Search results for: geometric and topological data models

Authors: Neerav Kumar, Naumaan Nayyar, Sharath Kashyap

Abstract:

Most companies see an increase in the adoption of machine learning (ML) applications across internal and external-facing use cases. ML applications vend output either in batch or real-time patterns. A complete batch ML pipeline architecture comprises data sourcing, feature engineering, model training, model deployment, model output vending into a data store for downstream application. Due to unclear role expectations, we have observed that scientists specializing in building and optimizing models are investing significant efforts into building the other components of the architecture, which we do not believe is the best use of scientists’ bandwidth. We propose a system architecture created using AWS services that bring industry best practices to managing the workflow and simplifies the process of model deployment and end-to-end data integration for an ML application. This narrows down the scope of scientists’ work to model building and refinement while specialized data engineers take over the deployment, pipeline orchestration, data quality, data permission system, etc. The pipeline infrastructure is built and deployed as code (using terraform, cdk, cloudformation, etc.) which makes it easy to replicate and/or extend the architecture to other models that are used in an organization.

Keywords: data pipeline, machine learning, AWS, architecture, batch machine learning

Procedia PDF Downloads 31

Authors: L. J. de Bessa Neto, V. S. Filho, J. V. Ferreira Nunes, G. C. Bergamo

Abstract:

There are many situations in which human activities have significant effects on the environment. Damage to the ozone layer is one of them. The objective of this work is to use the Least Squares Method, considering the linear, exponential, logarithmic, power and polynomial models of the second degree, to analyze through the coefficient of determination (R²), which model best fits the behavior of the chlorodifluoromethane (HCFC-142b) in parts per trillion between 1992 and 2018, as well as estimates of future concentrations between 5 and 10 periods, i.e. the concentration of this pollutant in the years 2023 and 2028 in each of the adjustments. A total of 809 observations of the concentration of HCFC-142b in one of the monitoring stations of gases precursors of the deterioration of the ozone layer during the period of time studied were selected and, using these data, the statistical software Excel was used for make the scatter plots of each of the adjustment models. With the development of the present study, it was observed that the logarithmic fit was the model that best fit the data set, since besides having a significant R² its adjusted curve was compatible with the natural trend curve of the phenomenon.

Keywords: chlorodifluoromethane (HCFC-142b), ozone, least squares method, regression models

Procedia PDF Downloads 96

Authors: Cheikh Bamba Dione, Alla Lo, Elhadji Mamadou Nguer, Siley O. Ba

Abstract:

In this paper, we propose two neural machine translation (NMT) systems (French-to-Wolof and Wolof-to-French) based on sequence-to-sequence with attention and transformer architectures. We trained our models on a parallel French-Wolof corpus of about 83k sentence pairs. Because of the low-resource setting, we experimented with advanced methods for handling data sparsity, including subword segmentation, back translation, and the copied corpus method. We evaluate the models using the BLEU score and find that transformer outperforms the classic seq2seq model in all settings, in addition to being less sensitive to noise. In general, the best scores are achieved when training the models on word-level-based units. For subword-level models, using back translation proves to be slightly beneficial in low-resource (WO) to high-resource (FR) language translation for the transformer (but not for the seq2seq) models. A slight improvement can also be observed when injecting copied monolingual text in the target language. Moreover, combining the copied method data with back translation leads to a substantial improvement of the translation quality.

Keywords: backtranslation, low-resource language, neural machine translation, sequence-to-sequence, transformer, Wolof

Procedia PDF Downloads 113

Authors: Mostafa Gamal, Hoda K. Mohamed, Islam El-Maddah, Ali Hamdi

Abstract:

In recent years, many digital documents on the web have been created due to the rapid growth of ’social applications’ communities or ’Data-intensive applications’. The evolution of online-based multimedia data poses new challenges in storing and querying large amounts of data for online recommender systems. Graph data models have been shown to be more efficient than relational data models for processing complex data. This paper will explain the key differences between graph and relational databases, their strengths and weaknesses, and why using graph databases is the best technology for building a realtime recommendation system. Also, The paper will discuss several similarity metrics algorithms that can be used to compute a similarity score of pairs of nodes based on their neighbourhoods or their properties. Finally, the paper will discover how NLP strategies offer the premise to improve the accuracy and coverage of realtime recommendations by extracting the information from the stored unstructured knowledge, which makes up the bulk of the world’s data to enrich the graph database with this information. As the size and number of data items are increasing rapidly, the proposed system should meet current and future needs.

