Search results for: error estimation

Authors: Joselito Medina-Marin, Maria G. Serna-Diaz, Alejandro Tellez-Jurado, Juan C. Seck-Tuoh-Mora, Eva S. Hernandez-Gress, Norberto Hernandez-Romero, Iaina P. Medina-Serna

Abstract:

Trichoderma harzianum is a fungus that has been utilized as a low-cost fungicide for biological control of pests, and it is important to determine the optimal conditions to produce the highest amount of conidiospores of Trichoderma harzianum. In this work, the conidiospore production of Trichoderma harzianum is modeled and optimized by using Artificial Neural Networks (AANs). In order to gather data of this process, 30 experiments were carried out taking into account the number of hours of culture (10 distributed values from 48 to 136 hours) and the culture humidity (70, 75 and 80 percent), obtained as a response the number of conidiospores per gram of dry mass. The experimental results were used to develop an iterative algorithm to create 1,110 ANNs, with different configurations, starting from one to three hidden layers, and every hidden layer with a number of neurons from 1 to 10. Each ANN was trained with the Levenberg-Marquardt backpropagation algorithm, which is used to learn the relationship between input and output values. The ANN with the best performance was chosen in order to simulate the process and be able to maximize the conidiospores production. The obtained ANN with the highest performance has 2 inputs and 1 output, three hidden layers with 3, 10 and 10 neurons in each layer, respectively. The ANN performance shows an R2 value of 0.9900, and the Root Mean Squared Error is 1.2020. This ANN predicted that 644175467 conidiospores per gram of dry mass are the maximum amount obtained in 117 hours of culture and 77% of culture humidity. In summary, the ANN approach is suitable to represent the conidiospores production of Trichoderma harzianum because the R2 value denotes a good fitting of experimental results, and the obtained ANN model was used to find the parameters to produce the biggest amount of conidiospores per gram of dry mass.

Keywords: Trichoderma harzianum, modeling, optimization, artificial neural network

Procedia PDF Downloads 117

Authors: M. Miljkovic, A. Urakpo, M. Simic-Koumoutsaris

Abstract:

Benefit-risk assessment (BRA) is a valuable tool that takes place in multiple stages during a medicine's lifecycle, and this assessment can be conducted in a variety of ways. The aim was to summarize current BRA methods used during approval decisions and in post-approval settings and to see possible future directions. Relevant reviews, recommendations, and guidelines published in medical literature and through regulatory agencies over the past five years have been examined. BRA implies the review of two dimensions: the dimension of benefits (determined mainly by the therapeutic efficacy) and the dimension of risks (comprises the safety profile of a drug). Regulators, industry, and academia have developed various approaches, ranging from descriptive textual (qualitative) to decision-analytic (quantitative) models, to facilitate the BRA of medicines during the product lifecycle (from Phase I trials, to authorization procedure, post-marketing surveillance and health technology assessment for inclusion in public formularies). These approaches can be classified into the following categories: stepwise structured approaches (frameworks); measures for benefits and risks that are usually endpoint specific (metrics), simulation techniques and meta-analysis (estimation techniques), and utility survey techniques to elicit stakeholders’ preferences (utilities). All these approaches share the following two common goals: to assist this analysis and to improve the communication of decisions, but each is subject to its own specific strengths and limitations. Before using any method, its utility, complexity, the extent to which it is established, and the ease of results interpretation should be considered. Despite widespread and long-time use, BRA is subject to debate, suffers from a number of limitations, and currently is still under development. The use of formal, systematic structured approaches to BRA for regulatory decision-making and quantitative methods to support BRA during the product lifecycle is a standard practice in medicine that is subject to continuous improvement and modernization, not only in methodology but also in cooperation between organizations.

Keywords: benefit-risk assessment, benefit-risk profile, product lifecycle, quantitative methods, structured approaches

Procedia PDF Downloads 113

Authors: M. P. Tripathi, Priti Tiwari

Abstract:

Soil and Water Assessment Tool (SWAT) is a distributed parameter continuous time model and was tested on daily and fortnightly basis for a small agricultural watershed (Dhangaon) of Chhattisgarh state in India. The SWAT model recently interfaced with ArcGIS and called as ArcSWAT. The watershed and sub-watershed boundaries, drainage networks, slope and texture maps were generated in the environment of ArcGIS of ArcSWAT. Supervised classification method was used for land use/cover classification from satellite imageries of the years 2009 and 2012. Manning's roughness coefficient 'n' for overland flow and channel flow and Fraction of Field Capacity (FFC) were calibrated for monsoon season of the years 2009 and 2010. The model was validated on a daily basis for the years 2011 and 2012 by using the observed daily rainfall and temperature data. Calibration and validation results revealed that the model was predicting the daily surface runoff and sediment yield satisfactorily. Sensitivity analysis showed that the annual sediment yield was inversely proportional to the overland and channel 'n' values whereas; annual runoff and sediment yields were directly proportional to the FFC. The model was also tested (calibrated and validated) for the fortnightly runoff and sediment yield for the year 2009-10 and 2011-12, respectively. Simulated values of fortnightly runoff and sediment yield for the calibration and validation years compared well with their observed counterparts. The calibration and validation results revealed that the ArcSWAT model could be used for identification of critical sub-watershed and for developing management scenarios for the Dhangaon watershed. Further, the model should be tested for simulating the surface runoff and sediment yield using generated rainfall and temperature before applying it for developing the management scenario for the critical or priority sub-watersheds.

Keywords: watershed, hydrologic and water quality, ArcSWAT model, remote sensing, GIS, runoff and sediment yield

Procedia PDF Downloads 340

Authors: Roengchai Tansuchat, Woraphon Yamaka, Paravee Maneejuk

Abstract:

From the past recent, the global financial crisis, economic instability, and large fluctuation in agricultural commodity price have led to increased concerns about the volatility transmission among them. The problem is further exacerbated by commodities volatility caused by other commodity price fluctuations, hence the decision on hedging strategy has become both costly and useless. Thus, this paper is conducted to analysis the volatility spillover effect among major agriculture including corn, soybeans, wheat and rice, to help the commodity suppliers hedge their portfolios, and manage the risk and co-volatility of them. We provide a switching regime approach to analyzing the issue of volatility spillovers in different economic conditions, namely upturn and downturn economic. In particular, we investigate relationships and volatility transmissions between these commodities in different economic conditions. We purposed a Copula-based multivariate Markov Switching GARCH model with two regimes that depend on an economic conditions and perform simulation study to check the accuracy of our proposed model. In this study, the correlation term in the cross-hedge ratio is obtained from six copula families – two elliptical copulas (Gaussian and Student-t) and four Archimedean copulas (Clayton, Gumbel, Frank, and Joe). We use one-step maximum likelihood estimation techniques to estimate our models and compare the performance of these copula using Akaike information criterion (AIC) and Bayesian information criteria (BIC). In the application study of agriculture commodities, the weekly data used are conducted from 4 January 2005 to 1 September 2016, covering 612 observations. The empirical results indicate that the volatility spillover effects among cereal futures are different, as response of different economic condition. In addition, the results of hedge effectiveness will also suggest the optimal cross hedge strategies in different economic condition especially upturn and downturn economic.

