Search results for: model testing

Authors: Kirti Gosavi, Anita Bhole

Abstract:

The paper demonstrates simulation and steady-state performance of three phase squirrel cage induction motor and detection of rotor broken bar fault using MATLAB. This simulation model is successfully used in the fault detection of rotor broken bar for the induction machines. A dynamic model using PWM inverter and mathematical modelling of the motor is developed. The dynamic simulation of the small power induction motor is one of the key steps in the validation of the design process of the motor drive system and it is needed for eliminating advertent design errors and the resulting error in the prototype construction and testing. The simulation model will be helpful in detecting the faults in three phase induction motor using Motor current signature analysis.

Keywords: squirrel cage induction motor, pulse width modulation (PWM), fault diagnosis, induction motor

Procedia PDF Downloads 599

Authors: Nicolas Plamondon, Stuart Atkinson, Shuzi Zhou

Abstract:

The insurance industry is usually not the first topic one has in mind when thinking about applications of data science. However, the use of data science in the finance and insurance industry is growing quickly for several reasons, including an abundance of reliable customer data, ferocious competition requiring more accurate pricing, etc. Among the top use cases of data science, we find pricing optimization, customer segmentation, customer risk assessment, fraud detection, marketing, and triage analytics. The objective of this paper is to present an application of the generalized additive model (GAM) on a commercial automobile insurance product: an individually rated commercial automobile. These are vehicles used for commercial purposes, but for which there is not enough volume to apply pricing to several vehicles at the same time. The GAM model was selected as an improvement over GLM for its ease of use and its wide range of applications. The model was trained using the largest split of the data to determine model parameters. The remaining part of the data was used as testing data to verify the quality of the modeling activity. We used the Gini coefficient to evaluate the performance of the model. For long-term monitoring, commonly used metrics such as RMSE and MAE will be used. Another topic of interest in the insurance industry is to process of producing the model. We will discuss at a high level the interactions between the different teams with an insurance company that needs to work together to produce a model and then monitor the performance of the model over time. Moreover, we will discuss the regulations in place in the insurance industry. Finally, we will discuss the maintenance of the model and the fact that new data does not come constantly and that some metrics can take a long time to become meaningful.

Keywords: insurance, data science, modeling, monitoring, regulation, processes

Procedia PDF Downloads 52

Authors: Agustinus Rudatyo Himamunanto, Anastasia Rita Widiarti

Abstract:

Transliteration using Javanese manuscripts is one of methods to preserve and legate the wealth of literature in the past for the present generation in Indonesia. The transliteration manual process commonly requires philologists and takes a relatively long time. The automatic transliteration process is expected to shorten the time so as to help the works of philologists. The preprocessing and segmentation stage firstly done is used to manage the document images, thus obtaining image script units that will compile input document images free from noise and have the similarity in properties in the thickness, size, and slope. The next stage of characteristic extraction is used to find unique characteristics that will distinguish each Javanese script image. One of characteristics that is used in this research is the number of black pixels in each image units. Each image of Java scripts contained in the data training will undergo the same process similar to the input characters. The system testing was performed with the data of the book Hamong Tani. The book Hamong Tani was selected due to its content, age and number of pages. Those were considered sufficient as a model experimental input. Based on the results of random page automatic transliteration process testing, it was determined that the maximum percentage correctness obtained was 81.53%. The percentage of success was obtained in 32x32 pixel input image size with the 5x5 image window. With regard to the results, it can be concluded that the automatic transliteration model offered is relatively good.

Keywords: Javanese script, character recognition, statistical, automatic transliteration

Procedia PDF Downloads 316

Authors: A. S. Haruna, M. U. Tambawal, A. A. Salawu

Abstract:

The psychological impact of peer influence on its individual group members, can make them resist HIV/AIDS counselling and testing. This study investigated the correlate of peer influence and resistance to HIV/AIDS counselling and testing among students in tertiary institutions in Kano state, Nigeria. To achieve this, three null hypotheses were postulated and tested. Cross-Sectional Survey Design was employed in which 1512 sample was selected from a student population of 104,841.Simple Random Sampling was used in the selection. A self-developed 20-item scale called Peer Influence and Psychological Resistance Inventory (PIPRI) was used for data collection. Pearson Product Moment Correlation (PPMCC) via test-retest method was applied to estimate a reliability coefficient of 0.86 for the scale. Data obtained was analyzed using t-test and PPMCC at 0.05 level of confidence. Results reveal 26.3% (397) of the respondents being influenced by their peer group, while 39.8% showed resistance. Also, the t-tests and PPMCC statistics were greater than their respective critical values. This shows that there was a significant gender difference in peer influence and a difference between peer influence and resistance to HIV/AIDS counselling and testing. However, a positive relationship between peer influence and resistance to HIV/AIDS counselling and testing was shown. A major recommendation offered suggests the use of reinforcement and social support for positive attitudes and maintenance of safe behaviour among students who patronize HIV/AIDS counselling.

Keywords: peer group influence, HIV/AIDS counselling and testing, psychological resistance, students

Procedia PDF Downloads 365

Authors: Khalid Hassan Abdesamed, Kalsom Abd Wahab

Abstract:

Economic development and growth are significantly linked to the consistent and sustainable sector of small and medium enterprises (SMEs). Banks are the frontrunners in financing and advising SMEs. The main objective of the study is to assess the tendency of SMEs to use the Islamic bank. Model was developed using quantitative method with a hypothetical-deductive testing approach. Model (N = 364) used primary data on the tendency of SMEs to use Islamic banks gathered from questionnaire. It is found by Mann-Whitney test that the tendency to use Islamic bank varies between those firms which consider formal financing with the ones relying on informal financing with the latter tends more to use Islamic bank. This study can serve academic researchers, policy makers, and developing countries as a model of SMEs’ desirability to Islamic banking.

Keywords: formal financing, informal financing, Islamic bank, SMEs

Procedia PDF Downloads 329

Authors: H. Bentarzi, A. Zitouni

Abstract:

The reliability of the power grid depends on the successful operation of thousands of protective relays. The failure of one relay to operate as intended may lead the entire power grid to blackout. In fact, major power system failures during transient disturbances may be caused by unnecessary protective relay tripping rather than by the failure of a relay to operate. Adequate relay testing provides a first defense against false trips of the relay and hence improves power grid stability and prevents catastrophic bulk power system failures. The goal of this research project is to design and enhance the relay tester using a technology such as Field Programmable Gate Array (FPGA) card NI 7851. A PC based tester framework has been developed using Simulink power system model for generating signals under different conditions (faults or transient disturbances) and LabVIEW for developing the graphical user interface and configuring the FPGA. Besides, the interface system has been developed for outputting and amplifying the signals without distortion. These signals should be like the generated ones by the real power system and large enough for testing the relay’s functionality. The signals generated that have been displayed on the scope are satisfactory. Furthermore, the proposed testing system can be used for improving the performance of protective relay.

Keywords: amplifier class D, field-programmable gate array (FPGA), protective relay, tester

Procedia PDF Downloads 184

Authors: A. Shebani, C. Pislaru

Abstract:

Wear of materials is an everyday experience and has been observed and studied for long time. The prediction of wear is a fundamental problem in the industrial field, mainly correlated to the planning of maintenance interventions and economy. Pin-on-disc test is the most common test which is used to study the wear behaviour. In this paper, the pin-on-disc (AEROTECH UNIDEX 11) is used for the investigation of the effects of normal load and hardness of material on the wear under dry and sliding conditions. In the pin-on-disc rig, two specimens were used; one, a pin which is made of steel with a tip, is positioned perpendicular to the disc, where the disc is made of aluminium. The pin wear and disc wear were measured by using the following instruments: The Talysurf instrument, a digital microscope, and the alicona instrument; where the Talysurf profilometer was used to measure the pin/disc wear scar depth, and the alicona was used to measure the volume loss for pin and disc. After that, the Archard model, American Society for Testing and Materials model (ASTM), and neural network model were used for pin/disc wear modelling and the simulation results are implemented by using the Matlab program. This paper focuses on how the alicona can be considered as a powerful tool for wear measurements and how the neural network is an effective algorithm for wear estimation.