Keywords: graph databases, NLP, recommendation systems, similarity metrics

Procedia PDF Downloads 73

Authors: Mohamed Arbi Khlifi, Badr M. Alshammari

Abstract:

This paper discusses the general methods to saturation in the steady-state, two axis (d & q) frame models of synchronous machines. In particular, the important role of the magnetic coupling between the d-q axes (cross-magnetizing phenomenon), is demonstrated. For that purpose, distinct methods of saturation modeling of dumper synchronous machine with cross-saturation are identified, and detailed models synthesis in d-q axes. A number of models are given in the final developed form. The procedure and the novel models are verified by a critical application to prove the validity of the method and the equivalence between all developed models is reported. Advantages of some of the models over the existing ones and their applicability are discussed.

Keywords: cross-magnetizing, models synthesis, synchronous machine, saturated modeling, state-space vectors

Procedia PDF Downloads 425

Authors: Mohamed Elhakeem, A. N. Thanos Papanicolaou, Christopher Wilson, Yi-Jia Chang

Abstract:

In this study, a physically-based, modelling framework was developed to predict saturated hydraulic conductivity (KSAT) dynamics in the Clear Creek Watershed (CCW), Iowa. The modelling framework integrated selected pedotransfer functions and watershed models with geospatial tools. A number of pedotransfer functions and agricultural watershed models were examined to select the appropriate models that represent the study site conditions. Models selection was based on statistical measures of the models’ errors compared to the KSAT field measurements conducted in the CCW under different soil, climate and land use conditions. The study has shown that the predictions of the combined pedotransfer function of Rosetta and the Water Erosion Prediction Project (WEPP) provided the best agreement to the measured KSAT values in the CCW compared to the other tested models. Therefore, Rosetta and WEPP were integrated with the Geographic Information System (GIS) tools for visualization of the data in forms of geospatial maps and prediction of KSAT variability in CCW due to the seasonal changes in climate and land use activities.

Keywords: saturated hydraulic conductivity, pedotransfer functions, watershed models, geospatial tools

Procedia PDF Downloads 226

Authors: John Allard, Alex Rich, Iris Aguilar, Zachary Dodds

Abstract:

With this paper we present several experiences deploying novel, low-cost resources for computing with 3D spatial models. Certainly, computing with 3D models undergirds some of our field’s most important contributions to the human experience. Most often, those are contrived artifacts. This work extends that tradition by focusing on novel resources that deliver uncontrived models of a system’s current surroundings. Atop this new capability, we present several projects investigating the student-accessibility of the computational tools for reasoning about the 3D space around us. We conclude that, with current scaffolding, real-world 3D models are now an accessible and viable foundation for creative computational work.

Keywords: 3D vision, matterport model, real-world 3D models, mathematical and computational methods

Procedia PDF Downloads 510

Authors: Gadah Alkeniah

Abstract:

Leadership is acknowledged internationally as fundamental to school efficiency and school enhancement nevertheless there are various understandings of what leadership is and how it is realised in practice. There are a number of educational leadership models that are considered important. However, the present study uses a systematic review method to examine and compare five models of the most well-known contemporary models of leadership as well as introduces the dimension of each model. Our results reveal that recently the distributed leadership has grown in popularity within the field of education. The study concludes by suggesting future directions in leadership development and education research.

Keywords: distributed leadership, instructional leadership, leadership models, moral leadership, strategic leadership, transformational leadership

Procedia PDF Downloads 176

Authors: Krishang Surapaneni

Abstract:

The goal of this project is to determine how to predict important aspects of options, including the ask price. We want to compare different machine learning models to learn the best model and the best hyperparameters for that model for this purpose and data set. Option pricing is a relatively new field, and it can be very complicated and intimidating, especially to inexperienced people, so we want to create a machine learning model that can predict important aspects of an option stock, which can aid in future research. We tested multiple different models and experimented with hyperparameter tuning, trying to find some of the best parameters for a machine-learning model. We tested three different models: a Random Forest Regressor, a linear regressor, and an MLP (multi-layer perceptron) regressor. The most important feature in this experiment is the ask price; this is what we were trying to predict. In the field of stock pricing prediction, there is a large potential for error, so we are unable to determine the accuracy of the models based on if they predict the pricing perfectly. Due to this factor, we determined the accuracy of the model by finding the average percentage difference between the predicted and actual values. We tested the accuracy of the machine learning models by comparing the actual results in the testing data and the predictions made by the models. The linear regression model performed worst, with an average percentage error of 17.46%. The MLP regressor had an average percentage error of 11.45%, and the random forest regressor had an average percentage error of 7.42%

Keywords: finance, linear regression model, machine learning model, neural network, stock price

Procedia PDF Downloads 54

Authors: Melodi Mbuyi Mata, Blessing Olamide Taiwo, Afolabi Ayodele David

Abstract:

The purpose of this research is to create empirical models for assessing the profitability of granite aggregate production in Akure, Ondo state aggregate quarries. In addition, an artificial neural network (ANN) model and multivariate predicting models for granite profitability were developed in the study. A formal survey questionnaire was used to collect data for the study. The data extracted from the case study mine for this study includes granite marketing operations, royalty, production costs, and mine production information. The following methods were used to achieve the goal of this study: descriptive statistics, MATLAB 2017, and SPSS16.0 software in analyzing and modeling the data collected from granite traders in the study areas. The ANN and Multi Variant Regression models' prediction accuracy was compared using a coefficient of determination (R²), Root mean square error (RMSE), and mean square error (MSE). Due to the high prediction error, the model evaluation indices revealed that the ANN model was suitable for predicting generated profit in a typical quarry. More quarries in Nigeria's southwest region and other geopolitical zones should be considered to improve ANN prediction accuracy.

Keywords: national development, granite, profitability assessment, ANN models

Procedia PDF Downloads 71

Authors: Kanokkan Titipornpun, Tripob Bhongsuwan, Jan Gimsa

Abstract:

The Ko Samui district of Surat Thani province is located in the high amounts of equivalent uranium in the ground surface that is the source of radon. Our research in the Ko Samui district aimed at comparing the indoor radon concentrations between dwellings and workplaces. Measurements of indoor radon concentrations were carried out in 46 dwellings and 127 workplaces, using CR-39 alpha-track detectors in closed-cup. A total of 173 detectors were distributed in 7 sub-districts. The detectors were placed in bedrooms of dwellings and workrooms of workplaces. All detectors were exposed to airborne radon for 90 days. After exposure, the alpha tracks were made visible by chemical etching before they were manually counted under an optical microscope. The track densities were assumed to be correlated with the radon concentration levels. We found that the radon concentrations could be well described by a log-normal distribution. Most concentrations (37%) were found in the range between 16 and 30 Bq.m^-3. The radon concentrations in dwellings and workplaces varied from a minimum of 11 Bq.m^-3 to a maximum of 305 Bq.m^-3. The minimum (11 Bq.m^-3) and maximum (305 Bq.m^-3) values of indoor radon concentrations were found in a workplace and a dwelling, respectively. Only for four samples (3%), the indoor radon concentrations were found to be higher than the reference level recommended by the WHO (100 Bq.m^-3). The overall geometric mean in the surveyed area was 32.6±1.65 Bq.m^-3, which was lower than the worldwide average (39 Bq.m^-3). The statistic comparison of the geometric mean indoor radon concentrations between dwellings and workplaces showed that the geometric mean in dwellings (46.0±1.55 Bq.m^-3) was significantly higher than in workplaces (28.8±1.58 Bq.m^-3) at the 0.05 level. Moreover, our study found that the majority of the bedrooms in dwellings had a closed atmosphere, resulting in poorer ventilation than in most of the workplaces that had access to air flow through open doors and windows at daytime. We consider this to be the main reason for the higher geometric mean indoor radon concentration in dwellings compared to workplaces.

Keywords: CR-39 detector, indoor radon, radon in dwelling, radon in workplace

Procedia PDF Downloads 256

Authors: Abdullahi Jibrin, Aishetu Abdulkadir

Abstract:

The development of allometric models is crucial to accurate forest biomass/carbon stock assessment. The aim of this study was to develop a set of biomass prediction models that will enable the determination of total tree aboveground biomass for savannah woodland area in Niger State, Nigeria. Based on the data collected through biometric measurements of 1816 trees and destructive sampling of 36 trees, five species specific and one site specific models were developed. The sample size was distributed equally between the five most dominant species in the study site (Vitellaria paradoxa, Irvingia gabonensis, Parkia biglobosa, Anogeissus leiocarpus, Pterocarpus erinaceous). Firstly, the equations were developed for five individual species. Secondly these five species were mixed and were used to develop an allometric equation of mixed species. Overall, there was a strong positive relationship between total tree biomass and the stem diameter. The coefficient of determination (R2 values) ranging from 0.93 to 0.99 P < 0.001 were realised for the models; with considerable low standard error of the estimates (SEE) which confirms that the total tree above ground biomass has a significant relationship with the dbh. The F-test value for the biomass prediction models were also significant at p < 0.001 which indicates that the biomass prediction models are valid. This study recommends that for improved biomass estimates in the study site, the site specific biomass models should preferably be used instead of using generic models.

