Search results for: machine modelling

Authors: Jacob Green, Cecilia Cabrera, Maximilian Jakobs, Andrea Dimitracopoulos, Mark van der Wilk, Ryan Greenhalgh

Abstract:

Predicting drug properties is key in drug discovery to enable de-risking of assets before expensive clinical trials and to find highly active compounds faster. Interest from the machine learning community has led to the release of a variety of benchmark datasets and proposed methods. However, it remains unclear for practitioners which method or approach is most suitable, as different papers benchmark on different datasets and methods, leading to varying conclusions that are not easily compared. Our large-scale empirical study links together numerous earlier works on different datasets and methods, thus offering a comprehensive overview of the existing property classes, datasets, and their interactions with different methods. We emphasise the importance of uncertainty quantification and the time and, therefore, cost of applying these methods in the drug development decision-making cycle. To the best of the author's knowledge, it has been observed that the optimal approach varies depending on the dataset and that engineered features with classical machine learning methods often outperform deep learning. Specifically, QSAR datasets are typically best analysed with classical methods such as Gaussian Processes, while ADMET datasets are sometimes better described by Trees or deep learning methods such as Graph Neural Networks or language models. Our work highlights that practitioners do not yet have a straightforward, black-box procedure to rely on and sets a precedent for creating practitioner-relevant benchmarks. Deep learning approaches must be proven on these benchmarks to become the practical method of choice in drug property prediction.

Keywords: activity (QSAR), ADMET, classical methods, drug property prediction, empirical study, machine learning

Procedia PDF Downloads 81

Authors: Yuanjin Liu

Abstract:

Retirement withdrawal strategies are very important to minimize the probability of ruin in retirement. The ruin probability is modeled as a function of initial withdrawal age, gender, asset allocation, inflation rate, and initial withdrawal rate. The ruin probability is obtained based on the 2019 period life table for the Social Security, IRS Required Minimum Distribution (RMD) Worksheets, US historical bond and equity returns, and inflation rates using simulation. Several popular machine learning algorithms of the generalized additive model, random forest, support vector machine, extreme gradient boosting, and artificial neural network are built. The model validation and selection are based on the test errors using hyperparameter tuning and train-test split. The optimal model is recommended for retirees to monitor the ruin probability. The optimal withdrawal strategy can be obtained based on the optimal predictive model.

Keywords: ruin probability, retirement withdrawal strategies, predictive models, optimal model

Procedia PDF Downloads 74

Authors: A. M. Byrne, E. Bonfiglio, C. Rigby, N. Edelstyn

Abstract:

Introduction: Neuromarketing employs numerous methodologies when investigating products and advertisement effectiveness. Electroencephalography (EEG), a non-invasive measure of electrical activity from the brain, is commonly used in neuromarketing. EEG data can be considered using time-frequency (TF) analysis, where changes in the frequency of brainwaves are calculated to infer participant’s mental states, or event-related potential (ERP) analysis, where changes in amplitude are observed in direct response to a stimulus. This presentation discusses the findings of a systematic review of EEG measures in neuromarketing. A systematic review summarises evidence on a research question, using explicit measures to identify, select, and critically appraise relevant research papers. Thissystematic review identifies which EEG measures are the most robust predictor of customer preference and purchase intention. Methods: Search terms identified174 papers that used EEG in combination with marketing-related stimuli. Publications were excluded if they were written in a language other than English or were not published as journal articles (e.g., book chapters). The review investigated which TF effect (e.g., theta-band power) and ERP component (e.g., N400) most consistently reflected preference and purchase intention. Machine-learning prediction was also investigated, along with the use of EEG combined with physiological measures such as eye-tracking. Results: Frontal alpha asymmetry was the most reliable TF signal, where an increase in activity over the left side of the frontal lobe indexed a positive response to marketing stimuli, while an increase in activity over the right side indexed a negative response. The late positive potential, a positive amplitude increase around 600 ms after stimulus presentation, was the most reliable ERP component, reflecting the conscious emotional evaluation of marketing stimuli. However, each measure showed mixed results when related to preference and purchase behaviour. Predictive accuracy was greatly improved through machine-learning algorithms such as deep neural networks, especially when combined with eye-tracking or facial expression analyses. Discussion: This systematic review provides a novel catalogue of the most effective use of each EEG measure commonly used in neuromarketing. Exciting findings to emerge are the identification of the frontal alpha asymmetry and late positive potential as markers of preferential responses to marketing stimuli. Predictive accuracy using machine-learning algorithms achieved predictive accuracies as high as 97%, and future research should therefore focus on machine-learning prediction when using EEG measures in neuromarketing.

Keywords: EEG, ERP, neuromarketing, machine-learning, systematic review, time-frequency

Procedia PDF Downloads 111

Authors: Lule Basha, Eralda Gjika

Abstract:

This study is focused on analyzing climate change in Albania and its potential effects on cereal yields. Initially, monthly temperature and rainfalls in Albania were studied for the period 1960-2021. Climacteric variables are important variables when trying to model cereal yield behavior, especially when significant changes in weather conditions are observed. For this purpose, in the second part of the study, linear and nonlinear models explaining cereal yield are constructed for the same period, 1960-2021. The multiple linear regression analysis and lasso regression method are applied to the data between cereal yield and each independent variable: average temperature, average rainfall, fertilizer consumption, arable land, land under cereal production, and nitrous oxide emissions. In our regression model, heteroscedasticity is not observed, data follow a normal distribution, and there is a low correlation between factors, so we do not have the problem of multicollinearity. Machine-learning methods, such as random forest, are used to predict cereal yield responses to climacteric and other variables. Random Forest showed high accuracy compared to the other statistical models in the prediction of cereal yield. We found that changes in average temperature negatively affect cereal yield. The coefficients of fertilizer consumption, arable land, and land under cereal production are positively affecting production. Our results show that the Random Forest method is an effective and versatile machine-learning method for cereal yield prediction compared to the other two methods.