Keywords: wear modelling, Archard Model, ASTM Model, Neural Networks Model, Pin-on-disc Test, Talysurf, digital microscope, Alicona

Procedia PDF Downloads 424

Authors: Mohammed Alrefaie, Yaser Miaji

Abstract:

Greenhouses provide a convenient means to grow plants in the best environment. They achieve this by trapping heat from the sunlight and using artificial means to enhance the environment of the greenhouse. This includes controlling factors such as air flow, light intensity and amount of water among others that can have a big impact on plant growth. The aim of the greenhouse is to give maximum yield from plants possible. This report details the development and testing of greenhouse environment control system that can regulate light intensity, airflow and power supply inside the greenhouse. The details of the module development to control these three factors along with results of testing are presented.

Keywords: greenhouse, control system, light intensity, comprehensive environment

Procedia PDF Downloads 455

Authors: Yehjune Heo

Abstract:

As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.

Keywords: anti-spoofing, CNN, fingerprint recognition, loss function, optimizer

Procedia PDF Downloads 105

Authors: Afsaneh Jasmine Majidi

Abstract:

Language testing is an important part of language teaching experience and language learning process as it presents assessment strategies for teachers to evaluate the efficiency of teaching and for learners to examine their outcomes. However, language testing is demanding and challenging because it should provide the opportunity for proper and objective decision. In addition to all the efforts test designers put to design valid and reliable tests, there are some other determining factors which are even more complex and complicated. These factors affect the educational system, individuals, and society, and the impact of the tests vary according to the scope of the test. Seemingly, the impact of a simple classroom assessment is not the same as that of high stake tests such as International English Language Testing System (IELTS). As the importance of the test increases, it affects wider domain. Accordingly, the impacts of high stake tests are reflected not only in teaching, learning strategies but also in society. Testing experts use the term ‘washback’ or ‘impact’ to define the different effects of a test on teaching, learning, and community. This paper first looks at the theoretical background of ‘washback’ and ‘impact’ in language testing by reviewing of relevant literature in the field and then investigates washback effects of IELTS test of on Iranian IELTS teachers and students. The study found significant relationship between the washback effect of IELTS test and teaching strategies of Iranian IELTS teachers as well as performance of Iranian IELTS candidates and their community.

Keywords: high stake tests, IELTS, Iranian Candidates, language testing, test impact, washback

Procedia PDF Downloads 295

Authors: Rebeca Ramirez Acosta, Sebastian Lenhoff

Abstract:

Decision makers worldwide need to determine if the implementation of a new market mechanism will contribute to the sustainability and resilience of the power system. Due to smart grid technologies, new products in the distribution and transmission system can be traded; however, the impact of changing a market rule will differ between several regions. To test systematically those impacts, a market categorization has been compiled and organized in a smart grid market testing toolbox. This toolbox maps all actual energy products and sets the basis for running a co-simulation test with the new rule to be implemented. It will help to measure the impact of the new rule, based on the sustainable and resilience indicators.

Keywords: co-simulation, electricity market, smart grid market, market testing

Procedia PDF Downloads 154

Authors: M.Rüştü Karaman, İsmail İşeri, Kadir Saltalı, A.Reşit Brohi, Ayhan Horuz, Mümin Dizman

Abstract:

Considerable relations has recently been given to the environmental hazardous caused by agricultural chemicals such as excess fertilizers. In this study, a neural network approach was investigated in the prediction of potential nitrate pollution across different land-use patterns by using a feedforward multilayered computer model of artificial neural network (ANN) with proper training. Periodical concentrations of some anions, especially nitrate (NO3-), and cations were also detected in drainage waters collected from the drain pipes placed in irrigated tomato field, unirrigated wheat field, fallow and pasture lands. The soil samples were collected from the irrigated tomato field and unirrigated wheat field on a grid system with 20 m x 20 m intervals. Site specific nitrate concentrations in the soil samples were measured for ANN based simulation of nitrate leaching potential from the land profiles. In the application of ANN model, a multi layered feedforward was evaluated, and data sets regarding with training, validation and testing containing the measured soil nitrate values were estimated based on spatial variability. As a result of the testing values, while the optimal structures of 2-15-1 was obtained (R2= 0.96, P < 0.01) for unirrigated field, the optimal structures of 2-10-1 was obtained (R2= 0.96, P < 0.01) for irrigated field. The results showed that the ANN model could be successfully used in prediction of the potential leaching levels of nitrate, based on different land use patterns. However, for the most suitable results, the model should be calibrated by training according to different NN structures depending on site specific soil parameters and varied agricultural managements.