Keywords: allometriy, biomass, carbon stock , model, regression equation, woodland, inventory

Procedia PDF Downloads 419

Authors: Awol Seid Ebrie

Abstract:

HIV results as an incurable disease, AIDS. After a person is infected with virus, the virus gradually destroys all the infection fighting cells called CD4 cells and makes the individual susceptible to opportunistic infections which cause severe or fatal health problems. Several studies show that the CD4 cells count is the most determinant indicator of the effectiveness of the treatment or progression of the disease. The objective of this paper is to investigate the progression of the disease over time among patient under HAART treatment. Two main approaches of the generalized multilevel ordinal models; namely the proportional odds model and the nonproportional odds model have been applied to the HAART data. Also, the multilevel part of both models includes random intercepts and random coefficients. In general, four models are explored in the analysis and then the models are compared using the deviance information criteria. Of these models, the random coefficients nonproportional odds model is selected as the best model for the HAART data used as it has the smallest DIC value. The selected model shows that the progression of the disease increases as the time under the treatment increases. In addition, it reveals that gender, baseline clinical stage and functional status of the patient have a significant association with the progression of the disease.

Keywords: nonproportional odds model, proportional odds model, random coefficients model, random intercepts model

Procedia PDF Downloads 389

Authors: Dalin Si, Azizan Aziz, Bertrand Lasternas

Abstract:

To encourage building owners to purchase electricity at the wholesale market and reduce building peak demand, this study aims to develop models that predict day-ahead hourly electricity consumption and demand using artificial neural network (ANN) and support vector machine (SVM). All prediction models are built in Python, with tool Scikit-learn and Pybrain. The input data for both consumption and demand prediction are time stamp, outdoor dry bulb temperature, relative humidity, air handling unit (AHU), supply air temperature and solar radiation. Solar radiation, which is unavailable a day-ahead, is predicted at first, and then this estimation is used as an input to predict consumption and demand. Models to predict consumption and demand are trained in both SVM and ANN, and depend on cooling or heating, weekdays or weekends. The results show that ANN is the better option for both consumption and demand prediction. It can achieve 15.50% to 20.03% coefficient of variance of root mean square error (CVRMSE) for consumption prediction and 22.89% to 32.42% CVRMSE for demand prediction, respectively. To conclude, the presented models have potential to help building owners to purchase electricity at the wholesale market, but they are not robust when used in demand response control.

Keywords: building energy prediction, data mining, demand response, electricity market

Procedia PDF Downloads 289

Authors: Josip Visković, Josip Arnerić, Ante Rozga

Abstract:

Based on the fact that volatility is time varying in high frequency data and that periods of high volatility tend to cluster, the most successful and popular models in modelling time varying volatility are GARCH type models. When financial returns exhibit sudden jumps that are due to structural breaks, standard GARCH models show high volatility persistence, i.e. integrated behaviour of the conditional variance. In such situations models in which the parameters are allowed to change over time are more appropriate. This paper compares different GARCH models in terms of their ability to describe structural changes in returns caused by financial crisis at stock markets of six selected central and east European countries. The empirical analysis demonstrates that Markov regime switching GARCH model resolves the problem of excessive persistence and outperforms uni-regime GARCH models in forecasting volatility when sudden switching occurs in response to financial crisis.

Keywords: central and east European countries, financial crisis, Markov switching GARCH model, transition probabilities

Procedia PDF Downloads 200

Authors: Ryan A. Black, Stacey A. McCaffrey

Abstract:

Over the past few decades, great strides have been made towards improving the science in the measurement of psychological constructs. Item Response Theory (IRT) has been the foundation upon which statistical models have been derived to increase both precision and accuracy in psychological measurement. These models are now being used widely to develop and refine tests intended to measure an individual's level of academic achievement, aptitude, and intelligence. Recently, the field of clinical psychology has adopted IRT models to measure psychopathological phenomena such as depression, anxiety, and addiction. Because advances in IRT measurement models are being made so rapidly across various fields, it has become quite challenging for psychologists and other behavioral scientists to keep abreast of the most recent developments, much less learn how to employ and decide which models are the most appropriate to use in their line of work. In the same vein, IRT measurement models vary greatly in complexity in several interrelated ways including but not limited to the number of item-specific parameters estimated in a given model, the function which links the expected response and the predictor, response option formats, as well as dimensionality. As a result, inferior methods (a.k.a. Classical Test Theory methods) continue to be employed in efforts to measure psychological constructs, despite evidence showing that IRT methods yield more precise and accurate measurement. To increase the use of IRT methods, this study endeavors to provide a comprehensive overview of binary IRT models; that is, measurement models employed on test data consisting of binary response options (e.g., correct/incorrect, true/false, agree/disagree). Specifically, this study will cover the most basic binary IRT model, known as the 1-parameter logistic (1-PL) model dating back to over 50 years ago, up until the most recent complex, 4-parameter logistic (4-PL) model. Binary IRT models will be defined mathematically and the interpretation of each parameter will be provided. Next, all four binary IRT models will be employed on two sets of data: 1. Simulated data of N=500,000 subjects who responded to four dichotomous items and 2. A pilot analysis of real-world data collected from a sample of approximately 770 subjects who responded to four self-report dichotomous items pertaining to emotional consequences to alcohol use. Real-world data were based on responses collected on items administered to subjects as part of a scale-development study (NIDA Grant No. R44 DA023322). IRT analyses conducted on both the simulated data and analyses of real-world pilot will provide a clear demonstration of how to construct, evaluate, and compare binary IRT measurement models. All analyses will be performed using the new IRT procedure in SAS 9.4. SAS code to generate simulated data and analyses will be available upon request to allow for replication of results.

