Search results for: hybrid genetic algorithms

Authors: U. Borasi, Amit Kr. Jain, Rakesh, Piyush Jain

Abstract:

Data collection, data preparation, model training, model evaluation, and deployment are all processes in a typical machine learning workflow. Training data needs to be gathered and organised. This often entails collecting a sizable dataset and cleaning it to remove or correct any inaccurate or missing information. Preparing the data for use in the machine learning model requires pre-processing it after it has been acquired. This often entails actions like scaling or normalising the data, handling outliers, selecting appropriate features, reducing dimensionality, etc. This pre-processed data is then used to train a model on some machine learning algorithm. After the model has been trained, it needs to be assessed by determining metrics like accuracy, precision, and recall, utilising a test dataset. Every time a new model is built, both data pre-processing and model training—two crucial processes in the Machine learning (ML) workflow—must be carried out. Thus, there are various Machine Learning algorithms that can be employed for every single approach to data pre-processing, generating a large set of combinations to choose from. Example: for every method to handle missing values (dropping records, replacing with mean, etc.), for every scaling technique, and for every combination of features selected, a different algorithm can be used. As a result, in order to get the optimum outcomes, these tasks are frequently repeated in different combinations. This paper suggests a simple architecture for organizing this largely produced “combination set of pre-processing steps and algorithms” into an automated workflow which simplifies the task of carrying out all possibilities.

Keywords: machine learning, automation, AUTOML, architecture, operator pool, configuration, scheduler

Procedia PDF Downloads 39

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 79

Authors: Margaret Boone Rappaport, Christopher J. Corbally

Abstract:

The ancient ape ancestral population from which living great ape and human species evolved had demographic features affecting their evolution. The population was large, had great genetic variability, and natural selection was effective at honing adaptations. The emerging populations of chimpanzees and humans were affected more by founder effects and genetic drift because they were smaller. Natural selection did not disappear, but it was not as strong. Consequences of the 'population crash' and the human effective population size are introduced briefly. The history of the ancient apes is written in the genomes of living humans and great apes. The expansion of the brain began before the human line emerged. Coalescence times for some genes are very old – up to several million years, long before Homo sapiens. The mismatch between gene trees and species trees highlights the anthropoid speciation processes, and gives the human genome history a fuzzy, probabilistic quality. However, it suggests traits that might form a foundation for capacities emerging later. A theoretical model is presented in which the genomes of early ape populations provide the substructure for the emergence of religious capacity later on the human line. The model does not search for religion, but its foundations. It suggests a course by which an evolutionary line that began with prosimians eventually produced a human species with biologically based religious capacity. The model of the sequential emergence of religious capacity relies on cognitive science, neuroscience, paleoneurology, primate field studies, cognitive archaeology, genomics, and population genetics. And, it emphasizes five trait types: (1) Documented, positive selection of sensory capabilities on the human line may have favored survival, but also eventually enriched human religious experience. (2) The bonobo model suggests a possible down-regulation of aggression and increase in tolerance while feeding, as well as paedomorphism – but, in a human species that remains cognitively sharp (unlike the bonobo). The two species emerged from the same ancient ape population, so it is logical to search for shared traits. (3) An up-regulation of emotional sensitivity and compassion seems to have occurred on the human line. This finds support in modern genetic studies. (4) The authors’ published model of morality's emergence in Homo erectus encompasses a cognitively based, decision-making capacity that was hypothetically overtaken, in part, by religious capacity. Together, they produced a strong, variable, biocultural capability to support human sociability. (5) The full flowering of human religious capacity came with the parietal expansion and smaller face (klinorhynchy) found only in Homo sapiens. Details from paleoneurology suggest the stage was set for human theologies. Larger parietal lobes allowed humans to imagine inner spaces, processes, and beings, and, with the frontal lobe, led to the first theologies composed of structured and integrated theories of the relationships between humans and the supernatural. The model leads to the evolution of a small population of African hominins that was ready to emerge with religious capacity when the species Homo sapiens evolved two hundred thousand years ago. By 50-60,000 years ago, when human ancestors left Africa, they were fully enabled.

Keywords: genetic drift, genomics, parietal expansion, religious capacity

Procedia PDF Downloads 325

Authors: Chongya Song, Kang Yen, Alexander Pons, Jin Liu

Abstract:

In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.

Keywords: consensus, curse of correlation, imbalance classification, rank-based chain-mode ensemble

Procedia PDF Downloads 120

Authors: Kemka Ihemelandu, Chukwuemeka Ihemelandu

Abstract:

Melanoma remains a public health crisis, with incidence rates increasing rapidly in the past decades. Improving diagnostic accuracy to decrease misdiagnosis using Artificial intelligence (AI) continues to be documented. Unfortunately, unintended racially biased outcomes, a product of lack of diversity in the dataset used, with a noted class imbalance favoring lighter vs. darker skin tone, have increasingly been recognized as a problem.Resulting in noted limitations of the accuracy of the Convolutional neural network (CNN)models. CNN models are prone to biased output due to biases in the dataset used to train them. Our aim in this study was the optimization of convolutional neural network algorithms to mitigate bias in the automated diagnosis of melanoma. We hypothesized that our proposed training algorithms based on a data augmentation method to optimize the diagnostic accuracy of a CNN classifier by generating new training samples from the original ones will reduce bias in the automated diagnosis of melanoma. We applied geometric transformation, including; rotations, translations, scale change, flipping, and shearing. Resulting in a CNN model that provided a modifiedinput data making for a model that could learn subtle racial features. Optimal selection of the momentum and batch hyperparameter increased our model accuracy. We show that our augmented model reduces bias while maintaining accuracy in the automated diagnosis of melanoma.

Keywords: bias, augmentation, melanoma, convolutional neural network

Procedia PDF Downloads 196

Authors: Valentina Marutyan

Abstract:

Healthcare data mining is a rapidly developing field at the intersection of technology and medicine that has the potential to change our understanding and approach to providing healthcare. Healthcare and data mining is the process of examining huge amounts of data to extract useful information that can be applied in order to improve patient care, treatment effectiveness, and overall healthcare delivery. This field looks for patterns, trends, and correlations in a variety of healthcare datasets, such as electronic health records (EHRs), medical imaging, patient demographics, and treatment histories. To accomplish this, it uses advanced analytical approaches. Predictive analysis using historical patient data is a major area of interest in healthcare data mining. This enables doctors to get involved early to prevent problems or improve results for patients. It also assists in early disease detection and customized treatment planning for every person. Doctors can customize a patient's care by looking at their medical history, genetic profile, current and previous therapies. In this way, treatments can be more effective and have fewer negative consequences. Moreover, helping patients, it improves the efficiency of hospitals. It helps them determine the number of beds or doctors they require in regard to the number of patients they expect. In this project are used models like logistic regression, random forests, and neural networks for predicting diseases and analyzing medical images. Patients were helped by algorithms such as k-means, and connections between treatments and patient responses were identified by association rule mining. Time series techniques helped in resource management by predicting patient admissions. These methods improved healthcare decision-making and personalized treatment. Also, healthcare data mining must deal with difficulties such as bad data quality, privacy challenges, managing large and complicated datasets, ensuring the reliability of models, managing biases, limited data sharing, and regulatory compliance. Finally, secret code of data mining in healthcare helps medical professionals and hospitals make better decisions, treat patients more efficiently, and work more efficiently. It ultimately comes down to using data to improve treatment, make better choices, and simplify hospital operations for all patients.