Keywords: agricultural commodity futures, cereal, cross-hedge, spillover effect, switching regime approach

Procedia PDF Downloads 168

Authors: Marzieh Khedmati, Shannon L. Bartelt-Hunt

Abstract:

Vegetative Filter Strips (VFS) are used for controlling the volume of runoff and decreasing contaminant concentrations in runoff before entering water bodies. Many studies have investigated the role of VFS in sediment and nutrient removal, but little is known about their efficiency for the removal of emerging contaminants such as antimicrobial resistance genes (ARGs). Vegetative Filter Strip Modeling System (VFSMOD) was used to simulate the efficiency of VFS in this regard. Several studies demonstrated the ability of VFSMOD to predict reductions in runoff volume and sediment concentration moving through the filters. The objectives of this study were to calibrate the VFSMOD with experimental data and assess the efficiency of the model in simulating the filter behavior in removing ARGs (ermB) and tylosin. The experimental data were obtained from a prior study conducted at the University of Nebraska (UNL) Rogers Memorial Farm. Three treatment factors were tested in the experiments, including manure amendment, narrow grass hedges and rainfall events. Sediment Delivery Ratio (SDR) was defined as the filter efficiency and the related experimental and model values were compared to each other. The VFS Model generally agreed with the experimental results and as a result, the model was used for predicting filter efficiencies when the runoff data are not available. Narrow Grass Hedges (NGH) were shown to be effective in reducing tylosin and ARGs concentration. The simulation showed that the filter efficiency in removing ARGs is different for different soil types and filter lengths. There is an optimum length for the filter strip that produces minimum runoff volume. Based on the model results increasing the length of the filter by 1-meter leads to higher efficiency but widening beyond that decreases the efficiency. The VFSMOD, which was proved to work well in estimation of VFS trapping efficiency, showed confirming results for ARG removal.

Keywords: antimicrobial resistance genes, emerging contaminants, narrow grass hedges, vegetative filter strips, vegetative filter strip modeling system

Procedia PDF Downloads 100

Authors: Keunhong Chae, Seokho Yoon

Abstract:

Recently, the global navigation satellite system (GNSS) such as Galileo and GPS is employing more satellites to provide a higher degree of accuracy for the location service, thus calling for a more efficient signaling scheme among the satellites used in the overall GNSS network. In that the network throughput is improved, the spatial diversity can be one of the efficient signaling schemes; however, it requires multiple antenna that could cause a significant increase in the complexity of the GNSS. Thus, a diversity scheme called the cooperative signaling was proposed, where the virtual multiple-input multiple-output (MIMO) signaling is realized with using only a single antenna in the transmit satellite of interest and with modeling the neighboring satellites as relay nodes. The main drawback of the cooperative signaling is that the relay nodes receive the transmitted signal at different time instants, i.e., they operate in an asynchronous way, and thus, the overall performance of the GNSS network could degrade severely. To tackle the problem, several modified cooperative signaling schemes were proposed; however, all of them are difficult to implement due to a signal decoding at the relay nodes. Although the implementation at the relay nodes could be simpler to some degree by employing the time-reversal and conjugation operations instead of the signal decoding, it would be more efficient if we could implement the operations of the relay nodes at the source node having more resources than the relay nodes. So, in this paper, we propose a novel cooperative signaling scheme, where the data signals are combined in a unique way at the source node, thus obviating the need of the complex operations such as signal decoding, time-reversal and conjugation at the relay nodes. The numerical results confirm that the proposed scheme provides the same performance in the cooperative diversity and the bit error rate (BER) as the conventional scheme, while reducing the complexity at the relay nodes significantly. Acknowledgment: This work was supported by the National GNSS Research Center program of Defense Acquisition Program Administration and Agency for Defense Development.

Keywords: global navigation satellite network, cooperative signaling, data combining, nodes

Procedia PDF Downloads 257

Authors: Adedayo Racheal Agbonna

Abstract:

The rising level of graduate unemployment in Nigeria has brought about the introduction of entrepreneurship education as a career option for self–reliance and self-employment. Sequel to this, it is important to have an understanding of the determining factors of entrepreneurial intention. Therefore this research empirically investigated the influence of entrepreneurship education on entrepreneurial intention of undergraduate students of selected universities in Ogun State, Nigeria. The study is significant to researchers, university policy makers, and the government. Survey research design was adopted in the study. The population consisted of 17,659 final year undergraduate students universities in Ogun State. The study adopted stratified and random sampling technique. The table of sample size determination was used to determine the sample size for this study at 95% confidence level and 5% margin error to arrive at a sample size of 1877 respondents. The elements of population were 400 level students of the selected universities. A structured questionnaire titled 'Entrepreneurship Education and students’ Entrepreneurial intention' was administered. The result of the reliability test had the following values 0.716, 0.907 and 0.949 for infrastructure, perceived university support, and entrepreneurial intention respectively. In the same vein, from the construct validity test, the following values were obtained 0.711, 0.663 and 0.759 for infrastructure, perceived university support and entrepreneurial intention respectively. Findings of this study revealed that each of the entrepreneurship education variables significantly affected intention University infrastructure B= -1.200, R²=0.679, F (₁,₁₈₇₅) = 3958.345, P < 0.05) Perceived University Support B= -1.027, R²=0.502, F(₁,₁₈₇₅) = 1924.612, P < 0.05). The perception of respondents in public university and private university on entrepreneurship education have a statistically significant difference [F(₁,₁₈₇₅) = 134.614, p < 0.05) α F(₁,₁₈₇₅) = 363.439]. The study concluded that entrepreneurship education positively influenced entrepreneurial intention of undergraduate students in Ogun State, Nigeria. Also, university infrastructure and perceived university support have negative and significant effect on entrepreneurial intention. The study recommended that to promote entrepreneurial intention of university undergraduate students, infrastructures and the university support that can arouse entrepreneurial intention of students should be put in place.