Keywords: artificial intelligence, ANN, drainage water, nitrate pollution

Procedia PDF Downloads 279

Authors: Ilker Ali Ozkan

Abstract:

In this study, an artificial neural network model has been developed to estimate chronic kidney failure which is a common disease. The patients’ age, their blood and biochemical values, and 24 input data which consists of various chronic diseases are used for the estimation process. The input data have been subjected to preprocessing because they contain both missing values and nominal values. 147 patient data which was obtained from the preprocessing have been divided into as 70% training and 30% testing data. As a result of the study, artificial neural network model with 25 neurons in the hidden layer has been found as the model with the lowest error value. Chronic kidney failure disease has been able to be estimated accurately at the rate of 99.3% using this artificial neural network model. The developed artificial neural network has been found successful for the estimation of chronic kidney failure disease using clinical data.

Keywords: estimation, artificial neural network, chronic kidney failure disease, disease diagnosis

Procedia PDF Downloads 413

Authors: Jay Ananth

Abstract:

The drug discovery process currently requires numerous years of clinical testing as well as money just for a single drug to earn FDA approval. For drugs that even make it this far in the process, there is a very slim chance of receiving FDA approval, resulting in detrimental hurdles to drug accessibility. To minimize these inefficiencies, numerous studies have implemented computational methods, although few computational investigations have focused on a crucial feature of drugs: lipophilicity. Lipophilicity is a physical attribute of a compound that measures its solubility in lipids and is a determinant of drug efficacy. This project leverages Artificial Intelligence to predict the impact of a drug’s lipophilicity on its performance by accounting for factors such as binding affinity and toxicity. The model predicted lipophilicity and binding affinity in the validation set with very high R² scores of 0.921 and 0.788, respectively, while also being applicable to a variety of target receptors. The results expressed a strong positive correlation between lipophilicity and both binding affinity and toxicity. The model helps in both drug development and discovery, providing every pharmaceutical company with recommended lipophilicity levels for drug candidates as well as a rapid assessment of early-stage drugs prior to any testing, eliminating significant amounts of time and resources currently restricting drug accessibility.

Keywords: drug discovery, lipophilicity, ligand-receptor interactions, machine learning, drug development

Procedia PDF Downloads 74

Authors: Richard Ji

Abstract:

Nondestructive deflection testing has been accepted widely as a cost-effective tool for evaluating the structural condition of airfield pavements. Backcalculation of pavement layer moduli can be used to characterize the pavement existing condition in order to compute the load bearing capacity of pavement. This paper presents an improved best-fit backcalculation methodology based on deflection predictions obtained using finite element method (FEM). The best-fit approach is based on minimizing the squared error between falling weight deflectometer (FWD) measured deflections and FEM predicted deflections. Then, concrete elastic modulus and modulus of subgrade reaction were back-calculated using Heavy Weight Deflectometer (HWD) deflections collected at the National Airport Pavement Testing Facility (NAPTF) test site. It is an alternative and more versatile method in considering concrete slab geometry and HWD testing locations compared to methods currently available.

Keywords: nondestructive testing, pavement moduli backcalculation, finite element method, concrete pavements

Procedia PDF Downloads 137

Authors: R. Boudjelthia

Abstract:

The aim of this study is to determine the influence of mix composition of concrete as the content of water and cement, water–binder ratio, and the replacement of fly ash on the durability of self compacting concrete (SCC) by using artificial neural networks (ANNs). To achieve this, an ANNs model is developed to predict the durability of self compacting concrete which is expressed in terms of chloride ions permeability in accordance with ASTM C1202-97 or AASHTO T277. Database gathered from the literature for the training and testing the model. A sensitivity analysis was also conducted using the trained and tested ANN model to investigate the effect of fly ash on the durability of SCC. The results indicate that the developed model is reliable and accurate. the durability of SCC expressed in terms of total charge passed over a 6-h period can be significantly improved by using at least 25% fly ash as replacement of cement. This study show that artificial neural network have strong potentialas a feasible tool for predicting accurately the durability of SCC containing fly ash.