Keywords: data mining, healthcare, big data, large amounts of data

Procedia PDF Downloads 53

Authors: Yue Huang, Hongcheng Gan

Abstract:

The new urbanization pattern has led to a rapid growth in demand for short-distance intercity travel, and the emergence of new travel modes has also increased the variety of intercity travel options. In previous studies on intercity travel mode choice behavior, the impact of functional amenities of travel mode and travelers’ long-term personality characteristics has rarely been considered, and empirical results have typically been calibrated using revealed preference (RP) or stated preference (SP) data. This study designed a questionnaire that combines the RP and SP experiment from the perspective of a trip chain combining inner-city and intercity mobility, with consideration for the actual condition of the Huainan-Hefei traffic corridor. On the basis of RP/SP fusion data, a hybrid choice model considering both random taste heterogeneity and psychological characteristics was established to investigate travelers’ mode choice behavior for traditional train, high-speed rail, intercity bus, private car, and intercity online car-hailing. The findings show that intercity time and cost exert the greatest influence on mode choice, with significant heterogeneity across the population. Although inner-city cost does not demonstrate a significant influence, inner-city time plays an important role. Service attributes of travel mode, such as catering and hygiene services, as well as free wireless network supply, only play a minor role in mode selection. Finally, our study demonstrates that safety-seeking tendency, hedonism, and introversion all have differential and significant effects on intercity travel mode choice.

Keywords: intercity travel mode choice, stated preference survey, hybrid choice model, RP/SP fusion data, psychological latent variable, heterogeneity

Procedia PDF Downloads 93

Authors: Maxwell Henderson, Tristan Cook, Justin Chan Jin Le, Mark Hodson, YoungJung Chang, John Novak, Daniel Padilha, Nishan Kulatilaka, Ansu Bagchi, Sanjoy Ray, John Kelly

Abstract:

We present a method of using adiabatic quantum optimization (AQO) to solve a mixed integer nonlinear programming (MINLP) problem instance. The MINLP problem is a general form of a set of NP-hard optimization problems that are critical to many business applications. It requires optimizing a set of discrete and continuous variables with nonlinear and potentially nonconvex constraints. Obtaining an exact, optimal solution for MINLP problem instances of non-trivial size using classical computation methods is currently intractable. Current leading algorithms leverage heuristic and divide-and-conquer methods to determine approximate solutions. Creating more accurate and efficient algorithms is an active area of research. Quantum computing (QC) has several theoretical benefits compared to classical computing, through which QC algorithms could obtain MINLP solutions that are superior to current algorithms. AQO is a particular form of QC that could offer more near-term benefits compared to other forms of QC, as hardware development is in a more mature state and devices are currently commercially available from D-Wave Systems Inc. It is also designed for optimization problems: it uses an effect called quantum tunneling to explore all lowest points of an energy landscape where classical approaches could become stuck in local minima. Our work used a novel algorithm formulated for AQO to solve a special type of MINLP problem. The research focused on determining: 1) if the problem is possible to solve using AQO, 2) if it can be solved by current hardware, 3) what the currently achievable performance is, 4) what the performance will be on projected future hardware, and 5) when AQO is likely to provide a benefit over classical computing methods. Two different methods, integer range and 1-hot encoding, were investigated for transforming the MINLP problem instance constraints into a mathematical structure that can be embedded directly onto the current D-Wave architecture. For testing and validation a D-Wave 2X device was used, as well as QxBranch’s QxLib software library, which includes a QC simulator based on simulated annealing. Our results indicate that it is mathematically possible to formulate the MINLP problem for AQO, but that currently available hardware is unable to solve problems of useful size. Classical general-purpose simulated annealing is currently able to solve larger problem sizes, but does not scale well and such methods would likely be outperformed in the future by improved AQO hardware with higher qubit connectivity and lower temperatures. If larger AQO devices are able to show improvements that trend in this direction, commercially viable solutions to the MINLP for particular applications could be implemented on hardware projected to be available in 5-10 years. Continued investigation into optimal AQO hardware architectures and novel methods for embedding MINLP problem constraints on to those architectures is needed to realize those commercial benefits.

Keywords: adiabatic quantum optimization, mixed integer nonlinear programming, quantum computing, NP-hard

Procedia PDF Downloads 508

Authors: Andreea D. Șerban, Răzvan Mălăncuș, Mihaela Ivancia, Șteofil Creangă

Abstract:

Just as air influences the quality of life in the terrestrial environment, water, as a living environment, is one of great importance when it comes to the quality of life of underwater animals, which acquires an even higher degree of importance when analyzing underwater creatures as future products for human consumption. Thus, going beyond the ideal environment, in which all water quality parameters are permanently in perfect standards for reproduction, growth, and development of fish material and customizing this study to reality, it was demonstrated the importance of reproduction, development, and growth of biological material, necessary in the population fish farms, in the same environment to gain the maximum yield that a fish farm can offer. The biological material used was harvested from 3 fish farms located at great distances from each other to have environments with different parameters. The specimens were clinically healthy at 2 years of age. Thus, the differences in water quality parameters had effects on specimens from other environments, describing large curves in their evolution in new environments. Another change was observed in the new environment, the specimens contributing with the "genetic package" to its modification, tending to a balance of the parameters studied to the values in the environment in which they lived until the time of the experiment. The study clearly showed that adaptability to the environment in which an individual has developed and grown is not valid in environments with different parameters, resulting even in the fatality of one sample during the experiment. In some specimens, the values of the studied hematological parameters were halved after the transfer to the new environment, and in others, the same parameters were doubled. The study concludes that the specimens were adapted to the environment in which they developed and grew, their descendants having a higher value of heritability only in the initial environment. It is known that heritability is influenced 50% by the genetic package of the individual and 50% by the environment, by removing the value of the environment, the duration of improvement of characters of interest will be shorter and the maximum yield of fish farms can be achieved in a smaller period.

