive Psychology. The program included six online (synchronous) weekly group sessions of approximately two hours each and homework (asynchronous) activities. The themes worked were Values and self-care/Prudence, Optimism, Empathy, Gratitude, Forgiveness, and Meaning of life and work. This study presents data from a longitudinal, pre-experimental design with pre (T1) and post-test (T2) evaluation in the intervention group. 47 individuals aged between 19-30 years old participated, mean age of 24.53 years (SD=3.13), 37 females (78.7%). 42 (89.4%) self-defined as heterosexual, four (8.5%) as homosexual, and one (2.5%) as bisexual. 33 (70.2%) had incomplete higher education, four (8.5%) completed higher education, and seven (14.9%) had a graduate level of education. 27 participants worked (57.4%), out of which 25 were health workers (53.2%). 14 (29.8%) were caregivers, 27 (57.4%) had a spiritual belief, 36 (76.6%) had access to leisure, and 38 (80.9%) had perceived social support. The instruments used were a sociodemographic questionnaire, the 10-item Perceived Stress Scale, and the 12-item General Health Questionnaire. The program was advertised on social networks and interested participants filled out the Consent Form and the evaluation protocol at T1 and T2 via Google Docs form. The main research was approved (CEP n.1,899,368; 4,143,219; CAAE: 61997516.5.0000.5334) and complied with sanitary and Ethics criteria in research with human beings. Wilcoxon statistics revealed significant improvements in indicators of perceived stress between T1 (X=22.21, SD=6.79) and T2 (X=15.10, SD=5.82); (Z=-4.353; p=0.001) as well as depression and anxiety symptoms (T1:X=26.72, SD=8.84; T2: X=19.23, SD=4.68); (Z=-3.945, p=0.001) of the emerging adults after their participation in the programme. The programme has an innovative character not only for presenting an online Positive Psychology approach but also for being based on an intervention developed, evaluated, and manualized in Brazil. By focusing on emerging adults, this study contributes to advancing research on a relatively new field in developmental studies. As a limitation, this is a pre-experimental and pilot study, requiring an increase in sample size for greater statistical robustness, also qualitative data analysis is crucial for methodological complementarity. The importance of investing efforts to accompany this age group and provide advances in longitudinal research in the area of health promotion and disease prevention is highlighted.

Keywords: emerging adults, disease prevention, health promotion, online program

Procedia PDF Downloads 104

Authors: Lakshmi N. Reddi, Akanksha Varma Sagi

Abstract:

Studies on biomimetics are largely developed, deriving inspiration from natural processes in our objective world to develop novel technologies. Recent studies are diverse in nature, making their categorization quite challenging. Based on an exhaustive survey, we developed categorizations based on either the essential elements of nature - air, water, land, fire, and space, or on form/shape, functionality, and process. Such diverse studies as aircraft wings inspired by bird wings, a self-cleaning coating inspired by a lotus petal, wetsuits inspired by beaver fur, and search algorithms inspired by arboreal ant path networks lend themselves to these categorizations. Our categorizations of biomimetic studies allowed us to define a different dimension of biomimetics. This new dimension is not restricted to inspiration from the objective world. It is based on the premise that the biological processes observed in the objective world find their reflections in our human bodies in a variety of ways. For example, the lungs provide the most efficient example for liquid-gas phase exchange, the heart exemplifies a very efficient pumping and circulatory system, and the kidneys epitomize the most effective cleaning system. The main focus of this paper is to bring out the magnificence of the cerebro-spinal system (CSS) insofar as it relates to our current computer architecture. In particular, the paper uses four key measures to analyze the differences between CSS and human- engineered computational systems. These are adaptability, sustainability, energy efficiency, and resilience. We found that the cerebrospinal system reveals some important challenges in the development and evolution of our current computer architectures. In particular, the myriad ways in which the CSS is integrated with other systems/processes (circulatory, respiration, etc) offer useful insights on how the human-engineered computational systems could be made more sustainable, energy-efficient, resilient, and adaptable. In our paper, we highlight the energy consumption differences between CSS and our current computational designs. Apart from the obvious differences in materials used between the two, the systemic nature of how CSS functions provides clues to enhance life-cycles of our current computational systems. The rapid formation and changes in the physiology of dendritic spines and their synaptic plasticity causing memory changes (ex., long-term potentiation and long-term depression) allowed us to formulate differences in the adaptability and resilience of CSS. In addition, the CSS is sustained by integrative functions of various organs, and its robustness comes from its interdependence with the circulatory system. The paper documents and analyzes quantifiable differences between the two in terms of the four measures. Our analyses point out the possibilities in the development of computational systems that are more adaptable, sustainable, energy efficient, and resilient. It concludes with the potential approaches for technological advancement through creation of more interconnected and interdependent systems to replicate the effective operation of cerebro-spinal system.