Keywords: artificial neural networks, durability, chloride ions permeability, self compacting concrete

Procedia PDF Downloads 342

Authors: Teh Raihana Nazirah Roslan, Siti Zulaiha Ibrahim, Sharmila Karim

Abstract:

A warrant is a financial contract that confers the right but not the obligation, to buy or sell a security at a certain price before expiration. The standard procedure to value equity warrants using call option pricing models such as the Black–Scholes model had been proven to contain many flaws, such as the assumption of constant interest rate and constant volatility. In fact, existing alternative models were found focusing more on demonstrating techniques for pricing, rather than empirical testing. Therefore, a mathematical model for pricing and analyzing equity warrants which comprises stochastic interest rate and stochastic volatility is essential to incorporate the dynamic relationships between the identified variables and illustrate the real market. Here, the aim is to develop dynamic pricing formulations for hybrid equity warrants by incorporating stochastic interest rates from the Cox-Ingersoll-Ross (CIR) model, along with stochastic volatility from the Heston model. The development of the model involves the derivations of stochastic differential equations that govern the model dynamics. The resulting equations which involve Cauchy problem and heat equations are then solved using partial differential equation approaches. The analytical pricing formulas obtained in this study comply with the form of analytical expressions embedded in the Black-Scholes model and other existing pricing models for equity warrants. This facilitates the practicality of this proposed formula for comparison purposes and further empirical study.

Keywords: Cox-Ingersoll-Ross model, equity warrants, Heston model, hybrid models, stochastic

Procedia PDF Downloads 87

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: Meng-Fei Cheng, Wei Fneg

Abstract:

New Taiwan high school standards emphasize employing scientific models and modeling practices in physics learning. However, to our knowledge. Few studies address how scientific models and modeling are approached in current science teaching, and they do not examine the views of scientific models portrayed in the textbooks. To explore the views of scientific models and modeling in textbooks, this study investigated the atomic unit in different textbook versions as an example and provided suggestions for modeling curriculum. This study adopted a quantitative analysis of qualitative data in the atomic units of four mainstream version of Taiwan high school physics textbooks. The models were further analyzed using five dimensions of the views of scientific models (nature of models, multiple models, purpose of the models, testing models, and changing models); each dimension had three levels (low, medium, high). Descriptive statistics were employed to compare the frequency of describing the five dimensions of the views of scientific models in the atomic unit to understand the emphasis of the views and to compare the frequency of the eight scientific models’ use to investigate the atomic model that was used most often in the textbooks. Descriptive statistics were further utilized to investigate the average levels of the five dimensions of the views of scientific models to examine whether the textbooks views were close to the scientific view. The average level of the five dimensions of the eight atomic models were also compared to examine whether the views of the eight atomic models were close to the scientific views. The results revealed the following three major findings from the atomic unit. (1) Among the five dimensions of the views of scientific models, the most portrayed dimension was the 'purpose of models,' and the least portrayed dimension was 'multiple models.' The most diverse view was the 'purpose of models,' and the most sophisticated scientific view was the 'nature of models.' The least sophisticated scientific view was 'multiple models.' (2) Among the eight atomic models, the most mentioned model was the atomic nucleus model, and the least mentioned model was the three states of matter. (3) Among the correlations between the five dimensions, the dimension of 'testing models' was highly related to the dimension of 'changing models.' In short, this study examined the views of scientific models based on the atomic units of physics textbooks to identify the emphasized and disregarded views in the textbooks. The findings suggest how future textbooks and curriculum can provide a thorough view of scientific models to enhance students' model-based learning.

Keywords: atomic models, textbooks, science education, scientific model

Procedia PDF Downloads 124

Authors: Dongkwon Han, Sangho Kim, Sunil Kwon

Abstract:

Unconventional gas resources have dramatically changed the future energy landscape. Unlike conventional gas resources, the key challenges in unconventional gas have been the requirement that applies to advanced approaches for production forecasting due to uncertainty and complexity of fluid flow. In this study, artificial neural network (ANN) model which integrates machine learning and data-driven approach was developed to predict productivity in shale gas. The database of 129 wells of Eagle Ford shale basin used for testing and training of the ANN model. The Input data related to hydraulic fracturing, well completion and productivity of shale gas were selected and the output data is a cumulative production. The performance of the ANN using all data sets, clustering and variables importance (VI) models were compared in the mean absolute percentage error (MAPE). ANN model using all data sets, clustering, and VI were obtained as 44.22%, 10.08% (cluster 1), 5.26% (cluster 2), 6.35%(cluster 3), and 32.23% (ANN VI), 23.19% (SVM VI), respectively. The results showed that the pre-trained ANN model provides more accurate results than the ANN model using all data sets.