Keywords: environment, heritability, quality, water

Procedia PDF Downloads 151

Authors: Ewenam Gbormittah

Abstract:

Because of the effects of the pandemic, companies are focusing on the future of work arrangements for their employees. This includes adapting to a remote or hybrid working model. It is important that employers provide those working remotely or in a hybrid mode a rewarding onboarding experience and opportunities for interaction. Although, Information & Communication Technologies (ICT) have transformed the ways organisations manage employees over the years, there is still a need for a platform where organisations can adjust their onboarding to suit the social and interactive aspects of their employees, to facilitate successful integration. This study aimed to explore this matter by investigating whether Virtual Reality (VR) technology contributes to new employees integration into the organisation during their job-onboarding (JOB) process. The research questions are as follows: (1) To what extent does VR have an impact on employees successful integration into the organisation, and (2) How does VR help elements of new employees Psychological Contract (PC) during the course of interactions. An exploratory case study approach, which consisted of a semi-structured interview was conducted on 20 employees, split from two different case organisations. The results of the data were analysed according to each case, and then a cross-case comparison was provided. The results have generated 8 themes, presenting in excess of 7 sub-themes for CS1 and presented 7 themes, in excess of 7 sub-themes for CS2. The cross-case analysis has revealed that VR does have the potential to support employees integration into the organisation. However, the effects were shown to be stronger for employees in CS2, compared to employees in CS1. The results highlight practical implications for onboarding psychology and strategic talent solutions within recruitment. Such strategy this research particularly outlines, involves providing insights on how to manage the PC of employees from the recruitment stage to creating successful employment relationships.

Keywords: job-onboarding, psychological contract, virtual reality, case study one, case study two

Procedia PDF Downloads 42

Authors: Tanyaporn Chairoch

Abstract:

Introduction: Cannabis is a drug to treat patients with many diseases such as Multiple sclerosis, Alzheimer’s disease, and Epilepsy, where theycontain many active compounds such as delta-9 tetrahydrocannabinol (THC) and cannabidiol (CBD). Especially, THC is the primary psychoactive ingredient in cannabis and binds to cannabinoid 1 (CB1) receptors. Moreover, CB1 is located on the neocortex, hippocampus, basal ganglia, cerebellum, and brainstem. In previous study, we found the association between the variant of CB1recptors gene (rs2023239) and decreased effect of nicotine reinforcement in patients. However, there are no data describing whether the distribution of CB1 receptor gene is a genetic marker for Thai patients who are treated with cannabis. Objective: Thus, the aim of this study we want to investigate the frequency of the CB1 receptor gene in Thai patients. Materials and Methods: All of sixty Thai patients received the medical cannabis for treatment who were recruited in this study. DNA will be extracted from EDTA whole blood by Genomic DNA Mini Kit. The genotyping of CNR1 gene (rs 2023239) was genotyped by the TaqMan real time PCR assay (ABI, Foster City, CA, USA).and using the real-time PCR ViiA7 (ABI, Foster City, CA, USA). Results: We found thirty-eight (63.3%) Thai patients were female, and twenty-two (36.70%) were male in this study with median age of 45.8 (range19 – 87 ) years. Especially, thirty-two (53.30%) medical cannabis tolerant controls were female ( 55%) and median age of52.1 (range 27 – 79 ) years. The most adverse effects for medical cannabis treatment was tachycardia. Furthermore, the number of rs 2023239 (TT) carriers was 26 of 27 (96.29%) in medical cannabis-induced adverse effects and 32 of 33 (96.96%) in tolerant controls. Additionally, rs 2023239 (CT) variant was found just only one of twenty-seven (3.7%) in medical cannabis-induced adverse effects and 1 of 33 (3.03%) in tolerant controls. Conclusions: The distribution of genetic variant in CNR1 gene might serve as a pharmacogenetics markers for screening before initiating the therapy with medical cannabis in Thai patients.

Keywords: cannabis, pharmacogenetics, CNR1 gene, thai patient

Procedia PDF Downloads 88

Authors: Morteza Taherinezhad, Ahmad Reza Rabbani, Morteza Asemani, Rudy Swennen

Abstract:

Oil-oil correlation is one of the most important issues in geochemical studies that enables to classify oils genetically. Oil-oil correlation is generally estimated based on non-polar fractions of crude oil (e.g., saturate and aromatic compounds). Despite several advantages, the drawback of using these compounds is their susceptibility of being affected by secondary processes. The polar fraction of crude oil (e.g., asphaltenes) has similar characteristics to kerogen, and this structural similarity is preserved during migration, thermal maturation, biodegradation, and water washing. Therefore, these structural characteristics can be considered as a useful correlation parameter, and it can be concluded that asphaltenes from different reservoirs with the same genetic signatures have a similar origin. Hence in this contribution, an integrated study by using both non-polar and polar fractions of oil was performed to use the merits of both fractions. Therefore, five oil samples from oil fields in the Persian Gulf were studied. Structural characteristics of extracted asphaltenes were investigated by Fourier transform infrared (FTIR) spectroscopy. Graphs based on aliphatic and aromatic compounds (predominant compounds in asphaltenes structure) and sulphoxide and carbonyl functional groups (which are representatives of sulphur and oxygen abundance in asphaltenes) were used for comparison of asphaltenes structures in different samples. Non-polar fractions were analyzed by GC-MS. The study of asphaltenes showed the studied oil samples comprise two oil families with distinct genetic characteristics. The first oil family consists of Salman and Reshadat oil samples, and the second oil family consists of Resalat, Siri E, and Siri D oil samples. To validate our results, biomarker parameters were employed, and this approach completely confirmed previous results. Based on biomarker analyses, both oil families have a marine source rock, whereby marl and carbonate source rocks are the source rock for the first and the second oil family, respectively.

Keywords: biomarker, non-polar fraction, oil-oil correlation, petroleum geochemistry, polar fraction

Procedia PDF Downloads 116

Authors: N. Demertzis, J. L. Bowen

Abstract:

Sepsis is a complex and rapidly evolving condition, resulting from uncontrolled prolonged activation of host immune system due to pathogenic insult. The aim of this study is the development of a multiplex electrochemical sensing platform, capable of detecting both pathogen associated and host immune markers to enable the rapid and definitive diagnosis of sepsis. A combination of aptamers and molecular imprinting approaches have been employed to generate sensing systems for lipopolysaccharide (LPS), c-reactive protein (CRP) and procalcitonin (PCT). Gold working electrodes were mechanically polished and electrochemically cleaned with 0.1 M sulphuric acid using cyclic voltammetry (CV). Following activation, a self-assembled monolayer (SAM) was generated, by incubating the electrodes with a thiolated anti-LPS aptamer / dithiodibutiric acid (DTBA) mixture (1:20). 3-aminophenylboronic acid (3-APBA) in combination with the anti-LPS aptamer was used for the development of the hybrid molecularly imprinted sensor (apta-MIP). Aptasensors, targeting PCT and CRP were also fabricated, following the same approach as in the case of LPS, with mercaptohexanol (MCH) replacing DTBA. In the case of the CRP aptasensor, the SAM was formed following incubation of a 1:1 aptamer: MCH mixture. However, in the case of PCT, the SAM was formed with the aptamer itself, with subsequent backfilling with 1 μM MCH. The binding performance of all systems has been evaluated using electrochemical impedance spectroscopy. The apta-MIP’s polymer thickness is controlled by varying the number of electropolymerisation cycles. In the ideal number of polymerisation cycles, the polymer must cover the electrode surface and create a binding pocket around LPS and its aptamer binding site. Less polymerisation cycles will create a hybrid system which resembles an aptasensor, while more cycles will be able to cover the complex and demonstrate a bulk polymer-like behaviour. Both aptasensor and apta-MIP were challenged with LPS and compared to conventional imprinted (absence of aptamer from the binding site, polymer formed in presence of LPS) and non-imprinted polymers (NIPS, absence of LPS whilst hybrid polymer is formed). A stable LPS aptasensor, capable of detecting down to 5 pg/ml of LPS was generated. The apparent Kd of the system was estimated at 17 pM, with a Bmax of approximately 50 pM. The aptasensor demonstrated high specificity to LPS. The apta-MIP demonstrated superior recognition properties with a limit of detection of 1 fg/ml and a Bmax of 100 pg/ml. The CRP and PCT aptasensors were both able to detect down to 5 pg/ml. Whilst full binding performance is currently being evaluated, there is none of the sensors demonstrate cross-reactivity towards LPS, CRP or PCT. In conclusion, stable aptasensors capable of detecting LPS, PCT and CRP at low concentrations have been generated. The realisation of a multiplex panel such as described herein, will effectively contribute to the rapid, personalised diagnosis of sepsis.

Keywords: aptamer, electrochemical impedance spectroscopy, molecularly imprinted polymers, sepsis

Procedia PDF Downloads 114

Authors: Nadia Sid, Alan Taylor, Marion Bourebrab

Abstract:

The construction sector is on the critical path to decarbonise the European economy by 2050. In order to achieve this objective it must enable reducing its CO2 emission by 90% and its energy consumption by as much as 50%. For this reason, a new class of low environmental impact construction materials named “eco-material” are becoming increasingly important in the struggle against climate change. A European funded collaborative project ISOBIO coordinated by TWI is aimed at taking a radical approach to the use of bio-based aggregates to create novel construction materials that are usable in high volume in using traditional methods, as well as developing markets such as exterior insulation of existing house stocks. The approach taken for this project is to use finely chopped material protected from bio-degradation through the use of functionalized silica nanoparticles. TWI is exploring the development of novel inorganic-organic hybrid nano-materials, to be applied as a surface treatment onto bio-based aggregates. These nanoparticles are synthesized by sol-gel processing and then functionalised with silanes to impart multifunctionality e.g. hydrophobicity, fire resistance and chemical bonding between the silica nanoparticles and the bio-based aggregates. This talk will illustrate the approach taken by TWI to design the functionalized silica nanoparticles by using a material-by-design approach. The formulation and synthesize process will be presented together with the challenges addressed by those hybrid nano-materials. The results obtained with regards to the water repellence and fire resistance will be displayed together with preliminary public results of the ISOBIO project. (This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 641927).

Keywords: bio-sourced material, composite material, durable insulation panel, water repellent material

Procedia PDF Downloads 227

Authors: A. S. Vidyashree, C. M. Kalleshwaraswamy, R. Asokan, H. M. Mahadevaswamy

Abstract:

Termites are very vital ecological thespians in tropical ecosystem, having been designated as “ecosystem engineers”, due to their significant role in providing soil ecosystem services. Despite their importance, our understanding of a number of their basic biological processes in termites is extremely limited. Developing a better understanding of termite biology is closely dependent upon consistent species identification. At present, identification of termites is relied on soldier castes. But for many species, soldier caste is not reported, that creates confusion in identification. The use of molecular markers may be helpful in estimating phylogenetic relatedness between the termite species and estimating genetic differentiation among local populations within each species. To understand this, termites samples were collected from various places of Western Ghats covering four states namely Karnataka, Kerala, Tamil Nadu, Maharashtra during 2013-15. Termite samples were identified based on their morphological characteristics, molecular characteristics, or both. Survey on the termite fauna in Karnataka, Kerala, Maharashtra and Tamil Nadu indicated the presence of a 16 species belongs to 4 subfamilies under two families viz., Rhinotermitidae and Termitidae. Termititidae was the dominant family which was belonging to 4 genera and four subfamilies viz., Macrotermitinae, Amitermitinae, Nasutitermitinae and Termitinae. Amitermitinae had three species namely, Microcerotermes fletcheri, M. pakistanicus and Speculitermes sinhalensis. Macrotermitinae had the highest number of species belonging two genera, namely Microtermes and Odontotermes. Microtermes genus was with only one species i.e., Microtermes obesi. The genus Odontotermes was represented by the highest number of species (07), namely, O. obesus was the dominant (41 per cent) and the most widely distributed species in Karnataka, Karala, Maharashtra and Tamil nadu followed by O. feae (19 per cent), O.assmuthi (11 per cent) and others like O. bellahunisensis O. horni O. redemanni, O. yadevi. Nasutitermitinae was represented by two genera namely Nasutitermes anamalaiensis and Trinervitermes biformis. Termitinae subfamily was represented by Labiocapritermes distortus. Rhinotermitidae was represented by single subfamily Heterotermetinae. In Heterotermetinae, two species namely Heterotermes balwanthi and H. malabaricus were recorded. Genetic relationship among termites collected from various locations of Western Ghats of India was characterized based on mitochondrial DNA sequences (12S, 16S, and COII). Sequence analysis and divergence among the species was assessed. These results suggest that the use of both molecular and morphological approaches is crucial in ensuring accurate species identification. Efforts were made to understand their evolution and to address the ambiguities in morphological taxonomy. The implication of the study in revising the taxonomy of Indian termites, their characterization and molecular comparisons between the sequences are discussed.