Keywords: cerebrospinal system, computer architecture, adaptability, sustainability, resilience, energy efficiency

Procedia PDF Downloads 99

Authors: Chetna Dhand, Venkatesh Mayandi, Silvia Marrero Diaz, Roger W. Beuerman, Seeram Ramakrishna, Rajamani Lakshminarayanan

Abstract:

Sturdy Insect Cuticle Sclerotization, Incredible Substrate independent Mussel’s bioadhesion, Tanning of Leather are some of catechol(amine)s mediated natural processes. Chemical contemplation spots toward a mechanism instigated with the formation of the quinone moieties from the respective catechol(amine)s, via oxidation, followed by the nucleophilic addition of the amino acids/proteins/peptides to this quinone leads to the development of highly strong, cross-linked and water-resistant proteinacious structures. Inspired with this remarkable catechol(amine)s chemistry towards amino acids/proteins/peptides, we attempted to design highly stable and water-resistant antifungal wound dressing mats with exceptional durability using collagen (protein), dopamine (catecholamine) and antifungal drugs (Amphotericin B and Caspofungin) as the key materials. Electrospinning technique has been used to fabricate desired nanofibrous mat including Collagen (COLL), COLL/Dopamine (COLL/DP) and calcium incorporated COLL/DP (COLL-DP-Ca2+). The prepared protein-based scaffolds have been studied for their microscopic investigations (SEM, TEM, and AFM), structural analysis (FT-IR), mechanical properties, water wettability characteristics and aqueous stability. Biocompatibility of these scaffolds has been analyzed for dermal fibroblast cells using MTS assay, Cell TrackerTM Green CMFDA and confocal imaging. Being the winner sample, COLL-DP-Ca2+ scaffold has been selected for incorporating two antifungal drugs namely Caspofungin (Peptide based) and Amphotericin B (Non-Peptide based). Antifungal efficiency of the designed mats has been evaluated for eight diverse fungal strains employing different microbial assays including disc diffusion, cell-viability assay, time kill kinetics etc. To confirm the durability of these mats, in term of their antifungal activity, drug leaching studies has been performed and monitored using disc diffusion assay each day. Ex-vivo fungal infection model has also been developed and utilized to validate the antifungal efficacy of the designed wound dressings. Results clearly reveal dopamine mediated crosslinking within COLL-antifungal scaffolds that leads to the generation of highly stable, mechanical tough, biocompatible wound dressings having the zone of inhabitation of ≥ 2 cm for almost all the investigated fungal strains. Leaching studies and Ex-vivo model has confirmed the durability of these wound dressing for more than 3 weeks and certified their suitability for commercialization. A model has also been proposed to enlighten the chemical mechanism involved for the development of these antifungal wound dressings with exceptional robustness.