Keywords: entrepreneurship education, entrepreneurial intention, perceived university support, university infrastructure

Procedia PDF Downloads 192

Authors: Nia Mair Fry, Matthew Profit, Chenfeng Li

Abstract:

This work focuses on the development and implementation of a fully implicit-implicit, coupled mechanical deformation and porous flow, finite element software tool. The fully implicit software accurately predicts classical fundamental analytical solutions such as the Terzaghi consolidation problem. Furthermore, it can capture other analytical solutions less well known in the literature, such as Gibson’s sedimentation rate problem and Coussy’s problems investigating wellbore stability for poroelastic rocks. The mechanical volume strains are transferred to the porous flow governing equation in an implicit framework. This will overcome some of the many current industrial issues, which use explicit solvers for the mechanical governing equations and only implicit solvers on the porous flow side. This can potentially lead to instability and non-convergence issues in the coupled system, plus giving results with an accountable degree of error. The specification of a fully monolithic implicit-implicit coupled porous media code sees the solution of both seepage-mechanical equations in one matrix system, under a unified time-stepping scheme, which makes the problem definition much easier. When using an explicit solver, additional input such as the damping coefficient and mass scaling factor is required, which are circumvented with a fully implicit solution. Further, improved accuracy is achieved as the solution is not dependent on predictor-corrector methods for the pore fluid pressure solution, but at the potential cost of reduced stability. In testing of this fully monolithic porous media code, there is the comparison of the fully implicit coupled scheme against an existing staggered explicit-implicit coupled scheme solution across a range of geotechnical problems. These cases include 1) Biot coefficient calculation, 2) consolidation theory with Terzaghi analytical solution, 3) sedimentation theory with Gibson analytical solution, and 4) Coussy well-bore poroelastic analytical solutions.

Keywords: coupled, implicit, monolithic, porous media

Procedia PDF Downloads 98

Authors: Yichin Chen

Abstract:

Taiwan is an island characterized by an active tectonics and high erosion rates. Monitoring the dynamic landscape of Taiwan is an important issue for disaster mitigation, geomorphological research, and watershed management. Long-term and high spatiotemporal landform data is essential for quantifying and simulating the geomorphological processes and developing warning systems. Recently, the advances in unmanned aerial vehicle (UAV) and computational photogrammetry technology have provided an effective way to rebuild and monitor the topography changes in high spatio-temporal resolutions. This study rebuilds the 30-years landform change in the Aiyuzi watershed in 1986-2017 by using the aerial photogrammetry-based techniques. The Aiyuzi watershed, located in central Taiwan and has an area of 3.99 Km², is famous for its frequent landslide and debris flow disasters. This study took the aerial photos by using UAV and collected multi-temporal historical, stereo photographs, taken by the Aerial Survey Office of Taiwan’s Forestry Bureau. To rebuild the orthoimages and digital surface models (DSMs), Pix4DMapper, a photogrammetry software, was used. Furthermore, to control model accuracy, a set of ground control points was surveyed by using eGPS. The results show that the generated DSMs have the ground sampling distance (GSD) of ~10 cm and ~0.3 cm from the UAV’s and historical photographs, respectively, and vertical error of ~1 m. By comparing the DSMs, there are many deep-seated landslides (with depth over 20 m) occurred on the upstream in the Aiyuzi watershed. Even though a large amount of sediment is delivered from the landslides, the steep main channel has sufficient capacity to transport sediment from the channel and to erode the river bed to ~20 m in depth. Most sediments are transported to the outlet of watershed and deposits on the downstream channel. This case study shows that UAV and photogrammetry technology are useful for topography change monitoring effectively.

Keywords: aerial photogrammetry, landslide, landform change, Taiwan

Procedia PDF Downloads 125

Authors: Safaa H. Sindi, Michael Roe

Abstract:

This project divides supply chain (SC) models into seven Eras, according to the evolution of the market’s needs throughout time. The five earliest Eras describe the emergence of supply chains, while the last two Eras are to be created. Research objectives: The aim is to generate the two latest Eras with their respective models that focus on the consumable goods. Era Six contains the Optimal Multidimensional Matrix (OMM) that incorporates most characteristics of the SC and allocates them into four quarters (Agile, Lean, Leagile, and Basic SC). This will help companies, especially (SMEs) plan their optimal SC route. Era Seven creates an Automated Multidimensional Model (AMM) which upgrades the matrix of Era six, as it accounts for all the supply chain factors (i.e. Offshoring, sourcing, risk) into an interactive system with Heuristic Learning that helps larger companies and industries to select the best SC model for their market. Methodologies: The data collection is based on a Fuzzy-Delphi study that analyses statements using Fuzzy Logic. The first round of Delphi study will contain statements (fuzzy rules) about the matrix of Era six. The second round of Delphi contains the feedback given from the first round and so on. Preliminary findings: both models are applicable, Matrix of Era six reduces the complexity of choosing the best SC model for SMEs by helping them identify the best strategy of Basic SC, Lean, Agile and Leagile SC; that’s tailored to their needs. The interactive heuristic learning in the AMM of Era seven will help mitigate error and aid large companies to identify and re-strategize the best SC model and distribution system for their market and commodity, hence increasing efficiency. Potential contributions to the literature: The problematic issue facing many companies is to decide which SC model or strategy to incorporate, due to the many models and definitions developed over the years. This research simplifies this by putting most definition in a template and most models in the Matrix of era six. This research is original as the division of SC into Eras, the Matrix of Era six (OMM) with Fuzzy-Delphi and Heuristic Learning in the AMM of Era seven provides a synergy of tools that were not combined before in the area of SC. Additionally the OMM of Era six is unique as it combines most characteristics of the SC, which is an original concept in itself.

Keywords: Leagile, automation, heuristic learning, supply chain models

Procedia PDF Downloads 363

Authors: Luis Alvarado, Victor Poblete, Isaac Gonzalez, Yetzabeth Gonzalez

Abstract:

In MIREX 2016 (http://www.music-ir.org/mirex), the deep neural network (DNN)-Deep Chroma Extractor, proposed by Korzeniowski and Wiedmer, reached the highest score in an audio chord recognition task. In the present paper, this tool is assessed under acoustic reverberant environments and distinct source-microphone distances. The evaluation dataset comprises The Beatles and Queen datasets. These datasets are sequentially re-recorded with a single microphone in a real reverberant chamber at four reverberation times (0 -anechoic-, 1, 2, and 3 s, approximately), as well as four source-microphone distances (32, 64, 128, and 256 cm). It is expected that the performance of the trained DNN will dramatically decrease under these acoustic conditions with signals degraded by room reverberation and distance to the source. Recently, the effect of the bio-inspired Locally-Normalized Cepstral Coefficients (LNCC), has been assessed in a text independent speaker verification task using speech signals degraded by additive noise at different signal-to-noise ratios with variations of recording distance, and it has also been assessed under reverberant conditions with variations of recording distance. LNCC showed a performance so high as the state-of-the-art Mel Frequency Cepstral Coefficient filters. Based on these results, this paper proposes a variation of locally-normalized triangular filters called Locally-Normalized Quarter Tone (LNQT) filters. By using the LNQT spectrogram, robustness improvements of the trained Deep Chroma Extractor are expected, compared with classical triangular filters, and thus compensating the music signal degradation improving the accuracy of the chord recognition system.