Keywords: isoptera, mitochondrial DNA sequences, rhinotermitidae, termitidae, Western ghats

Procedia PDF Downloads 253

Authors: Elcin Timur Cakmak, Ayse Oguzlar

Abstract:

This study presents the results of the tweets sent by Twitter users on social media about the Russia-Ukraine war by bigram and trigram methods. On February 24, 2022, Russian President Vladimir Putin declared a military operation against Ukraine, and all eyes were turned to this war. Many people living in Russia and Ukraine reacted to this war and protested and also expressed their deep concern about this war as they felt the safety of their families and their futures were at stake. Most people, especially those living in Russia and Ukraine, express their views on the war in different ways. The most popular way to do this is through social media. Many people prefer to convey their feelings using Twitter, one of the most frequently used social media tools. Since the beginning of the war, it is seen that there have been thousands of tweets about the war from many countries of the world on Twitter. These tweets accumulated in data sources are extracted using various codes for analysis through Twitter API and analysed by Python programming language. The aim of the study is to find the word sequences in these tweets by the n-gram method, which is known for its widespread use in computational linguistics and natural language processing. The tweet language used in the study is English. The data set consists of the data obtained from Twitter between February 24, 2022, and April 24, 2022. The tweets obtained from Twitter using the #ukraine, #russia, #war, #putin, #zelensky hashtags together were captured as raw data, and the remaining tweets were included in the analysis stage after they were cleaned through the preprocessing stage. In the data analysis part, the sentiments are found to present what people send as a message about the war on Twitter. Regarding this, negative messages make up the majority of all the tweets as a ratio of %63,6. Furthermore, the most frequently used bigram and trigram word groups are found. Regarding the results, the most frequently used word groups are “he, is”, “I, do”, “I, am” for bigrams. Also, the most frequently used word groups are “I, do, not”, “I, am, not”, “I, can, not” for trigrams. In the machine learning phase, the accuracy of classifications is measured by Classification and Regression Trees (CART) and Naïve Bayes (NB) algorithms. The algorithms are used separately for bigrams and trigrams. We gained the highest accuracy and F-measure values by the NB algorithm and the highest precision and recall values by the CART algorithm for bigrams. On the other hand, the highest values for accuracy, precision, and F-measure values are achieved by the CART algorithm, and the highest value for the recall is gained by NB for trigrams.

Keywords: classification algorithms, machine learning, sentiment analysis, Twitter

Procedia PDF Downloads 58

Authors: Daina Jonkus, Solvita Petrovska, Dace Smiltina, Lasma Cielava

Abstract:

The beta-lactoglobulin and kappa-casein are milk proteins which are important for milk composition. Cows with beta-lactoglobulin and kappa-casein gene BB genotypes have highest milk crude protein and fat content. The aim of the study was to determinate the frequencies of milk protein gene polymorphisms in local Latvian Brown (LB) cows breed and analyze the influence of beta-lactoglobulin and kappa-casein genotypes to milk productivity traits. 102 cows’ genotypes of milk protein genes were detected using Polymerase Chain Reaction and Restriction Fragment Length Polymorphism (PCR-RFLP) and electrophoresis on 3% agarose gel. For beta-lactoglobulin were observed 2 types of alleles A and B and for kappa-casein 3 types: A, B and E. Highest frequency in beta-lactoglobulin gene was observed for B allele – 0.926. Molecular analysis of beta-lactoglobulin gene shows 86.3% of individuals are homozygous by B allele and animals are with genotypes BB and 12.7% of individuals are heterozygous with genotypes AB. The highest milk yield 4711.7 kg was for 1st lactation cows with AB genotypes, whereas the highest milk protein content (3.35%) and fat content (4.46 %) was for BB genotypes. Analysis of the kappa-casein locus showed a prevalence of the A allele – 0.750. The genetic variant of B was characterized by a low frequency – 0.240. Moreover, the frequency of E occurred in the LB cows’ population with very low frequency – 0.010. 54.9 % of cows are homozygous with genotypes AA, and only 4.9 % are homozygous with genotypes BB. 32.8 % of individuals are heterozygous with genotypes AB, and 2.0 % are with AE. The highest milk productivity was for 1st lactation cows with AB genotypes: milk yield 4620.3 kg, milk protein content 3.39% and fat content 4.53 %. According to the results, in local Latvian brown there are only 2.9% of cows are with BB-BB genotypes, which is related to milk coagulation ability and affected cheese production yield. Acknowledgment: the investigation is supported by VPP 2014-2017 AgroBioRes Project No. 3 LIVESTOCK.

Keywords: beta-lactoglobulin, cows, genotype frequencies, kappa-casein

Procedia PDF Downloads 256

Authors: Dionisio Andujar, Juan lópez-Correa, Hugo Moreno, Angela Ri

Abstract:

The increased number of weeds in tomato crops highly lower yields. Weed identification with the aim of machine learning is important to carry out site-specific control. The last advances in computer vision are a powerful tool to face the problem. The analysis of RGB (Red, Green, Blue) images through Artificial Neural Networks had been rapidly developed in the past few years, providing new methods for weed classification. The development of the algorithms for crop and weed species classification looks for a real-time classification system using Object Detection algorithms based on Convolutional Neural Networks. The site study was located in commercial corn fields. The classification system has been tested. The procedure can detect and classify weed seedlings in tomato fields. The input to the Neural Network was a set of 10,000 RGB images with a natural infestation of Cyperus rotundus l., Echinochloa crus galli L., Setaria italica L., Portulaca oeracea L., and Solanum nigrum L. The validation process was done with a random selection of RGB images containing the aforementioned species. The mean average precision (mAP) was established as the metric for object detection. The results showed agreements higher than 95 %. The system will provide the input for an online spraying system. Thus, this work plays an important role in Site Specific Weed Management by reducing herbicide use in a single step.

Keywords: deep learning, object detection, cnn, tomato, weeds

Procedia PDF Downloads 89

Authors: Vinayak Bassi, Rajpreet Singh

Abstract:

Over the years, with the emergence of sophisticated computers and algorithms, finance has been quantified using computational prowess. Asset valuation has been one of the key components of quantitative finance. In fact, it has become one of the embryonic steps in determining risk related to a portfolio, the main goal of quantitative finance. This study comprises a drawing comparison between valuation output generated by two stochastic dynamic models, namely Black-Scholes and Dupire’s bi-dimensionality model. Both of these models are formulated for computing the valuation function for a portfolio of European options using Monte Carlo simulation methods. Although Monte Carlo algorithms have a slower convergence rate than calculus-based simulation techniques (like FDM), they work quite effectively over high-dimensional dynamic models. A fidelity gap is analyzed between the static (historical) and stochastic inputs for a sample portfolio of underlying assets. In order to enhance the performance efficiency of the model, the study emphasized the use of variable reduction methods and customizing random number generators to implement parallelization. An attempt has been made to further implement the Dupire’s model on a GPU to achieve higher computational performance. Furthermore, ideas have been discussed around the performance enhancement and bottleneck identification related to the implementation of options-pricing models on GPUs.