Keywords: unconventional gas, artificial neural network, machine learning, clustering, variables importance

Procedia PDF Downloads 172

Authors: M. Ouassaf, S. Belaidi

Abstract:

Aromatase is an estrogen biosynthetic enzyme belonging to the cytochrome P450 family, which catalyzes the limiting step in the conversion of androgens to estrogens. As it is relevant for the promotion of tumor cell growth. A set of thirty 1,2,3-triazole derivatives was used in the quantitative structure activity relationship (QSAR) study using regression multiple linear (MLR), We divided the data into two training and testing groups. The results showed a good predictive ability of the MLR model, the models were statistically robust internally (R² = 0.982) and the predictability of the model was tested by several parameters. including external criteria (R²pred = 0.851, CCC = 0.946). The knowledge gained in this study should provide relevant information that contributes to the origins of aromatase inhibitory activity and, therefore, facilitates our ongoing quest for aromatase inhibitors with robust properties.

Keywords: aromatase inhibitors, QSAR, MLR, 1, 2, 3-triazole

Procedia PDF Downloads 87

Authors: Longqing Li

Abstract:

The paper addresses the inefficiency of the classical model in measuring the Value-at-Risk (VaR) using a normal distribution or a Student’s t distribution. Specifically, the paper focuses on the one day ahead Value-at-Risk (VaR) of major stock market’s daily returns in US, UK, China and Hong Kong in the most recent ten years under 95% confidence level. To improve the predictable power and search for the best performing model, the paper proposes using two leading alternatives, Extreme Value Theory (EVT) and a family of GARCH models, and compares the relative performance. The main contribution could be summarized in two aspects. First, the paper extends the GARCH family model by incorporating EGARCH and TGARCH to shed light on the difference between each in estimating one day ahead Value-at-Risk (VaR). Second, to account for the non-normality in the distribution of financial markets, the paper applies Generalized Error Distribution (GED), instead of the normal distribution, to govern the innovation term. A dynamic back-testing procedure is employed to assess the performance of each model, a family of GARCH and the conditional EVT. The conclusion is that Exponential GARCH yields the best estimate in out-of-sample one day ahead Value-at-Risk (VaR) forecasting. Moreover, the discrepancy of performance between the GARCH and the conditional EVT is indistinguishable.

Keywords: Value-at-Risk, Extreme Value Theory, conditional EVT, backtesting

Procedia PDF Downloads 298

Authors: Vishal Raj, Noorhan Abbas

Abstract:

Ambiguity in NLP (Natural language processing) refers to the ability of a word, phrase, sentence, or text to have multiple meanings. This results in various kinds of ambiguities such as lexical, syntactic, semantic, anaphoric and referential am-biguities. This study is focused mainly on solving the issue of Lexical ambiguity. Word Sense Disambiguation (WSD) is an NLP technique that aims to resolve lexical ambiguity by determining the correct meaning of a word within a given context. Most WSD solutions rely on words for training and testing, but we have used lemma and Part of Speech (POS) tokens of words for training and testing. Lemma adds generality and POS adds properties of word into token. We have designed a novel method to create an affinity matrix to calculate the affinity be-tween any pair of lemma_POS (a token where lemma and POS of word are joined by underscore) of given training set. Additionally, we have devised an al-gorithm to create the sense clusters of tokens using affinity matrix under hierar-chy of POS of lemma. Furthermore, three different mechanisms to predict the sense of target word using the affinity/similarity value are devised. Each contex-tual token contributes to the sense of target word with some value and whichever sense gets higher value becomes the sense of target word. So, contextual tokens play a key role in creating sense clusters and predicting the sense of target word, hence, the model is named Contextual SenSe Model (CSM). CSM exhibits a noteworthy simplicity and explication lucidity in contrast to contemporary deep learning models characterized by intricacy, time-intensive processes, and chal-lenging explication. CSM is trained on SemCor training data and evaluated on SemEval test dataset. The results indicate that despite the naivety of the method, it achieves promising results when compared to the Most Frequent Sense (MFS) model.