Keywords: chord recognition, deep neural networks, feature extraction, music information retrieval

Procedia PDF Downloads 193

Authors: Sanjay Singh, Karunanithi Priyanka, Ramoji Kosuru, Raju Prasad Sharma

Abstract:

Herbal drugs are well known for their mixed pharmacological activities with the benefit of no harmful side effects. The use of herbal drugs is limited because of their higher dose requirement, frequent drug administration, poor bioavailability of phytochemicals and delayed onset of action. Ficus religiosa, a potent anti-oxidant plant useful in the treatment of diabetes and cancer was selected for the study. Solid lipid nanoparticles (SLN) of Ficus religiosa extract was developed for the enhancement in oral bioavailability of stigmasterol and β-sitosterol-d-glucoside, principal components present in the extract. Hot homogenization followed by ultrasonication method was used to develop extract loaded SLN. Developed extract loaded SLN were characterized for particle size, PDI, zeta potential, entrapment efficiency, in vitro drug release and kinetics, fourier transform infra-red spectroscopy, differential scanning calorimetry, powder X-ray diffractrometry and stability studies. Entrapment efficiency of optimized extract loaded SLN was found to be 68.46 % (56.13 % of stigmasterol and 12.33 % of β-sitosteryl-d-glucoside, respectively). RP HPLC method development was done for simultaneous estimation of stigmasterol and β-sitosterol-d-glucoside in Ficus religiosa extract in rat plasma. Bioavailability studies were carried out for extract in suspension form and optimized extract loaded SLN. AUC of stigmasterol and β-sitosterol-d-glucoside were increased by 6.7-folds by 9.2-folds, respectively in rats treated with extract loaded SLN compared to extract suspension. Also, Cmax of stigmasterol and β-sitosterol-d-glucoside were increased by 4.3-folds by 3.9-folds, respectively in rats treated with extract loaded SLN compared to extract suspension. Mean residence times (MRT) for stigmasterol were found to be 12.3 ± 0.67 hours from extract and 7.4 ± 2.1 hours from SLN and for β-sitosterol-d-glucoside, 10.49 ± 2.9 hours from extract and 6.4 ± 0.3 hours from SLN. Hence, it was concluded that SLN enhanced the bioavailability and reduced the MRT of stigmasterol and β-sitosterol-d-glucoside in Ficus religiosa extract which in turn may lead to reduction in dose of Ficus religiosa extract, prolonged duration of action and also enhanced therapeutic efficacy.

Keywords: Ficus religiosa, phytosterolins, bioavailability, solid lipid nanoparticles, stigmasterol and β-sitosteryl-d-glucoside

Procedia PDF Downloads 440

Authors: Luis Amador Jimenez, Md. Shohel Amin

Abstract:

Pavement performance models are based on projections of observed traffic loads, which makes uncertain to study funding strategies in the long run if history does not repeat. Neural networks can be used to estimate deterioration rates but the learning rate and momentum have not been properly investigated, in addition, economic evolvement could change traffic flows. This study addresses both issues through a case study for roads of Montreal that simulates traffic for a period of 50 years and deals with the measurement error of the pavement deterioration model. Travel demand models are applied to simulate annual average daily traffic (AADT) every 5 years. Accumulated equivalent single axle loads (ESALs) are calculated from the predicted AADT and locally observed truck distributions combined with truck factors. A back propagation Neural Network (BPN) method with a Generalized Delta Rule (GDR) learning algorithm is applied to estimate pavement deterioration models capable of overcoming measurement errors. Linear programming of lifecycle optimization is applied to identify M&R strategies that ensure good pavement condition while minimizing the budget. It was found that CAD 150 million is the minimum annual budget to good condition for arterial and local roads in Montreal. Montreal drivers prefer the use of public transportation for work and education purposes. Vehicle traffic is expected to double within 50 years, ESALS are expected to double the number of ESALs every 15 years. Roads in the island of Montreal need to undergo a stabilization period for about 25 years, a steady state seems to be reached after.

Keywords: pavement management system, traffic simulation, backpropagation neural network, performance modeling, measurement errors, linear programming, lifecycle optimization

Procedia PDF Downloads 429

Authors: Eric Dede, Marcus Tindall, John W. Cherrie, Steve Hankin, Christopher Collins

Abstract:

Current exposure models used in contaminated land risk assessment are highly conservative. Use of these models may lead to over-estimation of actual exposures, possibly resulting in negative financial implications due to un-necessary remediation. Thus, we are carrying out a study seeking to improve our understanding of human exposure to selected toxic elements in soil: arsenic (As), cadmium (Cd), chromium (Cr), nickel (Ni), and lead (Pb) resulting from allotment land-use. The study employs biomonitoring and physiologically-based pharmacokinetic (PBPK) modelling to quantify human exposure to these elements. We recruited 37 allotment users (adults > 18 years old) in Scotland, UK, to participate in the study. Concentrations of the elements (and their bioaccessibility) were measured in allotment samples (soil and allotment produce). Amount of produce consumed by the participants and participants’ biological samples (urine and blood) were collected for up to 12 consecutive months. Ethical approval was granted by the University of Reading Research Ethics Committee. PBPK models (coded in MATLAB) were used to estimate the distribution and accumulation of the elements in key body compartments, thus indicating the internal body burden. Simulating low element intake (based on estimated ‘doses’ from produce consumption records), predictive models suggested that detection of these elements in urine and blood was possible within a given period of time following exposure. This information was used in planning biomonitoring, and is currently being used in the interpretation of test results from biological samples. Evaluation of the models is being carried out using biomonitoring data, by comparing model predicted concentrations and measured biomarker concentrations. The PBPK models will be used to generate bioavailability values, which could be incorporated in contaminated land exposure models. Thus, the findings from this study will promote a more sustainable approach to contaminated land management.

Keywords: biomonitoring, exposure, PBPK modelling, toxic elements

Procedia PDF Downloads 288

Authors: Cristy Stagnar, Nina Hubig, Diana Ivankovic

Abstract:

The epigenome is a compelling candidate for mediating long-term responses to environmental effects modifying disease risk. The main goal of this research is to develop a machine learning-based DNA methylation score, which will be valuable in delineating the unique contribution of paternal epigenetic modifications to the germline impacting childhood health outcomes. It will also be a useful tool in validating self-reports of nonsmoking and in adjusting epigenome-wide DNA methylation association studies for this early-life exposure. Using secondary data from two population-based methylation profiling studies, our DNA methylation score is based on CpG DNA methylation measurements from cord blood gathered from children whose fathers smoked pre- and peri-conceptually. Each child’s mother and father fell into one of three class labels in the accompanying questionnaires -never smoker, former smoker, or current smoker. By applying different machine learning algorithms to the accessible resource for integrated epigenomic studies (ARIES) sub-study of the Avon longitudinal study of parents and children (ALSPAC) data set, which we used for training and testing of our model, the best-performing algorithm for classifying the father smoker and mother never smoker was selected based on Cohen’s κ. Error in the model was identified and optimized. The final DNA methylation score was further tested and validated in an independent data set. This resulted in a linear combination of methylation values of selected probes via a logistic link function that accurately classified each group and contributed the most towards classification. The result is a unique, robust DNA methylation score which combines information on DNA methylation and early life exposure of offspring to paternal smoking during pregnancy and which may be used to examine the paternal contribution to offspring health outcomes.