Keywords: monte carlo, stochastic models, computational finance, parallel programming, scientific computing

Procedia PDF Downloads 144

Authors: Samuel Ahamefula Mba

Abstract:

Fluid turbulence is a complex and nonlinear phenomenon that occurs in various natural and industrial processes. Understanding turbulence remains a challenging task due to its intricate nature. One approach to gain insights into turbulence is through the study of entropy, which quantifies the disorder or randomness of a system. This research presents a numerical investigation of entropy signatures in fluid turbulence. The work is to develop a numerical framework to describe and analyse fluid turbulence in terms of entropy. This decomposes the turbulent flow field into different scales, ranging from large energy-containing eddies to small dissipative structures, thus establishing a correlation between entropy and other turbulence statistics. This entropy-based framework provides a powerful tool for understanding the underlying mechanisms driving turbulence and its impact on various phenomena. This work necessitates the derivation of the Poisson equation for pressure transformation of Navier-Stokes equation and using Chebyshev-Finite Difference techniques to effectively resolve it. To carry out the mathematical analysis, consider bounded domains with smooth solutions and non-periodic boundary conditions. To address this, a hybrid computational approach combining direct numerical simulation (DNS) and Large Eddy Simulation with Wall Models (LES-WM) is utilized to perform extensive simulations of turbulent flows. The potential impact ranges from industrial process optimization and improved prediction of weather patterns.

Keywords: turbulence, Navier-Stokes equation, Poisson pressure equation, numerical investigation, Chebyshev-finite difference, hybrid computational approach, large Eddy simulation with wall models, direct numerical simulation

Procedia PDF Downloads 76

Authors: Sandra Smieszek, Jonathan Haines

Abstract:

Introduction: Numerous research efforts have focused on searching for ‘longevity genes’. However, attempting to decipher the genetic component of the longevous phenotype have resulted in limited success and the mechanisms governing longevity remain to be explained. We conducted a genome-wide homozygosity analysis (GWHA) of the founder population of the Amish community in central Ohio. While genome-wide association studies using unrelated individuals have revealed many interesting longevity associated variants, these variants are typically of small effect and cannot explain the observed patterns of heritability for this complex trait. The Amish provide a large cohort of extended kinships allowing for in depth analysis via family-based approach excellent population due to its. Heritability of longevity increases with age with significant genetic contribution being seen in individuals living beyond 60 years of age. In our present analysis we show that the heritability of longevity is estimated to be increasing with age particularly on the paternal side. Methods: The present analysis integrated both phenotypic and genotypic data and led to the discovery of a series of variants, distinct for stratified populations across ages and distinct for paternal and maternal cohorts. Specifically 5437 subjects were analyzed and a subset of 893 successfully genotyped individuals was used to assess CHIP heritability. We have conducted the homozygosity analysis to examine if homozygosity is associated with increased risk of living beyond 90. We analyzed AMISH cohort genotyped for 614,957 SNPs. Results: We delineated 10 significant regions of homozygosity (ROH) specific for the age group of interest (>90). Of particular interest was ROH on chromosome 13, P < 0.0001. The lead SNPs rs7318486 and rs9645914 point to COL4A2 and our lead SNP. COL25A1 encodes one of the six subunits of type IV collagen, the C-terminal portion of the protein, known as canstatin, is an inhibitor of angiogenesis and tumor growth. COL4A2 mutations have been reported with a broader spectrum of cerebrovascular, renal, ophthalmological, cardiac, and muscular abnormalities. The second region of interest points to IRS2. Furthermore we built a classifier using the obtained SNPs from the significant ROH region with 0.945 AUC giving ability to discriminate between those living beyond to 90 years of age and beyond. Conclusion: In conclusion our results suggest that a history of longevity does indeed contribute to increasing the odds of individual longevity. Preliminary results are consistent with conjecture that heritability of longevity is substantial when we start looking at oldest fifth and smaller percentiles of survival specifically in males. We will validate all the candidate variants in independent cohorts of centenarians, to test whether they are robustly associated with human longevity. The identified regions of interest via ROH analysis could be of profound importance for the understanding of genetic underpinnings of longevity.

Keywords: regions of homozygosity, longevity, SNP, Amish

Procedia PDF Downloads 218

Authors: Jigg Pelayo, Ricardo Villar

Abstract:

Leaning on the development of aerial laser scanning in the Philippine geospatial industry, researches about remote sensing and machine vision technology became a trend. Object detection via template matching is one of its application which characterized to be fast and in real time. The paper purposely attempts to provide application for robust pattern matching algorithm based on the normalized cross correlation (NCC) criterion function subjected in Object-based image analysis (OBIA) utilizing high-resolution aerial imagery and low density LiDAR data. The height information from laser scanning provides effective partitioning order, thus improving the hierarchal class feature pattern which allows to skip unnecessary calculation. Since detection is executed in the object-oriented platform, mathematical morphology and multi-level filter algorithms were established to effectively avoid the influence of noise, small distortion and fluctuating image saturation that affect the rate of recognition of features. Furthermore, the scheme is evaluated to recognized the performance in different situations and inspect the computational complexities of the algorithms. Its effectiveness is demonstrated in areas of Misamis Oriental province, achieving an overall accuracy of 91% above. Also, the garnered results portray the potential and efficiency of the implemented algorithm under different lighting conditions.

Keywords: algorithm, LiDAR, object recognition, OBIA

Procedia PDF Downloads 230

Authors: Jonathan Matyenyika

Abstract:

In recent years, automobile manufacturers have increasingly produced vehicles equipped with cutting-edge automotive electronic technology to match the fast-paced digital world of today; this has brought about various benefits in different business sectors that make use of these vehicles as a means of turning over a profit. In the logistics industry, vehicles equipped with this technology have proved to be very utilitarian; this paper focuses on the benefits automobile electronic equipped vehicles have in the logistics industry. Automotive vehicle manufacturers have introduced new technological electronic features to their vehicles to enhance and improve the overall performance, efficiency, safety and driver comfort. Some of these features have proved to be beneficial to logistics operators. To start with the introduction of adaptive cruise control in long-distance haulage vehicles, to see how this system benefits the drivers, we carried out research in the form of interviews with long-distance truck drivers with the main question being, what major difference have they experienced since they started to operate vehicles equipped with this technology to which most stated they had noticed that they are less tired and are able to drive longer distances as compared to when they used vehicles not equipped with this system. As a result, they can deliver faster and take on the next assignment, thus improving efficiency and bringing in more monetary return for the logistics company. Secondly, the introduction of electric hybrid technology, this system allows the vehicle to be propelled by electric power stored in batteries located in the vehicle instead of fossil fuel. Consequently, this benefits the logistic company as vehicles become cheaper to run as electricity is more affordable as compared to fossil fuel. The merging of electronic systems in vehicles has proved to be of great benefit, as my research proves that this can benefit the logistics industry in plenty of ways.