Keywords: word sense disambiguation (wsd), contextual sense model (csm), most frequent sense (mfs), part of speech (pos), natural language processing (nlp), oov (out of vocabulary), lemma_pos (a token where lemma and pos of word are joined by underscore), information retrieval (ir), machine translation (mt)

Procedia PDF Downloads 66

Authors: Rossella Arcucci, Luisa D'Amore, Simone Celestino, Giuseppe Scotti, Giuliano Laccetti

Abstract:

This work is the first dowel in a rather wide research activity in collaboration with Euro Mediterranean Center for Climate Changes, aimed at introducing scalable approaches in Ocean Circulation Models. We discuss designing and implementation of a parallel algorithm for solving the Variational Data Assimilation (DA) problem on Graphics Processing Units (GPUs). The algorithm is based on the fully scalable 3DVar DA model, previously proposed by the authors, which uses a Domain Decomposition approach (we refer to this model as the DD-DA model). We proceed with an incremental porting process consisting of 3 distinct stages: requirements and source code analysis, incremental development of CUDA kernels, testing and optimization. Experiments confirm the theoretic performance analysis based on the so-called scale up factor demonstrating that the DD-DA model can be suitably mapped on GPU architectures.

Keywords: data assimilation, GPU architectures, ocean models, parallel algorithm

Procedia PDF Downloads 381

Authors: Gokhan Kilic, Pelin Celik

Abstract:

Structural health monitoring (SHM) is widely used in evaluating the state and health of membrane structures. In the past, in order to collect data and send it to a data collection unit on membrane structures, wire sensors had to be put as part of the SHM process. However, this study recommends using wireless sensors instead of traditional wire ones to construct an economical, useful, and easy-to-install membrane structure health monitoring system. Every wireless sensor uses a software translation program that is connected to the monitoring server. Operational neural networks (ONNs) have recently been developed to solve the shortcomings of convolutional neural networks (CNNs), such as the network's resemblance to the linear neuron model. The results of using ONNs for monitoring to evaluate the structural health of a membrane are presented in this work.

Keywords: wireless sensor network, non-destructive testing, operational neural networks, membrane structures, dynamic monitoring

Procedia PDF Downloads 45

Authors: A. Mech

Abstract:

Repetitive transcranial magnetic stimulation has proven to be a valuable treatment option for patients who have failed to respond to multiple courses of antidepressant medication. In fact, the American Psychiatric Association recommends TMS after one failed treatment course of antidepressant medication. Genetic testing has proven valuable for pharmacokinetic variables, which, if understood, could lead to more efficient dosing of psychotropic medications to improve outcomes. Pharmacodynamic testing can identify biomarkers, which, if addressed, can improve patients' outcomes in antidepressant therapy. Monotherapy treatment of major depressive disorder with methylated B vitamin treatment has been shown to be safe and effective in patients with MTHFR polymorphisms without waiting for multiple trials of failed medication treatment for depression. Such treatment has demonstrated remission rates similar to antidepressant clinical trials. Combining pharmacodynamics testing with repetitive TMS treatment with NeuroStar has shown promising potential for enhancing remission rates and durability of treatment. In this study, a retrospective chart review (ongoing) of patients who obtained repetitive TMS treatment enhanced by dietary supplementation guided by Pharmacodynamic testing, displayed a greater remission rate (90%) than patients treated with only NeuroStar TMS (62%).

Keywords: improved remission rate, major depressive disorder, pharmacodynamic testing, rTMS outcomes

Procedia PDF Downloads 22

Authors: Jooyoung Park, Junkyeong Kim, Aoqi Zhang, Seunghee Park

Abstract:

Non-destructive testing on cable is in great demand due to safety accidents at sites where many equipments using cables are installed. In this paper, the quantitative change of the obtained signal was analyzed using a magnetic flux leakage (MFL) method. A two-dimensional simulation was conducted with a FEM model replicating real elevator cables. The simulation data were compared for three parameters (depth of defect, width of defect and inspection velocity). Then, an experiment on same conditions was carried out to verify the results of the simulation. Signals obtained from both the simulation and the experiment were transformed to characterize the properties of the damage. Throughout the results, a cable damage detection based on an MFL method was confirmed to be feasible. In further study, it is expected that the MFL signals of an entire specimen will be gained and visualized as well.