Keywords: epigenome, health outcomes, paternal preconception environmental exposures, supervised machine learning

Procedia PDF Downloads 161

Authors: Mohammed Seyam, Faridah Othman, Ahmed El-Shafie

Abstract:

The early warning of high stream flow events (HSF) and floods is an important aspect in the management of surface water and rivers systems. This process can be performed using either process-based models or data driven-based models such as artificial intelligence (AI) techniques. The main goal of this study is to develop efficient AI-based model for predicting the real-time hourly stream flow (Q) and apply it as early warning tool of HSF and floods in the downstream area of the Selangor River basin, taken here as a paradigm of humid tropical rivers in Southeast Asia. The performance of AI-based models has been improved through the integration of the lag time (Lt) estimation in the modelling process. A total of 8753 patterns of Q, water level, and rainfall hourly records representing one-year period (2011) were utilized in the modelling process. Six hydrological scenarios have been arranged through hypothetical cases of input variables to investigate how the changes in RF intensity in upstream stations can lead formation of floods. The initial SF was changed for each scenario in order to include wide range of hydrological situations in this study. The performance evaluation of the developed AI-based model shows that high correlation coefficient (R) between the observed and predicted Q is achieved. The AI-based model has been successfully employed in early warning throughout the advance detection of the hydrological conditions that could lead to formations of floods and HSF, where represented by three levels of severity (i.e., alert, warning, and danger). Based on the results of the scenarios, reaching the danger level in the downstream area required high RF intensity in at least two upstream areas. According to results of applications, it can be concluded that AI-based models are beneficial tools to the local authorities for flood control and awareness.

Keywords: floods, stream flow, hydrological modelling, hydrology, artificial intelligence

Procedia PDF Downloads 217

Authors: Massimo Miccoli, Luca Marangoni, Alberto Aniello Scaringi, Alessandro Marceddu, Alessandro Amicone

Abstract:

The susceptibility of deep neural networks (DNNs) to adversarial manipulations is a recognized challenge within the computer vision domain. Adversarial examples, crafted by adding subtle yet malicious alterations to benign images, exploit this vulnerability. Various defense strategies have been proposed to safeguard DNNs against such attacks, stemming from diverse research hypotheses. Building upon prior work, our approach involves the utilization of autoencoder models. Autoencoders, a type of neural network, are trained to learn representations of training data and reconstruct inputs from these representations, typically minimizing reconstruction errors like mean squared error (MSE). Our autoencoder was trained on a dataset of benign examples; learning features specific to them. Consequently, when presented with significantly perturbed adversarial examples, the autoencoder exhibited high reconstruction errors. The architecture of the autoencoder was tailored to the dimensions of the images under evaluation. We considered various image sizes, constructing models differently for 256x256 and 512x512 images. Moreover, the choice of the computer vision model is crucial, as most adversarial attacks are designed with specific AI structures in mind. To mitigate this, we proposed a method to replace image-specific dimensions with a structure independent of both dimensions and neural network models, thereby enhancing robustness. Our multi-modal autoencoder reconstructs the spectral representation of images across the red-green-blue (RGB) color channels. To validate our approach, we conducted experiments using diverse datasets and subjected them to adversarial attacks using models such as ResNet50 and ViT_L_16 from the torch vision library. The autoencoder extracted features used in a classification model, resulting in an MSE (RGB) of 0.014, a classification accuracy of 97.33%, and a precision of 99%.

Keywords: adversarial attacks, malicious images detector, binary classifier, multimodal transformer autoencoder

Procedia PDF Downloads 34

Authors: Mehwish Durrani, Rubina Nazli, Muhammad Abubakr, Muhammad Shafiq

Abstract:

Objectives: To evaluate the high socio-economic status, urbanization, and decrease ambulation can lead to early osteoporosis in women reporting from Peshawar region. Study Design: Descriptive cross-sectional study was done. Sample size was 100 subjects, using 30% proportion of osteoporosis, 95% confidence level, and 9% margin of error under WHO software for sample size determination. Place and Duration of study: This study was carried out in the tertiary referral health care facilities of Peshawar viz PGMI Hayatabad Medical Complex, Peshawar, Khyber Pakhtunkhwa Province, Pakistan. Ethical approval for the study was taken from the Institutional Ethical Research board (IERD) at Post Graduate Medical Institute, Hayatabad Medical Complex, and Peshawar.The study was done in six months time period. Patients and Methods: Levels of CTX1 as a marker of bone degradation in radiographically assessed perimenopausal women was determined. These females were randomly selected and screened for osteoporosis. Hemoglobin in gm/dl, ESR by Westergren method as millimeter in 1 hour, Serum Ca mg/dl, Serum alkaline Phosphatase international units per liter radiographic grade of osteoporosis according to Singh index as 1-6 and CTX 1 level in pg/ml. Results: High levels of CTX1 was observed in perimenopausal osteoporotic women which were radiographically diagnosed as osteoporotic patients. The High socio-economic class also predispose to osteoporosis. Decrease ambulation another risk factor showed significant association with the increased levels of CTX1. Conclusion: The results of this study propose that minimum ambulation and high socioeconomic class both had significance association with the increase levels of serum CTX1, which in turn will lead to osteoporosis and to its complications.

Keywords: osteoporosis, CTX1, perimenopausal women, Hayatabad Medical Complex, Khyberpuktoonkhwa

Procedia PDF Downloads 304

Authors: Zintle Sikhunyana

Abstract:

Management of public finance in many countries such as South Africa is affected by political decisions and by policies around fiscal decentralization amongst the government spheres. Economic success is said to be determined by efficient management of public finance and by the policies or strategies that are implemented to support efficient public finance management. Policymakers focus on pay attention to how economic policies have been implemented and how they are directed into ensuring stable development. This will allow policymakers to address economic challenges through the usage of fiscal policy parameters that are linked to the achieved rate of economic growth and development. Efficient public finance management reduces the likelihood of corruption and corruption is said to have negative effects on economic growth and development. Corruption in public finance refers to an act of using funds for personal benefits. To achieve macroeconomic objectives, governments make use of government expenditure and government expenditure is financed through tax revenue. The main aim of this paper is to investigate the potential impact of public finance management on economic growth and development in South Africa. The secondary data obtained from the South African Reserve Bank (SARB) and World Bank for 1980- 2020 has been utilized to achieve the research objectives. To test the impact of public finance management on economic growth and development, the study will use Seeming Unrelated Regression Equation (SURE) Modelling that allows researchers to model multiple equations with interdependent variables. The advantages of using SUR are that it efficiently allows estimation of relationships between variables by combining information on different equations and SUR test restrictions that involve parameters in different equations. The findings have shown that there is a positive relationship between efficient public finance management and economic growth/development. The findings also show that efficient public finance management has an indirect positive impact on economic growth and development. Corruption has a negative impact on economic growth and development. It results in an efficient allocation of government resources and thereby improves economic growth and development. The study recommends that governments who aim to stimulate economic growth and development should target and strengthen public finance management policies or strategies.