Keywords: cereal yield, climate change, machine learning, multiple regression model, random forest

Procedia PDF Downloads 91

Authors: José A. Menezes, Giordano Cabral, Bruno T. Gomes

Abstract:

Choosing good features is an essential part of machine learning. Recent techniques aim to automate this process. For instance, feature learning intends to learn the transformation of raw data into a useful representation to machine learning tasks. In automatic audio classification tasks, this is interesting since the audio, usually complex information, needs to be transformed into a computationally convenient input to process. Another technique tries to generate features by searching a feature space. Genetic algorithms, for instance, have being used to generate audio features by combining or modifying them. We find this approach particularly interesting and, despite the undeniable advances of feature learning approaches, we wanted to take a step forward in the use of genetic algorithms to find audio features, combining them with more conventional methods, like PCA, and inserting search control mechanisms, such as constraints over a confusion matrix. This work presents the results obtained on particular audio classification problems.

Keywords: feature generation, feature learning, genetic algorithm, music information retrieval

Procedia PDF Downloads 435

Authors: Maryam Shirmohammadi, Prasad K. D. V. Yarlagadda, YuanTong Gu

Abstract:

The mechanical damage on the agricultural crop during and after harvesting can create high volume of damage on tissue. Uniaxial compression and tensile loading were performed on flesh and peel samples of pumpkin. To investigate the structural changes on the tissue, Scanning Electron Microscopy (SEM) was used to capture the cellular structure change before and after loading on tissue for tensile, compression and indentation tests. To obtain required mechanical properties of tissue for the finite element analysis (FEA) model, laser measurement sensors were used to record the lateral displacement of tissue under the compression loading. Uniaxial force versus deformation data were recorded using Universal Testing Machine for both tensile and compression tests. The experimental Results were employed to develop a material model with failure criteria. The results obtained by the simulation were compared with those obtained by experiments. Note that although modelling food materials’ behaviour is not a new concept however, majority of previous studies focused on elastic behaviour and damages under linear limit, this study, however, has developed FEA models for tensile and compressive loading of pumpkin flesh and peel samples using, as the first study, both elastic and elasto-plastic material types. In addition, pumpkin peel and flesh tissues were considered as two different materials with different properties under mechanical loadings. The tensile and compression loadings were used to develop the material model for a composite structure for FEA model of mechanical peeling of pumpkin as a tough skinned vegetable.

Keywords: compressive and tensile response, finite element analysis, poisson’s ratio, elastic modulus, elastic and plastic response, rupture and bio-yielding

Procedia PDF Downloads 331

Authors: B. Almassri, F. Almahmoud, R. Francois

Abstract:

Near surface mounted reinforcement (NSM) technique is one of the promising techniques used nowadays to strengthen reinforced concrete (RC) structures. In the NSM technique, the Carbon Fibre Reinforced Polymer (CFRP) rods are placed inside pre-cut grooves and are bonded to the concrete with epoxy adhesive. This paper studies the non-classical mode of failure ‘the separation of concrete cover’ according to experimental and numerical FE modelling results. Experimental results and numerical modelling results of a 3D finite element (FE) model using the commercial software Abaqus and 2D FE model FEMIX were obtained on two beams, one corroded (25 years of corrosion procedure) and one control (A1CL3-R and A1T-R) were each repaired in bending using NSM CFRP rod and were then tested up to failure. The results showed that the NSM technique increased the overall capacity of control and corroded beams despite a non-classical mode of failure with separation of the concrete cover occurring in the corroded beam due to damage induced by corrosion. Another FE model used external steel stirrups around the repaired corroded beam A1CL3-R which failed with the separation of concrete cover, this model showed a change in the mode of failure form a non-classical mode of failure by the separation of concrete cover to the same mode of failure of the repaired control beam by the crushing of compressed concrete.

Keywords: corrosion, repair, Reinforced Concrete, FEM, CFRP, FEMIX

Procedia PDF Downloads 164

Authors: Y. Bablu Singh, B. S. Purkayashtha, Chungkham Yashawanta Singh

Abstract:

Morphological analysis forms the basic foundation in NLP applications including syntax parsing Machine Translation (MT), Information Retrieval (IR) and automatic indexing in all languages. It is the field of the linguistics; it can provide valuable information for computer based linguistics task such as lemmatization and studies of internal structure of the words. Computational Morphology is the application of morphological rules in the field of computational linguistics, and it is the emerging area in AI, which studies the structure of words, which are formed by combining smaller units of linguistics information, called morphemes: the building blocks of words. Morphological analysis provides about semantic and syntactic role in a sentence. It analyzes the Manipuri word forms and produces several grammatical information associated with the words. The Morphological Analyzer for Manipuri has been tested on 3500 Manipuri words in Shakti Standard format (SSF) using Meitei Mayek as source; thereby an accuracy of 80% has been obtained on a manual check.