Keywords: catecholamine chemistry, electrospinning technique, antifungals, wound dressings, collagen

Procedia PDF Downloads 377

Authors: Olga Hernán-Vega, Patricia López-Rodríguez, David Escot-Bocanegra, Raúl Fernández-Recio, Ignacio Bravo

Abstract:

Non-Cooperative Target Identification has become a key research domain in the Defense industry since it provides the ability to recognize targets at long distance and under any weather condition. High Resolution Range Profiles, one-dimensional radar images where the reflectivity of a target is projected onto the radar line of sight, are widely used for identification of flying targets. According to that, to face this problem, an approach to Non-Cooperative Target Identification based on the exploitation of Singular Value Decomposition to a matrix of range profiles is presented. Target Identification based on one-dimensional radar images compares a collection of profiles of a given target, namely test set, with the profiles included in a pre-loaded database, namely training set. The classification is improved by using Singular Value Decomposition since it allows to model each aircraft as a subspace and to accomplish recognition in a transformed domain where the main features are easier to extract hence, reducing unwanted information such as noise. Singular Value Decomposition permits to define a signal subspace which contain the highest percentage of the energy, and a noise subspace which will be discarded. This way, only the valuable information of each target is used in the recognition process. The identification algorithm is based on finding the target that minimizes the angle between subspaces and takes place in a transformed domain. Two metrics, F1 and F2, based on Singular Value Decomposition are accomplished in the identification process. In the case of F2, the angle is weighted, since the top vectors set the importance in the contribution to the formation of a target signal, on the contrary F1 simply shows the evolution of the unweighted angle. In order to have a wide database or radar signatures and evaluate the performance, range profiles are obtained through numerical simulation of seven civil aircraft at defined trajectories taken from an actual measurement. Taking into account the nature of the datasets, the main drawback of using simulated profiles instead of actual measured profiles is that the former implies an ideal identification scenario, since measured profiles suffer from noise, clutter and other unwanted information and simulated profiles don't. In this case, the test and training samples have similar nature and usually a similar high signal-to-noise ratio, so as to assess the feasibility of the approach, the addition of noise has been considered before the creation of the test set. The identification results applying the unweighted and weighted metrics are analysed for demonstrating which algorithm provides the best robustness against noise in an actual possible scenario. So as to confirm the validity of the methodology, identification experiments of profiles coming from electromagnetic simulations are conducted, revealing promising results. Considering the dissimilarities between the test and training sets when noise is added, the recognition performance has been improved when weighting is applied. Future experiments with larger sets are expected to be conducted with the aim of finally using actual profiles as test sets in a real hostile situation.

Keywords: HRRP, NCTI, simulated/synthetic database, SVD

Procedia PDF Downloads 354

Authors: Jeronimo Cox, Tomonari Furukawa

Abstract:

Magnetometers have become more popular in inertial measurement units (IMU) for their ability to correct estimations using the earth's magnetic field. Accelerometer and gyroscope-based packages fail with dead-reckoning errors accumulated over time. Localization in robotic applications with magnetometer-inclusive IMUs has become popular as a way to track the odometry of slower-speed robots. With high-speed motions, the accumulated error increases over smaller periods of time, making them difficult to track with IMU. Tracking a high-speed motion is especially difficult with limited observability. Visual obstruction of motion leaves motion-tracking cameras unusable. When motions are too dynamic for estimation techniques reliant on the observability of the gravity vector, the use of magnetometers is further justified. As available magnetometer calibration methods are limited with the assumption that background magnetic fields are uniform, estimation in nonuniform magnetic fields is problematic. Hard iron distortion is a distortion of the magnetic field by other objects that produce magnetic fields. This kind of distortion is often observed as the offset from the origin of the center of data points when a magnetometer is rotated. The magnitude of hard iron distortion is dependent on proximity to distortion sources. Soft iron distortion is more related to the scaling of the axes of magnetometer sensors. Hard iron distortion is more of a contributor to the error of attitude estimation with magnetometers. Indoor environments or spaces inside ferrite-based structures, such as building reinforcements or a vehicle, often cause distortions with proximity. As positions correlate to areas of distortion, methods of magnetometer localization include the production of spatial mapping of magnetic field and collection of distortion signatures to better aid location tracking. The goal of this paper is to compare magnetometer methods that don't need pre-productions of magnetic field maps. Mapping the magnetic field in some spaces can be costly and inefficient. Dynamic measurement fusion is used to track the motion of a multi-link system with us. Conventional calibration by data collection of rotation at a static point, real-time estimation of calibration parameters each time step, and using two magnetometers for determining local hard iron distortion are compared to confirm the robustness and accuracy of each technique. With opposite-facing magnetometers, hard iron distortion can be accounted for regardless of position, Rather than assuming that hard iron distortion is constant regardless of positional change. The motion measured is a repeatable planar motion of a two-link system connected by revolute joints. The links are translated on a moving base to impulse rotation of the links. Equipping the joints with absolute encoders and recording the motion with cameras to enable ground truth comparison to each of the magnetometer methods. While the two-magnetometer method accounts for local hard iron distortion, the method fails where the magnetic field direction in space is inconsistent.