Keywords: magnetic flux leakage (mfl), cable damage detection, non-destructive testing, numerical simulation

Procedia PDF Downloads 352

Authors: Zachary Pan

Abstract:

Our general mission is to solve the problem of classifying images into different body part types and deciding if each of them is healthy or not. However, for now, we will determine healthiness for only one-sixth of the body parts, specifically the chest. We will detect pneumonia in X-ray scans of those chest images. With this type of AI, doctors can use it as a second opinion when they are taking CT or X-ray scans of their patients. Another ad-vantage of using this machine learning classifier is that it has no human weaknesses like fatigue. The overall ap-proach to this problem is to split the problem into two parts: first, classify the image, then determine if it is healthy. In order to classify the image into a specific body part class, the body parts dataset must be split into test and training sets. We can then use many models, like neural networks or logistic regression models, and fit them using the training set. Now, using the test set, we can obtain a realistic accuracy the models will have on images in the real world since these testing images have never been seen by the models before. In order to increase this testing accuracy, we can also apply many complex algorithms to the models, like multiplicative weight update. For the second part of the problem, to determine if the body part is healthy, we can have another dataset consisting of healthy and non-healthy images of the specific body part and once again split that into the test and training sets. We then use another neural network to train on those training set images and use the testing set to figure out its accuracy. We will do this process only for the chest images. A major conclusion reached is that convolutional neural networks are the most reliable and accurate at image classification. In classifying the images, the logistic regression model, the neural network, neural networks with multiplicative weight update, neural networks with the black box algorithm, and the convolutional neural network achieved 96.83 percent accuracy, 97.33 percent accuracy, 97.83 percent accuracy, 96.67 percent accuracy, and 98.83 percent accuracy, respectively. On the other hand, the overall accuracy of the model that de-termines if the images are healthy or not is around 78.37 percent accuracy.

Keywords: body part, healthcare, machine learning, neural networks

Procedia PDF Downloads 71

Authors: Hestiasari Rante, Leonardo De Araújo, Heidi Schelhowe

Abstract:

Usability testing with children is similar in many aspects to usability testing with adults. However, there are a few differences that one needs to be aware of in order to get the most out of the sessions, and to ensure that children are comfortable and enjoying the process. This paper presents the need to acquire methodological knowledge for involving children as test users in usability testing, with consideration on Piaget’s theory of cognitive growth. As a case study, we use BatiKids, an application developed to evoke children’s enthusiasm to be involved in culture heritage preservation. The usability test was applied to 24 children from 9 to 10 years old. The children were divided into two groups; one interacted with the application through a graphic tablet with pen, and the other through touch screen. Both of the groups had to accomplish the same amount of tasks. In the end, children were asked to give feedback. The results suggested that children who interacted using the graphic tablet with pen had more difficulties rather than children who interacted through touch screen. However, the difficulty brought by the graphic tablet with pen is an important learning objective in order to understand the difficulties of using canting, which is an important part of batik.

Keywords: batikids, children, child-computer interaction, usability test

Procedia PDF Downloads 264

Authors: M. A. Zeinelabdeen, A. E. Abasaeed, M. H. Gaily, A. K. Sulieman, M. D. Putra

Abstract:

The effect of temperature on the production of fructose and bioethanol from date syrup via selective fermentation by S. cerevisiae ATCC 36859 strain was studied. Various temperatures have been tested (27, 30 and 33 ᵒC). The fermentation experiments were conducted in a water shaker bath at the three temperatures under testing and 120 rpm. The results showed that a high fructose yield can be achieved at all temperatures under testing while the optimal is 27 ᵒC with 84% fructose yield. A high ethanol yield can be obtained for all temperatures under testing. However; the maximum biomass concentration and ethanol yield (86.22%) were obtained at 30 ᵒC.

Keywords: dates, ethanol, fructose, fermentation, S. cerevisiae

Procedia PDF Downloads 363