Keywords: instrument development, item response theory, latent trait theory, psychometrics

Procedia PDF Downloads 327

Authors: Verónica Diaz Quezada

Abstract:

This research examines the teaching models used by secondary math teachers when teaching logarithmic, quadratic and exponential functions. For this, descriptive case studies have been carried out on 5 secondary teachers. These teachers have been chosen from 3 scientific-humanistic and technical schools, in Chile. Data have been obtained through non-participant class observation and the application of a questionnaire and a rubric to teachers. According to the results, the didactic model that prevails is the one that starts with an interactive strategy, moves to a more content-based structure, and ends with a reinforcement stage. Nonetheless, there is always influence from teachers, their methods, and the group of students.

Keywords: teaching models, math teachers, functions, secondary education

Procedia PDF Downloads 166

Authors: Yu Zhang, Pedro Desouza

Abstract:

Since big data has become substantially more accessible and manageable due to the development of powerful tools for dealing with unstructured data, people are eager to mine information from social media resources that could not be handled in the past. Sentiment analysis, as a novel branch of text mining, has in the last decade become increasingly important in marketing analysis, customer risk prediction and other fields. Scientists and researchers have undertaken significant work in creating and improving their sentiment models. In this paper, we present a concept of selecting appropriate classifiers based on the features and qualities of data sources by comparing the performances of five classifiers with three popular social media data sources: Twitter, Amazon Customer Reviews, and Movie Reviews. We introduced a couple of innovative models that outperform traditional sentiment classifiers for these data sources, and provide insights on how to further improve the predictive power of sentiment analysis. The modelling and testing work was done in R and Greenplum in-database analytic tools.

Keywords: sentiment analysis, social media, Twitter, Amazon, data mining, machine learning, text mining

Procedia PDF Downloads 325

Authors: M. O. Oke, T. S. Workneh

Abstract:

Drying behaviour of blanched sweet potato in a cabinet dryer using different five air temperatures (40-80oC) and ten sweet potato varieties sliced to 5 mm thickness were investigated. The drying data were fitted to eight models. The Modified Henderson and Pabis model gave the best fit to the experimental moisture ratio data obtained during the drying of all the varieties while Newton (Lewis) and Wang and Singh models gave the least fit. The values of Deff obtained for Bophelo variety (1.27 x 10-9 to 1.77 x 10-9 m2/s) was the least while that of S191 (1.93 x 10-9 to 2.47 x 10-9 m2/s) was the highest which indicates that moisture diffusivity in sweet potato is affected by the genetic factor. Activation energy values ranged from 0.27-6.54 kJ/mol. The lower activation energy indicates that drying of sweet potato slices requires less energy and is hence a cost and energy saving method. The drying behavior of blanched sweet potato was investigated in a cabinet dryer. Drying time decreased considerably with increase in hot air temperature. Out of the eight models fitted, the Modified Henderson and Pabis model gave the best fit to the experimental moisture ratio data on all the varieties while Newton, Wang and Singh models gave the least. The lower activation energy (0.27-6.54 kJ/mol) obtained indicates that drying of sweet potato slices requires less energy and is hence a cost and energy saving method.