Keywords: morphological analysis, machine translation, computational morphology, information retrieval, SSF

Procedia PDF Downloads 326

Authors: Surita Maini, Sanjay Dhanka

Abstract:

Machine learning (ML) involves developing algorithms and statistical models that enable computers to learn and make predictions or decisions based on data without being explicitly programmed. Because of its unlimited abilities ML is gaining popularity in medical sectors; Medical Imaging, Electronic Health Records, Genomic Data Analysis, Wearable Devices, Disease Outbreak Prediction, Disease Diagnosis, etc. In the last few decades, many researchers have tried to diagnose Breast Cancer (BC) using ML, because early detection of any disease can save millions of lives. Working in this direction, the authors have proposed a hybrid ML technique RBF SVM, to predict the BC in earlier the stage. The proposed method is implemented on the Breast Cancer UCI ML dataset with 569 instances and 32 attributes. The authors recorded performance metrics of the proposed model i.e., Accuracy 98.24%, Sensitivity 98.67%, Specificity 97.43%, F1 Score 98.67%, Precision 98.67%, and run time 0.044769 seconds. The proposed method is validated by K-Fold cross-validation.

Keywords: breast cancer, support vector classifier, machine learning, hyper parameter tunning

Procedia PDF Downloads 67

Authors: Gómez R. Marta, Martín M. Jesús María

Abstract:

The general aim of this paper identifies the areas of highest concentration of polychlorinated dibenzo-p-dioxins and dibenzofurans (PCDD/Fs) around the incinerator through the use of dispersion models. Atmospheric dispersion models are useful tools for estimating and prevent the impact of emissions from a particular source in air quality. These models allow considering different factors that influence in air pollution: source characteristics, the topography of the receiving environment and weather conditions to predict the pollutants concentration. The PCDD/Fs, after its emission into the atmosphere, are deposited on water or land, near or far from emission source depending on the size of the associated particles and climatology. In this way, they are transferred and mobilized through environmental compartments. The modelling of PCDD/Fs was carried out with following tools: Atmospheric Dispersion Model Software (ADMS) and Surfer. ADMS is a dispersion model Gaussian plume, used to model the impact of air quality industrial facilities. And Surfer is a program of surfaces which is used to represent the dispersion of pollutants on a map. For the modelling of emissions, ADMS software requires the following input parameters: characterization of emission sources (source type, height, diameter, the temperature of the release, flow rate, etc.) meteorological and topographical data (coordinate system), mainly. The study area was set at 5 Km around the incinerator and the first population center nearest to focus PCDD/Fs emission is about 2.5 Km, approximately. Data were collected during one year (2013) both PCDD/Fs emissions of the incinerator as meteorology in the study area. The study has been carried out during period's average that legislation establishes, that is to say, the output parameters are taking into account the current legislation. Once all data required by software ADMS, described previously, are entered, and in order to make the representation of the spatial distribution of PCDD/Fs concentration and the areas affecting them, the modelling was proceeded. In general, the dispersion plume is in the direction of the predominant winds (Southwest and Northeast). Total levels of PCDD/Fs usually found in air samples, are from <2 pg/m3 for remote rural areas, from 2-15 pg/m3 in urban areas and from 15-200 pg/m3 for areas near to important sources, as can be an incinerator. The results of dispersion maps show that maximum concentrations are the order of 10-8 ng/m3, well below the values considered for areas close to an incinerator, as in this case.

Keywords: atmospheric dispersion, dioxin, furan, incinerator

Procedia PDF Downloads 217

Authors: Radoslav Židek, Veronika Šidlová, Radovan Kasarda, Birgit Fuerst-Waltl

Abstract:

Machine learning represents a set of topics dealing with the creation and evaluation of algorithms that facilitate pattern recognition, classification, and prediction, based on models derived from existing data. The data can present identification patterns which are used to classify into groups. The result of the analysis is the pattern which can be used for identification of data set without the need to obtain input data used for creation of this pattern. An important requirement in this process is careful data preparation validation of model used and its suitable interpretation. For breeders, it is important to know the origin of animals from the point of the genetic diversity. In case of missing pedigree information, other methods can be used for traceability of animal´s origin. Genetic diversity written in genetic data is holding relatively useful information to identify animals originated from individual countries. We can conclude that the application of data mining for molecular genetic data using supervised learning is an appropriate tool for hypothesis testing and identifying an individual.

Keywords: genetic data, Pinzgau cattle, supervised learning, machine learning

Procedia PDF Downloads 550

Authors: Recep Karadag

Abstract:

Natural dyeing had started since pre-historical times for dyeing of textile materials. The natural dyeing had continued to beginning of 20th century. At the end of 19th century some synthetic dyes were synthesized. Although development of dyeing technologies and methods, natural dyeing was not developed in recent years. Despite rapid advances of synthetic dyestuff industries, natural dye processes have not developed. Therefore natural dyeing was not competed against synthetic dyes. At the same time, it was very difficult that large quantities of coloured textile was dyed with natural dyes And it was very difficult to get reproducible results in the natural dyeing using classical and traditional processes. However, natural dyeing has used slightly in the textile handicraft up to now. It is very important view that re-using of natural dyes to create awareness in textiles in recent years. Natural dyes have got many awareness and sustainability properties. Natural dyes are more eco-friendly than synthetic dyes. A lot of natural dyes have got antioxidant, antibacterial, antimicrobial, antifungal and anti –UV properties. It had been known that were obtained limited numbers colours with natural dyes in the past. On the contrary, colour scale is too wide with natural dyes. Except fluorescent colours, numerous colours can be obtained with natural dyes. Fastnesses of dyed textiles with natural dyes are good that there are light, washing, rubbing, etc. The fastness values can be improved depend on dyeing processes. Thanks to these properties mass production can be made with natural dyes in textiles. Therefore fabric dyeing machine was designed. This machine is too suitable for natural dyeing and mass production. Also any dyeing machine can be modified for natural dyeing. Although dye extraction and dyeing are made separately in the traditional natural dyeing processes and these procedures are become by designed this machine. Firstly, colouring compounds are extracted from natural dye resources, then dyeing is made with extracted colouring compounds. The colouring compounds are moderately dissolved in water. Less water is used in the extraction of colouring compounds from dye resources and dyeing with this new technique on the contrary much quantity water needs to use for dissolve of the colouring compounds in the traditional dyeing. This dyeing technique is very useful method for mass productions with natural dyes in traditional natural dyeing that use less energy, less dye materials, less water, etc. than traditional natural dyeing techniques. In this work, cotton, silk, linen and wool fabrics were dyed with some natural dye plants by the technique. According to the analysis very good results were obtained by this new technique. These results are shown sustainability and awareness of natural dyes for textiles.