Keywords: motion tracking, sensor fusion, magnetometer, state estimation

Procedia PDF Downloads 85

Authors: M. Ciminello, I. Dimino, S. Ameduri, A. Concilio

Abstract:

Improving aircraft's efficiency is one of the key elements of Aeronautics. Modern aircraft possess many advanced functions, such as good transportation capability, high Mach number, high flight altitude, and increasing rate of climb. However, no aircraft has a possibility to reach all of this optimized performance in a single airframe configuration. The aircraft aerodynamic efficiency varies considerably depending on the specific mission and on environmental conditions within which the aircraft must operate. Structures that morph their shape in response to their surroundings may at first seem like the stuff of science fiction, but take a look at nature and lots of examples of plants and animals that adapt to their environment would arise. In order to ensure both the controllable and the static robustness of such complex structural systems, a monitoring network is aimed at verifying the effectiveness of the given control commands together with the elastic response. In order to achieve this kind of information, the use of FBG sensors network is, in this project, proposed. The sensor network is able to measure morphing structures shape which may show large, global displacements due to non-standard architectures and materials adopted. Chord -wise variations may allow setting and chasing the best layout as a function of the particular and transforming reference state, always targeting best aerodynamic performance. The reason why an optical sensor solution has been selected is that while keeping a few of the contraindication of the classical systems (like cabling, continuous deployment, and so on), fibre optic sensors may lead to a dramatic reduction of the wires mass and weight thanks to an extreme multiplexing capability. Furthermore, the use of the ‘light’ as ‘information carrier’, permits dealing with nimbler, non-shielded wires, and avoids any kind of interference with the on-board instrumentation. The FBG-based transducers, herein presented, aim at monitoring the actual shape of adaptive trailing edge. Compared to conventional systems, these transducers allow more fail-safe measurements, by taking advantage of a supporting structure, hosting FBG, whose properties may be tailored depending on the architectural requirements and structural constraints, acting as strain modulator. The direct strain may, in fact, be difficult because of the large deformations occurring in morphing elements. A modulation transducer is then necessary to keep the measured strain inside the allowed range. In this application, chord-wise transducer device is a cantilevered beam sliding trough the spars and copying the camber line of the ATE ribs. FBG sensors array position are dimensioned and integrated along the path. A theoretical model describing the system behavior is implemented. To validate the design, experiments are then carried out with the purpose of estimating the functions between rib rotation and measured strain.

Keywords: fiber optic sensor, morphing structures, strain sensor, shape reconstruction

Procedia PDF Downloads 329

Authors: Nejmeddine Ouhichi, Fethi Lachaal, Radhouane Hamdi, Olivier Grunberger

Abstract:

Located in Cap Bon peninsula (Tunisia), the Lebna dam was built in 1987 to balance local water salt intrusion taking place in the coastal aquifer of Korba. The first intention was to reduce coastal groundwater over-pumping by supplying surface water to a large irrigation system. The unpredicted beneficial effect was recorded with the occurrence of a direct localized recharge to the coastal aquifer by leakage through the geological material of the southern bank of the lake. The hydrological balance of the reservoir dam gave an estimation of the annual leakage volume, but dynamic processes and sound quantification of recharge inputs are still required to understand the localized effect of the recharge in terms of piezometry and quality. Present work focused on simulating the recharge process to confirm the hypothesis, and established a sound quantification of the water supply to the coastal aquifer and extend it to multi-annual effects. A spatial frame of 30km² was used for modeling. Intensive outcrops and geophysical surveys based on 68 electrical resistivity soundings were used to characterize the aquifer 3D geometry and the limit of the Plio-quaternary geological material concerned by the underground flow paths. Permeabilities were determined using 17 pumping tests on wells and piezometers. Six seasonal piezometric surveys on 71 wells around southern reservoir dam banks were performed during the 2019-2021 period. Eight monitoring boreholes of high frequency (15min) piezometric data were used to examine dynamical aspects. Model boundary conditions were specified using the geophysics interpretations coupled with the piezometric maps. The dam-groundwater flow model was performed using Visual MODFLOW software. Firstly, permanent state calibration based on the first piezometric map of February 2019 was established to estimate the permanent flow related to the different reservoir levels. Secondly, piezometric data for the 2019-2021 period were used for transient state calibration and to confirm the robustness of the model. Preliminary results confirmed the temporal link between the reservoir level and the localized recharge flow with a strong threshold effect for levels below 16 m.a.s.l. The good agreement of computed flow through recharge cells on the southern banks and hydrological budget of the reservoir open the path to future simulation scenarios of the dilution plume imposed by the localized recharge. The dam reservoir-groundwater flow-model simulation results approve a potential for storage of up to 17mm/year in existing wells, under gravity-feed conditions during level increases on the reservoir into the three years of operation. The Lebna dam groundwater flow model characterized a spatiotemporal relation between groundwater and surface water.

Keywords: leakage, MODFLOW, saltwater intrusion, surface water-groundwater interaction

Procedia PDF Downloads 138

Authors: Masoud Fathi Kazerouni, Jens Schlemper, Klaus-Dieter Kuhnert

Abstract:

Green planet is one of the Earth’s names which is known as a terrestrial planet and also can be named the fifth largest planet of the solar system as another scientific interpretation. Plants do not have a constant and steady distribution all around the world, and even plant species’ variations are not the same in one specific region. Presence of plants is not only limited to one field like botany; they exist in different fields such as literature and mythology and they hold useful and inestimable historical records. No one can imagine the world without oxygen which is produced mostly by plants. Their influences become more manifest since no other live species can exist on earth without plants as they form the basic food staples too. Regulation of water cycle and oxygen production are the other roles of plants. The roles affect environment and climate. Plants are the main components of agricultural activities. Many countries benefit from these activities. Therefore, plants have impacts on political and economic situations and future of countries. Due to importance of plants and their roles, study of plants is essential in various fields. Consideration of their different applications leads to focus on details of them too. Automatic recognition of plants is a novel field to contribute other researches and future of studies. Moreover, plants can survive their life in different places and regions by means of adaptations. Therefore, adaptations are their special factors to help them in hard life situations. Weather condition is one of the parameters which affect plants life and their existence in one area. Recognition of plants in different weather conditions is a new window of research in the field. Only natural images are usable to consider weather conditions as new factors. Thus, it will be a generalized and useful system. In order to have a general system, distance from the camera to plants is considered as another factor. The other considered factor is change of light intensity in environment as it changes during the day. Adding these factors leads to a huge challenge to invent an accurate and secure system. Development of an efficient plant recognition system is essential and effective. One important component of plant is leaf which can be used to implement automatic systems for plant recognition without any human interface and interaction. Due to the nature of used images, characteristic investigation of plants is done. Leaves of plants are the first characteristics to select as trusty parts. Four different plant species are specified for the goal to classify them with an accurate system. The current paper is devoted to principal directions of the proposed methods and implemented system, image dataset, and results. The procedure of algorithm and classification is explained in details. First steps, feature detection and description of visual information, are outperformed by using Scale invariant feature transform (SIFT), HARRIS-SIFT, and FAST-SIFT methods. The accuracy of the implemented methods is computed. In addition to comparison, robustness and efficiency of results in different conditions are investigated and explained.