Keywords: corruption, economic growth, economic development, public finance management, fiscal decentralization

Procedia PDF Downloads 168

Authors: Noreen Noreen, Aamir Ijaz, Hamza Akhtar

Abstract:

Background: Screening plays a major role to detect chromosomal abnormalities, Down syndrome, neural tube defects and other inborn diseases of the newborn. Serum biomarkers in the second trimester are useful in determining risk of most common chromosomal anomalies; these test include Alpha-fetoprotein (AFP), Human chorionic gonadotropin (hCG), Unconjugated Oestriol (UEȝ)and inhibin-A. Quadruple biomarkers are worth test in diagnosing the congenital pathology during pregnancy, these procedures does not form a part of routine health care of pregnant women in Pakistan, so the median value is lacking for population in Pakistan. Objective: To determine median values of biochemical maternal serum markers in local population during second trimester maternal screening. Study settings: Department of Chemical Pathology and Endocrinology, Armed Forces Institute of Pathology (AFIP) Rawalpindi. Methods: Cross-Sectional study for estimation of reference values. Non-probability consecutive sampling, 155 healthy pregnant women, of 30-40 years of age, will be included. As non-parametric statistics will be used, the minimum sample size is 120. Result: Total 155 women were enrolled into this study. The age of all women enrolled ranged from 30 to39 yrs. Among them, 39 per cent of women were less than 34 years. Mean maternal age 33.46±2.35 SD and maternal body weight were 54.98±2.88. Median value of quadruple markers calculated from 15-18th week of gestation that will be used for calculation of MOM for screening of trisomy21 in this gestational age. Median value at 15 week of gestation were observed hCG 36650 mIU/ml, AFP 23.3 IU/ml, UEȝ 3.5 nmol/L, InhibinA 198 ng/L, at 16 week of gestation hCG 29050 mIU/ml, AFP 35.4 IU/ml, UEȝ 4.1 nmol/L, InhibinA 179 ng/L, at 17 week of gestation hCG 28450 mIU/ml, AFP 36.0 IU/ml, UEȝ 6.7 nmol/L, InhibinA 176 ng/L and at 18 week of gestation hCG 25200 mIU/ml, AFP 38.2 IU/ml, UEȝ 8.2 nmol/L, InhibinA 190 ng/L respectively.All the comparisons were significant (p-Value <0.005) with 95% confidence Interval (CI) and level of significance of study set by going through literature and set at 5%. Conclusion: The median values for these four biomarkers in Pakistani pregnant women can be used to calculate MoM.

Keywords: screening, down syndrome, quadruple test, second trimester, serum biomarkers

Procedia PDF Downloads 149

Authors: Vishal Pareek, Shubham Gupta, Sushil Chandra Jain

Abstract:

With increasing high-speed computation demand the power consumption, heat dissipation and chip size issues are posing challenges for logic design with conventional technologies. Recovery of bit loss and bit errors is other issues that require reversibility and fault tolerance in the computation. The reversible computing is emerging as an alternative to conventional technologies to overcome the above problems and helpful in a diverse area such as low-power design, nanotechnology, quantum computing. Bit loss issue can be solved through unique input-output mapping which require reversibility and bit error issue require the capability of fault tolerance in design. In order to incorporate reversibility a number of combinational reversible logic based circuits have been developed. However, very few sequential reversible circuits have been reported in the literature. To make the circuit fault tolerant, a number of fault model and test approaches have been proposed for reversible logic. In this paper, we have attempted to incorporate fault tolerance in sequential reversible building blocks such as D flip-flop, T flip-flop, JK flip-flop, R-S flip-flop, Master-Slave D flip-flop, and double edge triggered D flip-flop by making them parity preserving. The importance of this proposed work lies in the fact that it provides the design of reversible sequential circuits completely testable for any stuck-at fault and single bit fault. In our opinion our design of reversible building blocks is superior to existing designs in term of quantum cost, hardware complexity, constant input, garbage output, number of gates and design of online testable D flip-flop have been proposed for the first time. We hope our work can be extended for building complex reversible sequential circuits.

Keywords: parity preserving gate, quantum computing, fault tolerance, flip-flop, sequential reversible logic

Procedia PDF Downloads 514

Authors: Seada Hussen, Frie Ayalew

Abstract:

Integrating different energy resources, like solar PV and hydro, is used to ensure reliable power to rural communities like Hara village in Ethiopia. Hybrid power system offers power supply for rural villages by providing an alternative supply for the intermittent nature of renewable energy resources. The intermittent nature of renewable energy resources is a challenge to electrifying rural communities in a sustainable manner with solar resources. Major rural villages in Ethiopia are suffering from a lack of electrification, that cause our people to suffer deforestation, travel for long distance to fetch water, and lack good services like clinic and school sufficiently. The main objective of this project is to provide a balanced, stable, reliable supply for Hara village, Ethiopia using solar power with a pumped hydro energy storage system. The design of this project starts by collecting data from villages and taking solar irradiance data from NASA. In addition to this, geographical arrangement and location are also taken into consideration. After collecting this, all data analysis and cost estimation or optimal sizing of the system and comparison of solar with pumped hydro and solar with battery storage system is done using Homer Software. And since solar power only works in the daytime and pumped hydro works at night time and also at night and morning, both load will share to cover the load demand; this need controller designed to control multiple switch and scheduling in this project fuzzy logic controller is used to control this scenario. The result of the simulation shows that solar with pumped hydro energy storage system achieves good results than with a battery storage system since the comparison is done considering storage reliability, cost, storage capacity, life span, and efficiency.