Keywords: logistics, manufacturing, hybrid technology, haulage vehicles

Procedia PDF Downloads 36

Authors: Kamyar Maleki Bagherabadi, Torstein Aarseth Bø, Truls Flatberg, Olve Mo

Abstract:

Hydrogen fuel cells and batteries are one of the promising solutions aligned with carbon emission reduction goals for the marine sector. However, the higher installation and operation costs of hydrogen-based systems compared to conventional diesel gensets raise questions about the appropriate hydrogen tank size, energy, and fuel consumption estimations. Ship designers need methodologies and tools to calculate energy and fuel consumption for different component sizes to facilitate decision-making regarding feasibility and performance for retrofits and design cases. The aim of this work is to compare three alternative modeling approaches for the estimation of energy and fuel consumption with various hydrogen tank sizes, battery capacities, and load-sharing strategies. A fishery vessel is selected as an example, using logged load demand data over a year of operations. The modeled power system consists of a PEM fuel cell, a diesel genset, and a battery. The methodologies used are: first, an energy-based model; second, considering load variations during the time domain with a rule-based Power Management System (PMS); and third, a load variations model and dynamic PMS strategy based on optimization with perfect foresight. The errors and potentials of the methods are discussed, and design sensitivity studies for this case are conducted. The results show that the energy-based method can estimate fuel and energy consumption with acceptable accuracy. However, models that consider time variation of the load provide more realistic estimations of energy and fuel consumption regarding hydrogen tank and battery size, still within low computational time.

Keywords: fuel cell, battery, hydrogen, hybrid power system, power management system

Procedia PDF Downloads 13

Authors: Adrian W. Egger, Savvas P. Triantafyllou, Eleni N. Chatzi

Abstract:

The scaled boundary finite element method (SBFEM) is a semi-analytical numerical method, which introduces a scaling center in each element’s domain, thus transitioning from a Cartesian reference frame to one resembling polar coordinates. Consequently, an analytical solution is achieved in radial direction, implying that only the boundary need be discretized. The only limitation imposed on the resulting polygonal elements is that they remain star-convex. Further arbitrary p- or h-refinement may be applied locally in a mesh. The polygonal nature of SBFEM elements has been exploited in quadtree meshes to alleviate all issues conventionally associated with hanging nodes. Furthermore, since in 2D this results in only 16 possible cell configurations, these are precomputed in order to accelerate the forward analysis significantly. Any cells, which are clipped to accommodate the domain geometry, must be computed conventionally. However, since SBFEM permits polygonal elements, significantly coarser meshes at comparable accuracy levels are obtained when compared with conventional quadtree analysis, further increasing the computational efficiency of this scheme. The generalized stress intensity factors (gSIFs) are computed by exploiting the semi-analytical solution in radial direction. This is initiated by placing the scaling center of the element containing the crack at the crack tip. Taking an analytical limit of this element’s stress field as it approaches the crack tip, delivers an expression for the singular stress field. By applying the problem specific boundary conditions, the geometry correction factor is obtained, and the gSIFs are then evaluated based on their formal definition. Since the SBFEM solution is constructed as a power series, not unlike mode superposition in FEM, the two modes contributing to the singular response of the element can be easily identified in post-processing. Compared to the extended finite element method (XFEM) this approach is highly convenient, since neither enrichment terms nor a priori knowledge of the singularity is required. Computation of the gSIFs by SBFEM permits exceptional accuracy, however, when combined with hybrid quadtrees employing linear elements, this does not always hold. Nevertheless, it has been shown that crack propagation schemes are highly effective even given very coarse discretization since they only rely on the ratio of mode one to mode two gSIFs. The absolute values of the gSIFs may still be subject to large errors. Hence, we propose a post-processing scheme, which minimizes the error resulting from the approximation space of the cracked element, thus limiting the error in the gSIFs to the discretization error of the quadtree mesh. This is achieved by h- and/or p-refinement of the cracked element, which elevates the amount of modes present in the solution. The resulting numerical description of the element is highly accurate, with the main error source now stemming from its boundary displacement solution. Numerical examples show that this post-processing procedure can significantly improve the accuracy of the computed gSIFs with negligible computational cost even on coarse meshes resulting from hybrid quadtrees.

Keywords: linear elastic fracture mechanics, generalized stress intensity factors, scaled finite element method, hybrid quadtrees

Procedia PDF Downloads 126

Authors: Sima Parvizi Omran, Rezvan Tavakoli, Mahnaz Safari, Mohammadreza Aghasadeghi, Abolfazl Fateh, Pooneh Rahimi

Abstract:

Background: SARS-CoV-2, a single-stranded RNA betacoronavirus causes the global outbreak of coronavirus disease 2019 (COVID-19). Several clinical and scientific concerns are raised by this pandemic. Genetic factors can contribute to pathogenesis and disease susceptibility. There are single nucleotide polymorphisms (SNPs) in many of the genes in the immune system that affect the expression of specific genes or functions of some proteins related to immune responses against viral infections. In this study, we analyzed the impact of polymorphism in the interferon alpha and beta receptor subunit 2 (IFNAR2) and dipeptidyl peptidase 9 (Dpp9) genes and clinical parameters on the susceptibility and resistance to Coronavirus disease (COVID-19). Methods: A total of 330- SARS-CoV-2 positive patients (188 survivors and 142 nonsurvivors) were included in this study. All single-nucleotide polymorphisms (SNPs) on IFNAR2 (rs2236757) and Dpp9 (rs2109069) were genotyped by the polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP) method. Results: In survivor patients, the frequency of the favourable genotypes of IFNAR2 SNP (rs2236757 GC) was significantly higher than in nonsurvivor patients, and also Dpp9 (rs2109069 AT) genotypes were associated with the severity of COVID-19 infection. Conclusions: This study demonstrated that the severity of COVID- 19 patients was strongly associated with clinical parameters and unfavourable IFNAR2, Dpp9 SNP genotypes. In order to establish the relationship between host genetic factors and the severity of COVID-19 infection, further studies are needed in multiple parts of the world.