Keywords: SIFT combination, feature extraction, feature detection, natural images, natural plant recognition, HARRIS-SIFT, FAST-SIFT

Procedia PDF Downloads 276

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 290

Authors: Ammar Alali, Mahmoud Abughaban

Abstract:

Cost reduction and drilling optimization is the goal of many drilling operators. Historically, stuck pipe incidents were a major segment of non-productive time (NPT) associated costs. Traditionally, stuck pipe problems are part of the operations and solved post-sticking. However, the real key to savings and success is in predicting the stuck pipe incidents and avoiding the conditions leading to its occurrences. Previous attempts in stuck-pipe predictions have neglected the local geology of the problem. The proposed predictive tool utilizes geophysical data processing techniques and Machine Learning (ML) algorithms to predict drilling activities events in real-time using surface drilling data with minimum computational power. The method combines two types of analysis: (1) real-time prediction, and (2) cause analysis. Real-time prediction aggregates the input data, including historical drilling surface data, geological formation tops, and petrophysical data, from wells within the same field. The input data are then flattened per the geological formation and stacked per stuck-pipe incidents. The algorithm uses two physical methods (stacking and flattening) to filter any noise in the signature and create a robust pre-determined pilot that adheres to the local geology. Once the drilling operation starts, the Wellsite Information Transfer Standard Markup Language (WITSML) live surface data are fed into a matrix and aggregated in a similar frequency as the pre-determined signature. Then, the matrix is correlated with the pre-determined stuck-pipe signature for this field, in real-time. The correlation used is a machine learning Correlation-based Feature Selection (CFS) algorithm, which selects relevant features from the class and identifying redundant features. The correlation output is interpreted as a probability curve of stuck pipe incidents prediction in real-time. Once this probability passes a fixed-threshold defined by the user, the other component, cause analysis, alerts the user of the expected incident based on set pre-determined signatures. A set of recommendations will be provided to reduce the associated risk. The validation process involved feeding of historical drilling data as live-stream, mimicking actual drilling conditions, of an onshore oil field. Pre-determined signatures were created for three problematic geological formations in this field prior. Three wells were processed as case studies, and the stuck-pipe incidents were predicted successfully, with an accuracy of 76%. This accuracy of detection could have resulted in around 50% reduction in NPT, equivalent to 9% cost saving in comparison with offset wells. The prediction of stuck pipe problem requires a method to capture geological, geophysical and drilling data, and recognize the indicators of this issue at a field and geological formation level. This paper illustrates the efficiency and the robustness of the proposed cross-disciplinary approach in its ability to produce such signatures and predicting this NPT event.

Keywords: drilling optimization, hazard prediction, machine learning, stuck pipe

Procedia PDF Downloads 230

Authors: Hassan Younis

Abstract:

Purpose: The objective of this study is to review influential papers in the sustainability and supply chain studies domain, leveraging insights from this review to develop a structured framework for academics and researchers. This framework aims to assist scholars in identifying the most impactful publications for their scholarly pursuits. Subsequently, the study will apply and trial the developed framework on selected scholarly articles within the sustainability and supply chain studies domain to evaluate its efficacy, practicality, and reliability. Design/Methodology/Approach: Utilizing the "Publish or Perish" tool, a search was conducted to locate papers incorporating "sustainability" and "supply chain" in their titles. After rigorous filtering steps, a panel of university professors identified five crucial criteria for evaluating research robustness: average yearly citation counts (25%), scholarly contribution (25%), alignment of findings with objectives (15%), methodological rigor (20%), and journal impact factor (15%). These five evaluation criteria are abbreviated as “ACMAJ" framework. Each paper then received a tiered score (1-3) for each criterion, normalized within its category, and summed using weighted averages to calculate a Final Normalized Score (FNS). This systematic approach allows for objective comparison and ranking of the research based on its impact, novelty, rigor, and publication venue. Findings: The study's findings highlight the lack of structured frameworks for assessing influential sustainability research in supply chain management, which often results in a dependence on citation counts. A complete model that incorporates five essential criteria has been suggested as a response. By conducting a methodical trial on specific academic articles in the field of sustainability and supply chain studies, the model demonstrated its effectiveness as a tool for identifying and selecting influential research papers that warrant additional attention. This work aims to fill a significant deficiency in existing techniques by providing a more comprehensive approach to identifying and ranking influential papers in the field. Practical Implications: The developed framework helps scholars identify the most influential sustainability and supply chain publications. Its validation serves the academic community by offering a credible tool and helping researchers, students, and practitioners find and choose influential papers. This approach aids field literature reviews and study suggestions. Analysis of major trends and topics deepens our grasp of this critical study area's changing terrain. Originality/Value: The framework stands as a unique contribution to academia, offering scholars an important and new tool to identify and validate influential publications. Its distinctive capacity to efficiently guide scholars, learners, and professionals in selecting noteworthy publications, coupled with the examination of key patterns and themes, adds depth to our understanding of the evolving landscape in this critical field of study.

Keywords: supply chain management, sustainability, framework, model

Procedia PDF Downloads 52

Authors: Z. Gharaee

Abstract:

Recognizing actions performed by others is important in our daily lives since it is necessary for communicating with others in a proper way. We perceive an action by observing the kinematics of motions involved in the performance. We use our experience and concepts to make a correct recognition of the actions. Although building the action concepts is a life-long process, which is repeated throughout life, we are very efficient in applying our learned concepts in analyzing motions and recognizing actions. Experiments on the subjects observing the actions performed by an actor show that an action is recognized after only about two hundred milliseconds of observation. In this study, hierarchical action recognition architecture is proposed by using growing grid layers. The first-layer growing grid receives the pre-processed data of consecutive 3D postures of joint positions and applies some heuristics during the growth phase to allocate areas of the map by inserting new neurons. As a result of training the first-layer growing grid, action pattern vectors are generated by connecting the elicited activations of the learned map. The ordered vector representation layer receives action pattern vectors to create time-invariant vectors of key elicited activations. Time-invariant vectors are sent to second-layer growing grid for categorization. This grid creates the clusters representing the actions. Finally, one-layer neural network developed by a delta rule labels the action categories in the last layer. System performance has been evaluated in an experiment with the publicly available MSR-Action3D dataset. There are actions performed by using different parts of human body: Hand Clap, Two Hands Wave, Side Boxing, Bend, Forward Kick, Side Kick, Jogging, Tennis Serve, Golf Swing, Pick Up and Throw. The growing grid architecture was trained by applying several random selections of generalization test data fed to the system during on average 100 epochs for each training of the first-layer growing grid and around 75 epochs for each training of the second-layer growing grid. The average generalization test accuracy is 92.6%. A comparison analysis between the performance of growing grid architecture and self-organizing map (SOM) architecture in terms of accuracy and learning speed show that the growing grid architecture is superior to the SOM architecture in action recognition task. The SOM architecture completes learning the same dataset of actions in around 150 epochs for each training of the first-layer SOM while it takes 1200 epochs for each training of the second-layer SOM and it achieves the average recognition accuracy of 90% for generalization test data. In summary, using the growing grid network preserves the fundamental features of SOMs, such as topographic organization of neurons, lateral interactions, the abilities of unsupervised learning and representing high dimensional input space in the lower dimensional maps. The architecture also benefits from an automatic size setting mechanism resulting in higher flexibility and robustness. Moreover, by utilizing growing grids the system automatically obtains a prior knowledge of input space during the growth phase and applies this information to expand the map by inserting new neurons wherever there is high representational demand.

Keywords: action recognition, growing grid, hierarchical architecture, neural networks, system performance

Procedia PDF Downloads 157