Keywords: antibacterial, antimicrobial, natural dyes, sustainability

Procedia PDF Downloads 522

Authors: M. Baldini, H. K. Jacobsen, M. Jaccard

Abstract:

In light of the international efforts to comply with the Paris agreement and emission targets for future energy systems, Denmark and Canada are among the front-runner countries dealing with climate change. The experiences in the energy sector have seen both countries coping with trade-offs between investments in renewable energy technologies and energy efficiency, thus tackling the climate issue from the supply and demand side respectively. On the demand side, the industrial sector is going through a remarkable transformation, with implementation of energy efficiency measures, change of input fuel for end-use processes and forecasted electrification as main features under the spotlight. By looking at Canada and Denmark's experiences as pathfinders on the demand and supply approach to climate change, it is possible to obtain valuable experience that may be applied to other countries aiming at the same goal. This paper presents a comparative study on industrial energy efficiency between Canada and Denmark. The study focuses on technologies and system options, policy design and implementation and modelling methodologies when implementing industrial energy savings in optimization models in comparison to simulation models. The study identifies gaps and junctures in the approach towards climate change actions and, learning from each other, lessen the differences to further foster the adoption of energy efficiency measurements in the industrial sector, aiming at reducing energy consumption and, consequently, CO₂ emissions.

Keywords: industrial energy efficiency, comparative study, CO₂ reduction, energy system modelling

Procedia PDF Downloads 172

Authors: Jigg L. Pelayo, Ricardo G. Villar, Einstine M. Opiso

Abstract:

The advances of aerial laser scanning in the Philippines has open-up entire fields of research in remote sensing and machine vision aspire to provide accurate timely information for the government and the public. Rapid mapping of polygonal roads and roof boundaries is one of its utilization offering application to disaster risk reduction, mitigation and development. The study uses low density LiDAR data and high resolution aerial imagery through object-oriented approach considering the theoretical concept of data analysis subjected to machine learning algorithm in minimizing the constraints of feature extraction. Since separating one class from another in distinct regions of a multi-dimensional feature-space, non-trivial computing for fitting distribution were implemented to formulate the learned ideal hyperplane. Generating customized hybrid feature which were then used in improving the classifier findings. Supplemental algorithms for filtering and reshaping object features are develop in the rule set for enhancing the final product. Several advantages in terms of simplicity, applicability, and process transferability is noticeable in the methodology. The algorithm was tested in the different random locations of Misamis Oriental province in the Philippines demonstrating robust performance in the overall accuracy with greater than 89% and potential to semi-automation. The extracted results will become a vital requirement for decision makers, urban planners and even the commercial sector in various assessment processes.

Keywords: feature extraction, machine learning, OBIA, remote sensing

Procedia PDF Downloads 362

Authors: Varun Dongre, Stefan Pirker, Stefan Heinrich

Abstract:

Over the last decades, the numerical modelling of fluidized bed processes has become feasible even for industrial processes. Commonly, continuous two-fluid models are applied to describe large-scale fluidization. In order to allow for coarse grids novel two-fluid models account for unresolved sub-grid heterogeneities. However, computational efforts remain high – in the order of several hours of compute-time for a few seconds of real-time – thus preventing the representation of long-term phenomena such as heating or particle conversion processes. In order to overcome this limitation, data-based recurrence computational fluid dynamics (rCFD) has been put forward in recent years. rCFD can be regarded as a data-based method that relies on the numerical predictions of a conventional short-term simulation. This data is stored in a database and then used by rCFD to efficiently time-extrapolate the flow behavior in high spatial resolution. This study will compare the numerical predictions of rCFD simulations with those of corresponding full CFD reference simulations for lab-scale and pilot-scale fluidized beds. In assessing the predictive capabilities of rCFD simulations, we focus on solid mixing and secondary gas holdup. We observed that predictions made by rCFD simulations are highly sensitive to numerical parameters such as diffusivity associated with face swaps. We achieved a computational speed-up of four orders of magnitude (10,000 time faster than classical TFM simulation) eventually allowing for real-time simulations of fluidized beds. In the next step, we apply the checkerboarding technique by introducing gas tracers subjected to convection and diffusion. We then analyze the concentration profiles by observing mixing, transport of gas tracers, insights about the convective and diffusive pattern of the gas tracers, and further towards heat and mass transfer methods. Finally, we run rCFD simulations and calibrate them with numerical and physical parameters compared with convectional Two-fluid model (full CFD) simulation. As a result, this study gives a clear indication of the applicability, predictive capabilities, and existing limitations of rCFD in the realm of fluidization modelling.