Keywords: pumped hydro storage, solar energy, solar PV, battery energy storage, fuzzy logic controller

Procedia PDF Downloads 37

Authors: Ghufran Ahmed, Muhammad Osama Siddiqui, Shahbaz Siddiqui, Rauf Ahmad Shams Malick, Faisal Khan, Mubashir Khan

Abstract:

In this paper, a machine learning-based approach for early prediction of diseases in cows is proposed. Different ML algos are applied to extract useful patterns from the available dataset. Technology has changed today’s world in every aspect of life. Similarly, advanced technologies have been developed in livestock and dairy farming to monitor dairy cows in various aspects. Dairy cattle monitoring is crucial as it plays a significant role in milk production around the globe. Moreover, it has become necessary for farmers to adopt the latest early prediction technologies as the food demand is increasing with population growth. This highlight the importance of state-ofthe-art technologies in analyzing how important technology is in analyzing dairy cows’ activities. It is not easy to predict the activities of a large number of cows on the farm, so, the system has made it very convenient for the farmers., as it provides all the solutions under one roof. The cattle industry’s productivity is boosted as the early diagnosis of any disease on a cattle farm is detected and hence it is treated early. It is done on behalf of the machine learning output received. The learning models are already set which interpret the data collected in a centralized system. Basically, we will run different algorithms on behalf of the data set received to analyze milk quality, and track cows’ health, location, and safety. This deep learning algorithm draws patterns from the data, which makes it easier for farmers to study any animal’s behavioral changes. With the emergence of machine learning algorithms and the Internet of Things, accurate tracking of animals is possible as the rate of error is minimized. As a result, milk productivity is increased. IoT with ML capability has given a new phase to the cattle farming industry by increasing the yield in the most cost-effective and time-saving manner.

Keywords: IoT, machine learning, health care, dairy cows

Procedia PDF Downloads 18

Authors: Abidemi C. Adegboye, Samuel Iweriebor

Abstract:

The primary link between financial institutions and economic performance is the provision of resources by these institutions to businesses in order to drive enterprise expansion, sustainability, and development. In this study, the role of access to finance in driving innovations and productivity in Nigerian SMEs is investigated using the World Bank Enterprise Survey (ES) dataset. Innovation is defined based on the ES analysis using five compositions including product, method, organisational, use of foreign-licensed technology, and spending on R&D. The study considers finance in terms of source in meeting investment needs and in terms of access. Moreover, finance access is categorized as external and internal to a firm with each having different implications. The research methodology adopted a survey analysis based on the 2014 World Bank Enterprise Survey of 19 states in Nigeria. The survey comprised over 10,000 manufacturing and services firms, both at the small scale and medium scale levels. The logit estimation technique is used to estimate the relationships in the study. The results from the empirical analysis show that in general, access to finance drives SME innovation in Nigeria. In particular, ease of accessing bank loans and credit is shown to be the strongest positive force in driving all types of innovation among SMEs in Nigeria. In the same vein, the type of finance source for investment matters in terms of how it affects innovation: it is shown that both internal and external sources improve investment in product, process, and organisational innovation, but only external financing has effect on R&D spending and use of foreign licensed technology. Overall spending on R&D is only driven by access to external finance by the SMEs. For productivity, the results show that while structure of financing investment improves productivity, increased access to finance may actually lead to productivity decline among SMEs in Nigeria. There is a need for the financial system to evolve structures to increase fund availability to SMEs in Nigeria, especially for the purpose of innovation investment.

Keywords: access to finance, financing investment, innovation, productivity, SMEs

Procedia PDF Downloads 326

Authors: Bougema Theodore Ntenkeh, Chi-bikom Barbara Kyien

Abstract:

The reduction of poverty and hunger sits at the heart of the United Nations 2030 Agenda for Sustainable Development, and are the first two of the Sustainable Development Goals. The World Food Day celebrated on the 16th of October every year, highlights the need for people to have physical and economic access at all times to enough nutritious and safe food to live a healthy and active life; while the world poverty day celebrated on the 17th of October is an opportunity to acknowledge the struggle of people living in poverty, a chance for them to make their concerns heard, and for the community to recognize and support poor people in their fight against poverty. The association between household food security and poverty reduction is not only sparse in Cameroon but mostly qualitative. The paper therefore investigates the effect of household food security on poverty reduction in Cameroon quantitatively using data from the Cameroon Household Consumption Survey collected by the Government Statistics Office. The methodology employed five indicators of household food security using the Multiple Correspondence Analysis and poverty is captured as a dummy variable. Using a control function technique, with pre and post estimation test for robustness, the study postulates that household food security has a positive and significant effect on poverty reduction in Cameroon. A unit increase in the food security score reduces the probability of the household being poor by 31.8%, and this effect is statistically significant at 1%. The result further illustrates that the age of the household head and household size increases household poverty while households residing in urban areas are significantly less poor. The paper therefore recommends that households should diversify their food intake to enhance an effective supply of labour in the job market as a strategy to reduce household poverty. Furthermore, family planning methods should be encouraged as a strategy to reduce birth rate for an equitable distribution of household resources including food while the government of Cameroon should also develop the rural areas given that trend in urbanization are associated with the concentration of productive economic activities, leading to increase household income, increased household food security and poverty reduction.

Keywords: food security, poverty reduction, SDGs, Cameroon

Procedia PDF Downloads 35

Authors: Sehrish Qayyum

Abstract:

Active military power contention is shifting to economic and cyberwar to retain hegemony. Attuned Pestle analysis confirms that structural stress of hegemon’s power loss drives a containment approach towards caging actions. Ongoing diplomatic, asymmetric, proxy and direct wars are increasing stress hegemon’s power retention due to tangled military and economic alliances. It creates the condition of catalepsy with defective reflexive control which affects the core warfare operations. When one’s own power is doubted it gives power to one’s own doubt to ruin all planning either done with superlative cost-benefit analysis. Strategically calculated estimation of Hegemon’s power game since the early WWI to WWII, WWII-to Cold War and then to the current era in three chronological periods exposits that Thucydides’s trap became the reason for war broke out. Thirst for power is the demise of imagination and cooperation for better sense to prevail instead it drives ashes to dust. Pestle analysis is a wide array of evaluation from political and economic to legal dimensions of the state matters. It helps to develop the Pacification and Security Policy Plan (PSPP) to avoid hegemon’s structural stress of power loss in fact, in turn, creates an alliance with maximum amicable outputs. PSPP may serve to regulate and pause the hurricane of power clashes. PSPP along with a strategic work plan is based on Pestle analysis to deal with any conceivable war condition and approach for saving international peace. Getting tangled into self-imposed epistemic dilemmas results in regret that becomes the only option of performance. It is a generic application of probability tests to find the best possible options and conditions to develop PSPP for any adversity possible so far. Innovation in expertise begets innovation in planning and action-plan to serve as a rheostat approach to deal with any plausible power clash.