Keywords: sweet potato slice, drying models, moisture ratio, moisture diffusivity, activation energy

Procedia PDF Downloads 484

Authors: Akinbo Razak Yinka, Adesanya Kehinde Kazeem, Oladokun Oluwagbenga Peter

Abstract:

Time series data are sequences of observations collected over a period of time. Such data can be used to predict health outcomes, such as disease progression, mortality, hospitalization, etc. The Statistical approach is based on mathematical models that capture the patterns and trends of the data, such as autocorrelation, seasonality, and noise, while Neural methods are based on artificial neural networks, which are computational models that mimic the structure and function of biological neurons. This paper compared both parametric and non-parametric time series models of patients treated for malaria in Maternal and Child Health Centres in Lagos State, Nigeria. The forecast methods considered linear regression, Integrated Moving Average, ARIMA and SARIMA Modeling for the parametric approach, while Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) Network were used for the non-parametric model. The performance of each method is evaluated using the Mean Absolute Error (MAE), R-squared (R2) and Root Mean Square Error (RMSE) as criteria to determine the accuracy of each model. The study revealed that the best performance in terms of error was found in MLP, followed by the LSTM and ARIMA models. In addition, the Bootstrap Aggregating technique was used to make robust forecasts when there are uncertainties in the data.

Keywords: ARIMA, bootstrap aggregation, MLP, LSTM, SARIMA, time-series analysis

Procedia PDF Downloads 34

Authors: Xiaogang Li, Jieqiong Miao

Abstract:

As for the problem of the grey forecasting model prediction accuracy is low, an improved grey prediction model is put forward. Firstly, use trigonometric function transform the original data sequence in order to improve the smoothness of data , this model called SGM( smoothness of grey prediction model), then combine the improved grey model with support vector machine , and put forward the grey support vector machine model (SGM - SVM).Before the establishment of the model, we use trigonometric functions and accumulation generation operation preprocessing data in order to enhance the smoothness of the data and weaken the randomness of the data, then use support vector machine (SVM) to establish a prediction model for pre-processed data and select model parameters using genetic algorithms to obtain the optimum value of the global search. Finally, restore data through the "regressive generate" operation to get forecasting data. In order to prove that the SGM-SVM model is superior to other models, we select the battery life data from calce. The presented model is used to predict life of battery and the predicted result was compared with that of grey model and support vector machines．For a more intuitive comparison of the three models, this paper presents root mean square error of this three different models .The results show that the effect of grey support vector machine (SGM-SVM) to predict life is optimal, and the root mean square error is only 3.18%. Keywords: grey forecasting model, trigonometric function, support vector machine, genetic algorithms, root mean square error

Keywords: Grey prediction model, trigonometric functions, support vector machines, genetic algorithms, root mean square error

Procedia PDF Downloads 428

Authors: Zainab Mutlaq Ibrahim, Mohamed Bader-El-Den, Mihaela Cocea

Abstract:

Students' textual feedback can hold unique patterns and useful information about learning process, it can hold information about advantages and disadvantages of teaching methods, assessment components, facilities, and other aspects of teaching. The results of analysing such a feedback can form a key point for institutions’ decision makers to advance and update their systems accordingly. This paper proposes a data mining framework for analysing end of unit general textual feedback using part of speech feature (PoS) with four machine learning algorithms: support vector machines, decision tree, random forest, and naive bays. The proposed framework has two tasks: first, to use the above algorithms to build an optimal model that automatically classifies the whole data set into two subsets, one subset is tailored to assessment practices (assessment related), and the other one is the non-assessment related data. Second task to use the same algorithms to build an optimal model for whole data set, and the new data subsets to automatically detect their sentiment. The significance of this paper is to compare the performance of the above four algorithms using part of speech feature to the performance of the same algorithms using n-grams feature. The paper follows Knowledge Discovery and Data Mining (KDDM) framework to construct the classification and sentiment analysis models, which is understanding the assessment domain, cleaning and pre-processing the data set, selecting and running the data mining algorithm, interpreting mined patterns, and consolidating the discovered knowledge. The results of this paper experiments show that both models which used both features performed very well regarding first task. But regarding the second task, models that used part of speech feature has underperformed in comparison with models that used unigrams and bigrams.

Keywords: assessment, part of speech, sentiment analysis, student feedback

Procedia PDF Downloads 107

Authors: Miroslav H. Hristov, Velizar A. Vassilev, Georgi K. Dukendjiev

Abstract:

Due to the constant development of measurement systems and the aim for computerization, unavoidable improvements are made for the main disadvantages of air gauges. With the appearance of the air-electronic measuring devices, some of their disadvantages are solved. The output electrical signal allows them to be included in the modern systems for measuring information processing and process management. Producer efforts are aimed at reducing the influence of supply pressure and measurement system setup errors. Increased accuracy requirements and preventive error measures are due to the main uses of air electronic systems - measurement of geometric dimensions in the automotive industry where they are applied as modules in measuring systems to measure geometric parameters, form, orientation and location of the elements.