Keywords: multiphase flow, recurrence CFD, two-fluid model, industrial processes

Procedia PDF Downloads 75

Authors: Gebremeskel Hagos Gebremedhin, Feng Chong, Heyan Huang

Abstract:

Software system is the combination of architecture and organized components to accomplish a specific function or set of functions. A good software architecture facilitates application system development, promotes achievement of functional requirements, and supports system reconfiguration. We describe three studies demonstrating the utility of our architecture in the subdomain of mobile office robots and identify software engineering principles embodied in the architecture. The main aim of this paper is to analyze prove architecture design and automatic re-architecting using machine learning. Intelligence software architecture and automatic re-architecting process is reorganizing in to more suitable one of the software organizational structure system using the user access dataset for creating relationship among the components of the system. The 3-step approach of data mining was used to analyze effective recovery, transformation and implantation with the use of clustering algorithm. Therefore, automatic re-architecting without changing the source code is possible to solve the software complexity problem and system software reuse.

Keywords: intelligence, software architecture, re-architecting, software reuse, High level design

Procedia PDF Downloads 119

Authors: Amira Abdelhafez, Rufus Brunt

Abstract:

Geothermal energy in Egypt represents a significant untapped renewable resource that can reduce reliance on conventional power generation. Exploiting these geothermal resources depends on depth, temperature range, and geological characteristics. The intracontinental rift setting of the Gulf of Suez (GoS)-Red Sea rift is a favourable tectonic setting for convection-dominated geothermal plays. The geothermal gradient across the GoS ranges from 24.9 to 86.66 °C/km, with a heat flow of 31-127.2 mW/m². Surface expressions of convective heat loss emerge along the gulf flanks as hot springs (e.g., Hammam Faraun) accompanying deeper geothermal resources. These thermal anomalies are driven mainly by the local tectonic configuration. Characterizing the structural framework of major faults and their control on reservoir properties and subsurface hydrothermal fluid circulation is vital for geothermal applications in the gulf. The geothermal play systems of the GoS depend on structural and lithological properties that contribute to heat storage and vertical transport. Potential geothermal reservoirs include the Nubia sandstones, which, due to their thickness, continuity, and contact with hot basement rocks at a mean depth of 3 km, create an extensive reservoir for geothermal fluids. To develop these geothermal resources for energy production, defining the permeability anisotropy of the reservoir due to faults and facies variation is a crucial step in our study, particularly the evaluation of influence on thermal breakthrough and production rates.

Keywords: geothermal, October field, site specific study, reservoir modelling

Procedia PDF Downloads 11

Authors: L. Al Ahmad, C. Latrille, D. Hainos, D. Blanc, M. Clausse

Abstract:

A two-dimensional finite volume axisymmetric model is developed to predict the simultaneous heat and mass transfers during the drying of industrial sludge. The simulations were run using COMSOL-Multiphysics 3.5a. The input parameters of the numerical model were acquired from a preliminary experimental work. Results permit to establish correlations describing the evolution of the various parameters as a function of the drying temperature and the sludge water content. The selection and coupling of the equation are validated based on the drying kinetics acquired experimentally at a temperature range of 45-65 °C and absolute pressure range of 200-1000 mbar. The model, incorporating the heat and mass transfer mechanisms at different operating conditions, shows simulated values of temperature and water content. Simulated results are found concordant with the experimental values, only at the first and last drying stages where sludge shrinkage is insignificant. Simulated and experimental results show that sludge drying is favored at high temperatures and low pressure. As experimentally observed, the drying time is reduced by 68% for drying at 65 °C compared to 45 °C under 1 atm. At 65 °C, a 200-mbar absolute pressure vacuum leads to an additional reduction in drying time estimated by 61%. However, the drying rate is underestimated in the intermediate stage. This rate underestimation could be improved in the model by considering the shrinkage phenomena that occurs during sludge drying.

Keywords: industrial sludge drying, heat transfer, mass transfer, mathematical modelling

Procedia PDF Downloads 134

Authors: Szymon Rutkowski, Tomasz Korbak

Abstract:

We present a reinforcement-learning-based method of training neural machine translation models without parallel corpora. The standard encoder-decoder approach to machine translation suffers from two problems we aim to address. First, it needs parallel corpora, which are scarce, especially for low-resource languages. Second, it lacks psychological plausibility of learning procedure: learning a foreign language is about learning to communicate useful information, not merely learning to transduce from one language’s 'encoding' to another. We instead pose the problem of learning to translate as learning a policy in a communication game between two agents: the translator and the classifier. The classifier is trained beforehand on a natural language inference task (determining the entailment relation between a premise and a hypothesis) in the target language. The translator produces a sequence of actions that correspond to generating translations of both the hypothesis and premise, which are then passed to the classifier. The translator is rewarded for classifier’s performance on determining entailment between sentences translated by the translator to disciple’s native language. Translator’s performance thus reflects its ability to communicate useful information to the classifier. In effect, we train a machine translation model without the need for parallel corpora altogether. While similar reinforcement learning formulations for zero-shot translation were proposed before, there is a number of improvements we introduce. While prior research aimed at grounding the translation task in the physical world by evaluating agents on an image captioning task, we found that using a linguistic task is more sample-efficient. Natural language inference (also known as recognizing textual entailment) captures semantic properties of sentence pairs that are poorly correlated with semantic similarity, thus enforcing basic understanding of the role played by compositionality. It has been shown that models trained recognizing textual entailment produce high-quality general-purpose sentence embeddings transferrable to other tasks. We use stanford natural language inference (SNLI) dataset as well as its analogous datasets for French (XNLI) and Polish (CDSCorpus). Textual entailment corpora can be obtained relatively easily for any language, which makes our approach more extensible to low-resource languages than traditional approaches based on parallel corpora. We evaluated a number of reinforcement learning algorithms (including policy gradients and actor-critic) to solve the problem of translator’s policy optimization and found that our attempts yield some promising improvements over previous approaches to reinforcement-learning based zero-shot machine translation.