Keywords: SARS-CoV-2, COVID-19, interferon alpha and beta receptor subunit 2, dipeptidyl peptidase 9, single-nucleotide polymorphisms

Procedia PDF Downloads 142

Authors: Valbona Sota, Efigjeni Kongjika

Abstract:

Wild almond is a woody species, which is difficult to propagate either generatively by seed or by vegetative methods (grafting or cuttings) and also considered as Endangered (EN) in Albania based on IUCN criteria. As a wild relative of cultivated fruit trees, this species represents a source of genetic variability and can be very important in breeding programs and cultivation. For this reason, it would be of interest to use an effective method of in vitro mid-term conservation, which involves strategies to slow plant growth through physicochemical alterations of in vitro growth conditions. Multiplication of wild almond was carried out using zygotic embryos, as primary explants, with the purpose to develop a successful propagation protocol. Results showed that zygotic embryos can proliferate through direct or indirect organogenesis. During subculture, stage was obtained a great number of new plantlets identical to mother plants derived from the zygotic embryos. All in vitro plantlets obtained from subcultures underwent in vitro conservation by minimal growth in low temperature (4ºC) and darkness. The efficiency of this technique was evaluated for 3, 6, and 10 months of conservation period. Maintenance in these conditions reduced micro cuttings growth. Survival and regeneration rates for each period were evaluated and resulted that the maximal time of conservation without subculture on 4ºC was 10 months, but survival and regeneration rates were significantly reduced, specifically 15.6% and 7.6%. An optimal period of conservation in these conditions can be considered the 5-6 months storage, which can lead to 60-50% of survival and regeneration rates. This protocol may be beneficial for mass propagation, mid-term conservation, and for genetic manipulation of wild almond.

Keywords: micropropagation, minimal growth, storage, wild almond

Procedia PDF Downloads 119

Authors: Ivo Zution Goncalves, Christopher M. U. Neale, Hiran Medeiros, Everardo Mantovani, Natalia Souza

Abstract:

Multispectral and thermal infrared imagery from satellite sensors coupled with climate and soil datasets were used to estimate evapotranspiration and biomass in center pivots planted to maize in Brazil during the 2016 season. The hybrid remote sensing based model named Spatial EvapoTranspiration Modelling Interface (SETMI) was applied using multispectral and thermal infrared imagery from the Landsat Thematic Mapper instrument. Field data collected by the IRRIGER center pivot management company included daily weather information such as maximum and minimum temperature, precipitation, relative humidity for estimating reference evapotranspiration. In addition, soil water content data were obtained every 0.20 m in the soil profile down to 0.60 m depth throughout the season. Early season soil samples were used to obtain water-holding capacity, wilting point, saturated hydraulic conductivity, initial volumetric soil water content, layer thickness, and saturated volumetric water content. Crop canopy development parameters and irrigation application depths were also inputs of the model. The modeling approach is based on the reflectance-based crop coefficient approach contained within the SETMI hybrid ET model using relationships developed in Nebraska. The model was applied to several fields located in Minas Gerais State in Brazil with approximate latitude: -16.630434 and longitude: -47.192876. The model provides estimates of real crop evapotranspiration (ET), crop irrigation requirements and all soil water balance outputs, including biomass estimation using multi-temporal satellite image inputs. An interpolation scheme based on the growing degree-day concept was used to model the periods between satellite inputs, filling the gaps between image dates and obtaining daily data. Actual and accumulated ET, accumulated cold temperature and water stress and crop water requirements estimated by the model were compared with data measured at the experimental fields. Results indicate that the SETMI modeling approach using data assimilation, showed reliable daily ET and crop water requirements for maize, interpolated between remote sensing observations, confirming the applicability of the SETMI model using new relationships developed in Nebraska for estimating mainly ET and water requirements in Brazil under tropical conditions.

Keywords: basal crop coefficient, irrigation, remote sensing, SETMI

Procedia PDF Downloads 128

Authors: Rosa Tsegaye Aga, Xuan Jiang, Pavel Vazquez Faci, Siqing Liu, Simon Rayner, Endalkachew Alemu, Markos Abebe

Abstract:

Tuberculosis (TB) is a major cause of disease globally. In most cases, TB is treatable and curable, but only with the proper treatment. There is a time when drug-resistant TB occurs when bacteria become resistant to the drugs that are used to treat TB. Current strategies to identify drug-resistant TB bacteria are laboratory-based, and it takes a longer time to identify the drug-resistant bacteria and treat the patient accordingly. But machine learning (ML) and data science approaches can offer new approaches to the problem. In this study, we propose to develop an ML-based model to predict the antibiotic resistance phenotypes of TB isolates in minutes and give the right treatment to the patient immediately. The study has been using the whole genome sequence (WGS) of TB isolates as training data that have been extracted from the NCBI repository and contain different countries’ samples to build the ML models. The reason that different countries’ samples have been included is to generalize the large group of TB isolates from different regions in the world. This supports the model to train different behaviors of the TB bacteria and makes the model robust. The model training has been considering three pieces of information that have been extracted from the WGS data to train the model. These are all variants that have been found within the candidate genes (F1), predetermined resistance-associated variants (F2), and only resistance-associated gene information for the particular drug. Two major datasets have been constructed using these three information. F1 and F2 information have been considered as two independent datasets, and the third information is used as a class to label the two datasets. Five machine learning algorithms have been considered to train the model. These are Support Vector Machine (SVM), Random forest (RF), Logistic regression (LR), Gradient Boosting, and Ada boost algorithms. The models have been trained on the datasets F1, F2, and F1F2 that is the F1 and the F2 dataset merged. Additionally, an ensemble approach has been used to train the model. The ensemble approach has been considered to run F1 and F2 datasets on gradient boosting algorithm and use the output as one dataset that is called F1F2 ensemble dataset and train a model using this dataset on the five algorithms. As the experiment shows, the ensemble approach model that has been trained on the Gradient Boosting algorithm outperformed the rest of the models. In conclusion, this study suggests the ensemble approach, that is, the RF + Gradient boosting model, to predict the antibiotic resistance phenotypes of TB isolates by outperforming the rest of the models.

Keywords: machine learning, MTB, WGS, drug resistant TB

Procedia PDF Downloads 32

Authors: O. Sunantha, S. Zhenfeng, S. Phattraporn, A. Zeeshan

Abstract:

The decline of soil organic carbon (SOC) in global agriculture is a critical issue requiring rapid and accurate estimation for informed policymaking. Previous studies have demonstrated the variability of SOC predictors derived from remote sensing data and environmental variables. However, the specific parameters most suitable for accurately estimating SOC in agricultural areas remain unclear. This study utilizes remote sensing data to precisely estimate SOC and identify influential factors in diverse agricultural areas, such as paddy, corn, sugarcane, cassava, and perennial crops. Extreme gradient boosting (XGBoost), random forest (RF), and support vector regression (SVR) models are employed to analyze these factors impact on SOC estimation. The results show key factors influencing SOC estimation include slope, vegetation indices (EVI), spectral reflectance indices (red index, red edge2), temperature, land use, and surface soil moisture, as indicated by their averaged importance scores across XGBoost, RF, and SVR models. Therefore, using different machine learning algorithms for SOC estimation reveals varying influential factors from remote sensing data and environmental variables. This approach emphasizes feature selection, as different machine learning algorithms identify various key factors from remote sensing data and environmental variables for accurate SOC estimation.

Keywords: factors influencing SOC estimation, remote sensing data, environmental variables, machine learning

Procedia PDF Downloads 3