Keywords: air-electronic, geometrical parameters, improvement, measurement systems

Procedia PDF Downloads 202

Authors: A. A. A. Aboalnour, Ahmed M. Amasaib, Mohammed-Almujtaba A. Mohammed-Farah, Abdelhakam, A. Noreldien

Abstract:

This paper presents a design and study of Parabolic Trough Solar Collector (PTC). Mathematical models were used in this work to find the direct and reflected solar radiation from the air layer on the surface of the earth per hour based on the total daily solar radiation on a horizontal surface. Also mathematical models had been used to calculate the radiation of the tilted surfaces. Most of the ingredients used in this project as previews data required on several solar energy applications, thermal simulation, and solar power systems. In addition, mathematical models had been used to study the flow of the fluid inside the tube (receiver), and study the effect of direct and reflected solar radiation on the pressure, temperature, speed, kinetic energy and forces of fluid inside the tube. Finally, the mathematical models had been used to study the (PTC) performances and estimate its thermal efficiency.

Keywords: CFD, experimental, mathematical models, parabolic trough, radiation

Procedia PDF Downloads 382

Authors: Elif Aykin Dincer, Mustafa Erbas

Abstract:

The vacuum drying behavior of beef slices (10 x 4 x 0.2 cm3) was experimentally investigated at the temperature of 60, 70, and 80°C under 25 mbar ultimate vacuum pressure and the mathematical models (Lewis, Page, Midilli, Two-term, Wangh and Singh and Modified Henderson and Pabis) were used to fit the vacuum drying of beef slices. The increase in drying air temperature resulted in a decrease in drying time. It took approximately 206, 180 and 157 min to dry beef slices from an initial moisture content to a final moisture content of 0.05 kg water/kg dry matter at 60, 70 and 80 °C of vacuum drying, respectively. It is also observed that the drying rate increased with increasing drying temperature. The coefficients (R2), the reduced chi-square (x²) and root mean square error (RMSE) values were obtained by application of six models to the experimental drying data. The best model with the highest R2 and, the lowest x² and RMSE values was selected to describe the drying characteristics of beef slices. The Page model has shown a better fit to the experimental drying data as compared to other models. In addition, the effective moisture diffusivities of beef slices in the vacuum drying at 60 - 80 °C varied in the range of 1.05 – 1.09 x 10-10 m2/s. Consequently, this results can be used to simulate vacuum drying process of beef slices and improve efficiency of the drying process.

Keywords: beef slice, drying models, effective diffusivity, vacuum

Procedia PDF Downloads 262

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 232

Authors: A.D. Susanti, W. B. Sediawan, S.K. Wirawan, Budhijanto, Ritmaleni

Abstract:

Oryzanol content in rice bran oil (RBO) naturally has high antioxidant activity. Its reviewed has several health properties and high interested in pharmacy, cosmetics, and nutrition’s. Because of the low concentration of oryzanol in crude RBO (0.9-2.9%) then its need to be further processed for practical usage, such as via adsorption process. In this study, investigation and adjustment of adsorption equilibrium models were conducted through the kinetic data approachments. Mathematical modeling on kinetics of batch adsorption of oryzanol separation from RBO has been set-up and then applied for equilibrium results. The size of adsorbent particles used in this case are usually relatively small then the concentration in the adsorbent is assumed to be not different. Hence, the adsorption rate is controlled by the rate of oryzanol mass transfer from the bulk fluid of RBO to the surface of silica gel. In this approachments, the rate of mass transfer is assumed to be proportional to the concentration deviation from the equilibrium state. The equilibrium models applied were Langmuir, coefficient distribution, and Freundlich with the values of the parameters obtained from equilibrium results. It turned out that the models set-up can quantitatively describe the experimental kinetics data and the adjustment of the values of equilibrium isotherm parameters significantly improves the accuracy of the model. And then the value of mass transfer coefficient per unit adsorbent mass (kca) is obtained by curve fitting.

Keywords: adsorption equilibrium, adsorption kinetics, oryzanol, rice bran oil

Procedia PDF Downloads 295

Authors: Mohkammad Nur Cahyadi, Imam Wahyu Farid, Ronny Mardianto, Agung Budi Cahyono, Eko Yuli Handoko, Daud Wahyu Imani, Arizal Bawazir, Luki Adi Triawan

Abstract:

Unmanned aerial vehicle (UAV) technology has cost efficiency and data retrieval time advantages. Using technologies such as UAV, GNSS, and LiDAR will later be combined into one of the newest technologies to cover each other's deficiencies. This integration system aims to increase the accuracy of calculating the volume of the land stockpile of PT. Garam (Salt Company). The use of UAV applications to obtain geometric data and capture textures that characterize the structure of objects. This study uses the Taror 650 Iron Man drone with four propellers, which can fly for 15 minutes. LiDAR can classify based on the number of image acquisitions processed in the software, utilizing photogrammetry and structural science principles from Motion point cloud technology. LiDAR can perform data acquisition that enables the creation of point clouds, three-dimensional models, Digital Surface Models, Contours, and orthomosaics with high accuracy. LiDAR has a drawback in the form of coordinate data positions that have local references. Therefore, researchers use GNSS, LiDAR, and drone multi-sensor technology to map the stockpile of salt on open land and warehouses every year, carried out by PT. Garam twice, where the previous process used terrestrial methods and manual calculations with sacks. Research with LiDAR needs to be combined with UAV to overcome data acquisition limitations because it only passes through the right and left sides of the object, mainly when applied to a salt stockpile. The UAV is flown to assist data acquisition with a wide coverage with the help of integration of the 200-gram LiDAR system so that the flying angle taken can be optimal during the flight process. Using LiDAR for low-cost mapping surveys will make it easier for surveyors and academics to obtain pretty accurate data at a more economical price. As a survey tool, LiDAR is included in a tool with a low price, around 999 USD; this device can produce detailed data. Therefore, to minimize the operational costs of using LiDAR, surveyors can use Low-Cost LiDAR, GNSS, and UAV at a price of around 638 USD. The data generated by this sensor is in the form of a visualization of an object shape made in three dimensions. This study aims to combine Low-Cost GPS measurements with Low-Cost LiDAR, which are processed using free user software. GPS Low Cost generates data in the form of position-determining latitude and longitude coordinates. The data generates X, Y, and Z values to help georeferencing process the detected object. This research will also produce LiDAR, which can detect objects, including the height of the entire environment in that location. The results of the data obtained are calibrated with pitch, roll, and yaw to get the vertical height of the existing contours. This study conducted an experimental process on the roof of a building with a radius of approximately 30 meters.

Keywords: LiDAR, unmanned aerial vehicle, low-cost GNSS, contour

Procedia PDF Downloads 52

Authors: Yuhanis Yusof, Zuriani Mustaffa, Siti Sakira Kamaruddin

Abstract:

Data mining is a fundamental technique in identifying patterns from large data sets. The extracted facts and patterns contribute in various domains such as marketing, forecasting, and medical. Prior to that, data are consolidated so that the resulting mining process may be more efficient. This study investigates the effect of different data normalization techniques, which are Min-max, Z-score, and decimal scaling, on Swarm-based forecasting models. Recent swarm intelligence algorithms employed includes the Grey Wolf Optimizer (GWO) and Artificial Bee Colony (ABC). Forecasting models are later developed to predict the daily spot price of crude oil and gasoline. Results showed that GWO works better with Z-score normalization technique while ABC produces better accuracy with the Min-Max. Nevertheless, the GWO is more superior that ABC as its model generates the highest accuracy for both crude oil and gasoline price. Such a result indicates that GWO is a promising competitor in the family of swarm intelligence algorithms.

Keywords: artificial bee colony, data normalization, forecasting, Grey Wolf optimizer

Procedia PDF Downloads 447

Authors: Shahroz Khan, Erkan Gunpinar, Kemal Mart

Abstract:

Recently parametric design techniques became a vital concept in the field of Computer Aided Design (CAD), which helps to provide sophisticated platform to the designer in order to automate the design process in efficient time. In these techniques, design process starts by parameterizing the important features of design models (typically the key dimensions), with the implementation of design constraints. The design constraints help to retain the overall shape of the model while modifying its parameters. However, the process of initializing an appropriate number of design parameters and constraints is the crucial part of parametric design techniques, especially for complex surface models such as yacht hull. This paper introduces a method to create complex surface models in favor of parametric design techniques, a method to define the right number of parameters and respective design constraints, and a system to implement design parameters in contract to design constraints schema. For this, in our proposed approach the design process starts by dividing the yacht hull into three sections. Each section consists of different shape lines, which form the overall shape of yacht hull. The shape lines are created using Cubic Bezier Curves, which allow larger design flexibility. Design parameters and constraints are defined on the shape lines in 3D design space to facilitate the designers for better and individual handling of parameters. Afterwards, shape modifiers are developed, which allow the modification of each parameter while satisfying the respective set of criteria and design constraints. Such as, geometric continuities should be maintained between the shape lines of the three sections, fairness of the hull surfaces should be preserved after modification and while design modification, effect of a single parameter should be negligible on other parameters. The constraints are defined individually on shape lines of each section and mutually between the shape lines of two connecting sections. In order to validate and visualize design results of our shape modifiers, a real time graphic interface is created.

Keywords: design parameter, design constraints, shape modifies, yacht hull

Procedia PDF Downloads 277