Keywords: agent-based language learning, low-resource translation, natural language inference, neural machine translation, reinforcement learning

Procedia PDF Downloads 128

Authors: Luisa Carrer, Lorenzo De Masi

Abstract:

In this paper, we exploit the massive amount of information from Facebook to build a measure of gender attitudes in Italy at a previously impossible resolution—the municipal level. We construct our index via a machine learning method to replicate a benchmark region-level measure. Interestingly, we find that most of the variation in our Gender Norms Index (GNI) is across towns within narrowly defined geographical areas rather than across regions or provinces. In a second step, we show how this local variation in norms can be leveraged for identification purposes. In particular, we use our index to investigate whether these differences in norms carry over to the policy activity of politicians elected in the Italian Parliament. We document that females are more likely to sit in parliamentary committees focused on gender-sensitive matters, labor, and social issues, but not if they come from a relatively conservative town. These effects are robust to conditioning the legislative term and electoral district, suggesting the importance of social norms in shaping legislators’ policy activity.

Keywords: gender equality, gender norms index, Facebook, machine learning, politics

Procedia PDF Downloads 78

Authors: Yasmine Abu Adla, Racha Soubra, Milana Kasab, Mohamad O. Diab, Aly Chkeir

Abstract:

Over the past several years, researchers have shown a great interest in assessing the mobility of elderly people to measure their functional status. Usually, such an assessment is done by conducting tests that require the subject to walk a certain distance, turn around, and finally sit back down. Consequently, this study aims to provide an at home monitoring system to assess the patient’s status continuously. Thus, we proposed a technique to automatically detect when a subject sits down while walking at home. In this study, we utilized a Doppler radar system to capture the motion of the subjects. More than 20 features were extracted from the radar signals, out of which 11 were chosen based on their intraclass correlation coefficient (ICC > 0.75). Accordingly, the sequential floating forward selection wrapper was applied to further narrow down the final feature vector. Finally, 5 features were introduced to the linear discriminant analysis classifier, and an accuracy of 93.75% was achieved as well as a precision and recall of 95% and 90%, respectively.

Keywords: Doppler radar system, stand-to-sit phase, TUG test, machine learning, classification

Procedia PDF Downloads 161

Authors: C. Castro-Egler, A. Durán-Escalante, A. García-González

Abstract:

This paper presents a method to generate a finite element model of the human auditory inner ear system. The geometric model has been realized using 2D images from a virtual model of temporal bones. A point cloud has been gotten manually from those images to construct a whole mesh with hexahedral elements. The main difference with the predecessor models is the spiral shape of the cochlea with its three scales completely defined: scala tympani, scala media and scala vestibuli; which are separate by basilar membrane and Reissner membrane. To validate this model, numerical simulations have been realised with two models: an isolated inner ear and a whole model of human auditory system. Ideal conditions of displacement are applied over the oval window in the isolated Inner Ear model. The whole model is made up of the outer auditory channel, the tympani, the ossicular chain, and the inner ear. The boundary condition for the whole model is 1Pa over the auditory channel entrance. The numerical simulations by FEM have been done using a harmonic analysis with a frequency range between 100-10.000 Hz with an interval of 100Hz. The following results have been carried out: basilar membrane displacement; the scala media pressure according to the cochlea length and the transfer function of the middle ear normalized with the pressure in the tympanic membrane. The basilar membrane displacements and the pressure in the scala media make it possible to validate the response in frequency of the basilar membrane.

Keywords: finite elements method, human auditory system model, numerical analysis, 3D modelling cochlea

Procedia PDF Downloads 362

Authors: Rodrigo S. Fonseca, Antônio C. P. Veiga

Abstract:

Aiming at helping people with some movement limitation that makes typing and communication difficult, there is a need to customize an assistive tool with a learning environment that helps the user in order to optimize text input, identifying the error and providing the correction and possibilities of choice in the Portuguese language. The work presents an Orthographic and Grammatical System that can be incorporated into writing environments, improving and facilitating the use of an alphanumeric keyboard, using a prototype built using a genetic algorithm in addition to carrying out the prediction, which can occur based on the quantity and position of the inserted letters and even placement in the sentence, ensuring the sequence of ideas using a Long Short Term Memory (LSTM) neural network. The prototype optimizes data entry, being a component of assistive technology for the textual formulation, detecting errors, seeking solutions and informing the user of accurate predictions quickly and effectively through machine learning.

Keywords: genetic algorithm, neural networks, word prediction, machine learning

Procedia PDF Downloads 194

Authors: Aadityaa Singla

Abstract:

The big five personality traits are as follows: openness, conscientiousness, extraversion, agreeableness, and neuroticism. In order to get an insight into their personality, many flocks to these categories, which each have different meanings/characteristics. This information is important not only to individuals but also to career professionals and psychologists who can use this information for candidate assessment or job recruitment. The links between AI and psychology have been well studied in cognitive science, but it is still a rather novel development. It is possible for various AI classification models to accurately predict a personality question via ten input questions. This would contrast with the hundred questions that normal humans have to answer to gain a complete picture of their five personality traits. In order to approach this problem, various AI classification models were used on a dataset to predict what a user may answer. From there, the model's prediction was compared to its actual response. Normally, there are five answer choices (a 20% chance of correct guess), and the models exceed that value to different degrees, proving their significance. By utilizing an MLP classifier, decision tree, linear model, and K-nearest neighbors, they were able to obtain a test accuracy of 86.643, 54.625, 47.875, and 52.125, respectively. These approaches display that there is potential in the future for more nuanced predictions to be made regarding personality.