Keywords: alliance, hegemon, pestle analysis, pacification and security policy plan, security

Procedia PDF Downloads 84

Authors: Gayathri Nagarajan, L. D. Dhinesh Babu

Abstract:

Health care is one of the prominent industries that generate voluminous data thereby finding the need of machine learning techniques with big data solutions for efficient processing and prediction. Missing data, incomplete data, real time streaming data, sensitive data, privacy, heterogeneity are few of the common challenges to be addressed for efficient processing and mining of health care data. In comparison with other applications, accuracy and fast processing are of higher importance for health care applications as they are related to the human life directly. Though there are many machine learning techniques and big data solutions used for efficient processing and prediction in health care data, different techniques and different frameworks are proved to be effective for different applications largely depending on the characteristics of the datasets. In this paper, we present a framework that uses ensemble machine learning technique gradient boosted trees for data classification in health care big data. The framework is built on Spark platform which is fast in comparison with other traditional frameworks. Unlike other works that focus on a single technique, our work presents a comparison of six different machine learning techniques along with gradient boosted trees on datasets of different characteristics. Five benchmark health care datasets are considered for experimentation, and the results of different machine learning techniques are discussed in comparison with gradient boosted trees. The metric chosen for comparison is misclassification error rate and the run time of the algorithms. The goal of this paper is to i) Compare the performance of gradient boosted trees with other machine learning techniques in Spark platform specifically for health care big data and ii) Discuss the results from the experiments conducted on datasets of different characteristics thereby drawing inference and conclusion. The experimental results show that the accuracy is largely dependent on the characteristics of the datasets for other machine learning techniques whereas gradient boosting trees yields reasonably stable results in terms of accuracy without largely depending on the dataset characteristics.

Keywords: big data analytics, ensemble machine learning, gradient boosted trees, Spark platform

Procedia PDF Downloads 210

Authors: Lina Wu, Jia Liu, Ye Li

Abstract:

The goal of this project is to investigate constant properties (called the Liouville-type Problem) for a p-stable map as a local or global minimum of a p-energy functional where the domain is a Euclidean space and the target space is a closed half-ellipsoid. The First and Second Variation Formulas for a p-energy functional has been applied in the Calculus Variation Method as computation techniques. Stokes’ Theorem, Cauchy-Schwarz Inequality, Hardy-Sobolev type Inequalities, and the Bochner Formula as estimation techniques have been used to estimate the lower bound and the upper bound of the derived p-Harmonic Stability Inequality. One challenging point in this project is to construct a family of variation maps such that the images of variation maps must be guaranteed in a closed half-ellipsoid. The other challenging point is to find a contradiction between the lower bound and the upper bound in an analysis of p-Harmonic Stability Inequality when a p-energy minimizing map is not constant. Therefore, the possibility of a non-constant p-energy minimizing map has been ruled out and the constant property for a p-energy minimizing map has been obtained. Our research finding is to explore the constant property for a p-stable map from a Euclidean space into a closed half-ellipsoid in a certain range of p. The certain range of p is determined by the dimension values of a Euclidean space (the domain) and an ellipsoid (the target space). The certain range of p is also bounded by the curvature values on an ellipsoid (that is, the ratio of the longest axis to the shortest axis). Regarding Liouville-type results for a p-stable map, our research finding on an ellipsoid is a generalization of mathematicians’ results on a sphere. Our result is also an extension of mathematicians’ Liouville-type results from a special ellipsoid with only one parameter to any ellipsoid with (n+1) parameters in the general setting.

Keywords: Bochner formula, Calculus Stokes' Theorem, Cauchy-Schwarz Inequality, first and second variation formulas, Liouville-type problem, p-harmonic map

Procedia PDF Downloads 244

Authors: Michael A. Sprayberry, Vincent C. Paquit

Abstract:

Process parameter optimization in metal powder bed electron beam melting (MPBEBM) is crucial to ensure the technology's repeatability, control, and industry-continued adoption. Despite continued efforts to address the challenges via the traditional design of experiments and process mapping techniques, there needs to be more successful in an on-the-fly optimization framework that can be adapted to MPBEBM systems. Additionally, data-intensive physics-based modeling and simulation methods are difficult to support by a metal AM alloy or system due to cost restrictions. To mitigate the challenge of resource-intensive experiments and models, this paper introduces a Multi-Objective Reinforcement Learning (MORL) methodology defined as an optimization problem for MPBEBM. An off-policy MORL framework based on policy gradient is proposed to discover optimal sets of beam power (P) – beam velocity (v) combinations to maintain a steady-state melt pool depth and phase transformation. For this, an experimentally validated Eagar-Tsai melt pool model is used to simulate the MPBEBM environment, where the beam acts as the agent across the P – v space to maximize returns for the uncertain powder bed environment producing a melt pool and phase transformation closer to the optimum. The culmination of the training process yields a set of process parameters {power, speed, hatch spacing, layer depth, and preheat} where the state (P,v) with the highest returns corresponds to a refined process parameter mapping. The resultant objects and mapping of returns to the P-v space show convergence with experimental observations. The framework, therefore, provides a model-free multi-objective approach to discovery without the need for trial-and-error experiments.

Keywords: additive manufacturing, metal powder bed fusion, reinforcement learning, process parameter optimization

Procedia PDF Downloads 55

Authors: Tarcisio F. Leao, Bruno Utiyama, Jeison Fonseca, Eduardo Bock, Aron Andrade

Abstract:

This work presents a blood flow estimator based in Look-Up-Table (LUT) for control of Left Ventricular Assist Device (LVAD). This device has been used as bridge to transplantation or as destination therapy to treat patients with heart failure (HF). Destination Therapy application requires a high performance LVAD; thus, a stable control is important to keep adequate interaction between heart and device. LVAD control provides an adequate cardiac output while sustaining an appropriate flow and pressure blood perfusion, also described as physiologic control. Because thrombus formation and system reliability reduction, sensors are not desirable to measure these variables (flow and pressure blood). To achieve this, control systems have been researched to estimate blood flow. LVAD used in the study is composed by blood centrifugal pump, control, and power supply. This technique used pump and actuator (motor) parameters of LVAD, such as speed and electric current. Estimator relates electromechanical torque (motor or actuator) and hydraulic power (blood pump) via LUT. An in vitro Mock Loop was used to evaluate deviations between blood flow estimated and actual. A solution with glycerin (50%) and water was used to simulate the blood viscosity with hematocrit 45%. Tests were carried out with variation hematocrit: 25%, 45% and 58% of hematocrit, or 40%, 50% and 60% of glycerin in water solution, respectively. Test with bovine blood was carried out (42% hematocrit). Mock Loop is composed: reservoir, tubes, pressure and flow sensors, and fluid (or blood), beyond LVAD. Estimator based in LUT is patented, number BR1020160068363, in Brazil. Mean deviation is 0.23 ± 0.07 L/min for mean flow estimated. Larger mean deviation was 0.5 L/min considering hematocrit variation. This estimator achieved deviation adequate for physiologic control implementation. Future works will evaluate flow estimation performance in control system of LVAD.

Keywords: blood pump, flow estimator, left ventricular assist device, look-up-table

Procedia PDF Downloads 151