Keywords: machine learning, personally, big five personality traits, cognitive science

Procedia PDF Downloads 145

Authors: Hayriye Anıl, Görkem Kar

Abstract:

In addition to being rich in renewable energy resources, Turkey is one of the countries that promise potential in geothermal energy production with its high installed power, cheapness, and sustainability. Increasing imbalance penalties become an economic burden for organizations since geothermal generation plants cannot maintain the balance of supply and demand due to the inadequacy of the production forecasts given in the day-ahead market. A better production forecast reduces the imbalance penalties of market participants and provides a better imbalance in the day ahead market. In this study, using machine learning, deep learning, and, time series methods, the total generation of the power plants belonging to Zorlu Natural Electricity Generation, which has a high installed capacity in terms of geothermal, was estimated for the first one and two weeks of March, then the imbalance penalties were calculated with these estimates and compared with the real values. These modeling operations were carried out on two datasets, the basic dataset and the dataset created by extracting new features from this dataset with the feature engineering method. According to the results, Support Vector Regression from traditional machine learning models outperformed other models and exhibited the best performance. In addition, the estimation results in the feature engineering dataset showed lower error rates than the basic dataset. It has been concluded that the estimated imbalance penalty calculated for the selected organization is lower than the actual imbalance penalty, optimum and profitable accounts.

Keywords: machine learning, deep learning, time series models, feature engineering, geothermal energy production forecasting

Procedia PDF Downloads 110

Authors: Ronit Chakraborty, Sugata Banerji

Abstract:

There has been a marked increase in the reported prevalence of Autism Spectrum Disorder (ASD) among children in the US over the past two decades. This research has analyzed the growth in state-level ASD prevalence against 45 different potentially explanatory factors, including socio-economic, demographic, healthcare, public policy, and political factors. The goal was to understand if these factors have adequate predictive power in modeling the differential growth in ASD prevalence across various states and if they do, which factors are the most influential. The key findings of this study include (1) the confirmation that the chosen feature set has considerable power in predicting the growth in ASD prevalence, (2) the identification of the most influential predictive factors, (3) given the nature of the most influential predictive variables, an indication that a considerable portion of the reported ASD prevalence differentials across states could be attributable to over and under diagnosis, and (4) identification of Florida as a key outlier state pointing to a potential under-diagnosis of ASD there.

Keywords: autism spectrum disorder, clustering, machine learning, predictive modeling

Procedia PDF Downloads 103

Authors: Pei Yi Lin

Abstract:

Objective: The objective of this study is to use machine learning methods to build an early prediction classifier model for acute delirium to improve the quality of medical care for intensive care patients. Background: Delirium is a common acute and sudden disturbance of consciousness in critically ill patients. After the occurrence, it is easy to prolong the length of hospital stay and increase medical costs and mortality. In 2021, the incidence of delirium in the intensive care unit of internal medicine was as high as 59.78%, which indirectly prolonged the average length of hospital stay by 8.28 days, and the mortality rate is about 2.22% in the past three years. Therefore, it is expected to build a delirium prediction classifier through big data analysis and machine learning methods to detect delirium early. Method: This study is a retrospective study, using the artificial intelligence big data database to extract the characteristic factors related to delirium in intensive care unit patients and let the machine learn. The study included patients aged over 20 years old who were admitted to the intensive care unit between May 1, 2022, and December 31, 2022, excluding GCS assessment <4 points, admission to ICU for less than 24 hours, and CAM-ICU evaluation. The CAMICU delirium assessment results every 8 hours within 30 days of hospitalization are regarded as an event, and the cumulative data from ICU admission to the prediction time point are extracted to predict the possibility of delirium occurring in the next 8 hours, and collect a total of 63,754 research case data, extract 12 feature selections to train the model, including age, sex, average ICU stay hours, visual and auditory abnormalities, RASS assessment score, APACHE-II Score score, number of invasive catheters indwelling, restraint and sedative and hypnotic drugs. Through feature data cleaning, processing and KNN interpolation method supplementation, a total of 54595 research case events were extracted to provide machine learning model analysis, using the research events from May 01 to November 30, 2022, as the model training data, 80% of which is the training set for model training, and 20% for the internal verification of the verification set, and then from December 01 to December 2022 The CU research event on the 31st is an external verification set data, and finally the model inference and performance evaluation are performed, and then the model has trained again by adjusting the model parameters. Results: In this study, XG Boost, Random Forest, Logistic Regression, and Decision Tree were used to analyze and compare four machine learning models. The average accuracy rate of internal verification was highest in Random Forest (AUC=0.86), and the average accuracy rate of external verification was in Random Forest and XG Boost was the highest, AUC was 0.86, and the average accuracy of cross-validation was the highest in Random Forest (ACC=0.77). Conclusion: Clinically, medical staff usually conduct CAM-ICU assessments at the bedside of critically ill patients in clinical practice, but there is a lack of machine learning classification methods to assist ICU patients in real-time assessment, resulting in the inability to provide more objective and continuous monitoring data to assist Clinical staff can more accurately identify and predict the occurrence of delirium in patients. It is hoped that the development and construction of predictive models through machine learning can predict delirium early and immediately, make clinical decisions at the best time, and cooperate with PADIS delirium care measures to provide individualized non-drug interventional care measures to maintain patient safety, and then Improve the quality of care.

Keywords: critically ill patients, machine learning methods, delirium prediction, classifier model

Procedia PDF Downloads 75

Authors: Mathieu Le Cam, Tejaswinee Darure, Mateusz Pawlucki

Abstract:

Climate control of cabin aircraft is traditionally conditioned as a single unit by the environmental control system. Cabin temperature is controlled by the crew while passengers of the aircraft have control on the gaspers providing fresh air from the above head area. The small nozzles are difficult to reach and adjust to meet the passenger’s needs in terms of flow and direction. More dedicated control over the near environment of each passenger can be beneficial in many situations. The European project COCOON, funded under Clean Sky 2, aims at developing and demonstrating a microclimate conditioning module (MCM) integrated into a standard economy 3-seat row. The system developed will lead to improved passenger comfort with more control on their personal thermal area. This study focuses on the assessment of thermal comfort of passengers in the cabin aircraft through simulation on the TAITherm modelling platform. A first analysis investigates thermal comfort and sensation of passengers in varying cabin environmental conditions: from cold to very hot scenarios, with and without MCM installed in the seats. The modelling platform is also used to evaluate the impact of different physiologies of passengers on their thermal comfort as well as different seat locations. Under the current cabin conditions, a passenger of a 50th percentile body size is feeling uncomfortably cool due to the high velocity cabin air ventilation. The simulation shows that the in-seat MCM developed in COCOON project improves the thermal comfort of the passenger.

Keywords: cabin aircraft, in-seat HVAC, microclimate conditioning module, thermal comfort

Procedia PDF Downloads 200

Authors: Man-Yun Liu, Emily Chia-Yu Su

Abstract:

Alzheimer's disease (AD) is the public health crisis of the 21st century. AD is a degenerative brain disease and the most common cause of dementia, a costly disease on the healthcare system. Unfortunately, the cause of AD is poorly understood, furthermore; the treatments of AD so far can only alleviate symptoms rather cure or stop the progress of the disease. Currently, there are several ways to diagnose AD; medical imaging can be used to distinguish between AD, other dementias, and early onset AD, and cerebrospinal fluid (CSF). Compared with other diagnostic tools, blood (plasma) test has advantages as an approach to population-based disease screening because it is simpler, less invasive also cost effective. In our study, we used blood biomarkers dataset of The Alzheimer’s disease Neuroimaging Initiative (ADNI) which was funded by National Institutes of Health (NIH) to do data analysis and develop a prediction model. We used independent analysis of datasets to identify plasma protein biomarkers predicting early onset AD. Firstly, to compare the basic demographic statistics between the cohorts, we used SAS Enterprise Guide to do data preprocessing and statistical analysis. Secondly, we used logistic regression, neural network, decision tree to validate biomarkers by SAS Enterprise Miner. This study generated data from ADNI, contained 146 blood biomarkers from 566 participants. Participants include cognitive normal (healthy), mild cognitive impairment (MCI), and patient suffered Alzheimer’s disease (AD). Participants’ samples were separated into two groups, healthy and MCI, healthy and AD, respectively. We used the two groups to compare important biomarkers of AD and MCI. In preprocessing, we used a t-test to filter 41/47 features between the two groups (healthy and AD, healthy and MCI) before using machine learning algorithms. Then we have built model with 4 machine learning methods, the best AUC of two groups separately are 0.991/0.709. We want to stress the importance that the simple, less invasive, common blood (plasma) test may also early diagnose AD. As our opinion, the result will provide evidence that blood-based biomarkers might be an alternative diagnostics tool before further examination with CSF and medical imaging. A comprehensive study on the differences in blood-based biomarkers between AD patients and healthy subjects is warranted. Early detection of AD progression will allow physicians the opportunity for early intervention and treatment.

Keywords: Alzheimer's disease, blood-based biomarkers, diagnostics, early detection, machine learning

Procedia PDF Downloads 322

Authors: Maxime A. J. Kuitche, Ruxandra M. Botez, Arthur Guillemin

Abstract:

As the Unmanned Aerial Systems have found diverse utilities in both military and civil aviation, the necessity to obtain an accurate aerodynamic model has shown an enormous growth of interest. Recent modeling techniques are procedures using optimization algorithms and statistics that require many flight tests and are therefore extremely demanding in terms of costs. This paper presents a procedure to estimate the aerodynamic behavior of an unmanned aerial system from a numerical approach using computational fluid dynamic analysis. The study was performed using an unstructured mesh obtained from a grid convergence analysis at a Mach number of 0.14, and at an angle of attack of 0°. The flow around the aircraft was described using a standard k-ω turbulence model. Thus, the Reynold Averaged Navier-Stokes (RANS) equations were solved using ANSYS FLUENT software. The method was applied on the UAS-S45 designed and manufactured by Hydra Technologies in Mexico. The lift, the drag, and the pitching moment coefficients were obtained at different angles of attack for several flight conditions defined in terms of altitudes and Mach numbers. The results obtained from the Computational Fluid Dynamics analysis were compared with the results obtained by using the DATCOM semi-empirical procedure. This comparison has indicated that our approach is highly accurate and that the aerodynamic model obtained could be useful to estimate the flight dynamics of the UAS-S45.

Keywords: aerodynamic modelling, CFD Analysis, ANSYS FLUENT, UAS-S45

Procedia PDF Downloads 375