Search results for: stepwise regression.

Authors: Mahtab Davari, Charles Edward Okon, Somayeh Aghanavesi

Abstract:

Every institute of learning is usually interested in the performance of enrolled students. The level of these performances determines the approach an institute of study may adopt in rendering academic services. The focus of this paper is to evaluate students' academic performance in given courses of study using machine learning methods. This study evaluated various supervised machine learning classification algorithms such as Logistic Regression (LR), Support Vector Machine (SVM), Random Forest, Decision Tree, K-Nearest Neighbors, Linear Discriminant Analysis (LDA), and Quadratic Discriminant Analysis, using selected features to predict study performance. The accuracy, precision, recall, and F1 score obtained from a 5-Fold Cross-Validation were used to determine the best classification algorithm to predict students’ performances. SVM (using a linear kernel), LDA, and LR were identified as the best-performing machine learning methods. Also, using the LR model, this study identified students' educational habits such as reading and paying attention in class as strong determinants for a student to have an above-average performance. Other important features include the academic history of the student and work. Demographic factors such as age, gender, high school graduation, etc., had no significant effect on a student's performance.

Keywords: Student performance, supervised machine learning, prediction, classification, cross-validation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 472

Authors: Tanwarat Kajsongkram, Saowalux Rotamporn, Sirinat Limbunruang, Sirinan Thubthimthed

Abstract:

High Performance Liquid Chromatography (HPLC) method was developed and validated for simultaneous estimation of 6-Gingerol(6G) and 6-Shogaol(6S) in joint pain relief gel containing ginger extract. The chromatographic separation was achieved by using C18 column, 150 x 4.6mm i.d., 5μ Luna, mobile phase containing acetonitrile and water (gradient elution). The flow rate was 1.0 ml/min and the absorbance was monitored at 282 nm. The proposed method was validated in terms of the analytical parameters such as specificity, accuracy, precision, linearity, range, limit of detection (LOD), limit of quantification (LOQ), and determined based on the International Conference on Harmonization (ICH) guidelines. The linearity ranges of 6G and 6S were obtained over 20- 60 and 6-18 μg/ml respectively. Good linearity was observed over the above-mentioned range with linear regression equation Y= 11016x- 23778 for 6G and Y = 19276x-19604 for 6S (x is concentration of analytes in μg/ml and Y is peak area). The value of correlation coefficient was found to be 0.9994 for both markers. The limit of detection (LOD) and limit of quantification (LOQ) for 6G were 0.8567 and 2.8555 μg/ml and for 6S were 0.3672 and 1.2238 μg/ml respectively. The recovery range for 6G and 6S were found to be 91.57 to 102.36 % and 84.73 to 92.85 % for all three spiked levels. The RSD values from repeated extractions for 6G and 6S were 3.43 and 3.09% respectively. The validation of developed method on precision, accuracy, specificity, linearity, and range were also performed with well-accepted results.

Keywords: Ginger, 6-gingerol, HPLC, 6-shogaol.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3375

Authors: Abdulfatah Faraj Aboufayed

Abstract:

Water erosion is the most important problems of the soil in the Jabel Nefusa area located in northwest of Libya; therefore, erosion station had been established in the Faculty of Veterinary and dryfarming research Station, University of the Al-japel Al-gharbi in Zentan. The length of the station is 72.6 feet, 6 feet width and the percentage of its slope is 3%. The station were established to measure the amount of soil eroded and amount of surface water produced during the seasons 95/96 and 96/97 from each rain storms. The monitoring shows that there was a difference between the two seasons in the number of rainstorms which made differences in the amount of surface runoff water and the amount of soil eroded between the two seasons. Although the slope is low (3%), the soil texture is sandy and the land ploughed twice during each season surface runoff and soil eroded were occurred. The average amount of eroded soil was 3792 grams (gr) per season and the average amount of surface runoff water was 410 liter (L) per season. The amount of surface runoff water would be much greater from Jebel Nefusa upland with steep slopes and collecting of them will save a valuable amount of water which lost as a runoff while this area is in desperate of this water. The regression analysis of variance show strong correlation between rainfall depth and the other two depended variable (the amount of surface runoff water and the amount of eroded soil. It shows also strong correlation between amount of surface runoff water and amount of eroded soil.

Keywords: Rain, Surface runoff water, Soil, Water erosion, Soil erosion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1947

Authors: Y. Deng, X. Li, C. Kwan, B. Raj, R. Stern

Abstract:

The current speech interfaces in many military applications may be adequate for native speakers. However, the recognition rate drops quite a lot for non-native speakers (people with foreign accents). This is mainly because the nonnative speakers have large temporal and intra-phoneme variations when they pronounce the same words. This problem is also complicated by the presence of large environmental noise such as tank noise, helicopter noise, etc. In this paper, we proposed a novel continuous acoustic feature adaptation algorithm for on-line accent and environmental adaptation. Implemented by incremental singular value decomposition (SVD), the algorithm captures local acoustic variation and runs in real-time. This feature-based adaptation method is then integrated with conventional model-based maximum likelihood linear regression (MLLR) algorithm. Extensive experiments have been performed on the NATO non-native speech corpus with baseline acoustic model trained on native American English. The proposed feature-based adaptation algorithm improved the average recognition accuracy by 15%, while the MLLR model based adaptation achieved 11% improvement. The corresponding word error rate (WER) reduction was 25.8% and 2.73%, as compared to that without adaptation. The combined adaptation achieved overall recognition accuracy improvement of 29.5%, and WER reduction of 31.8%, as compared to that without adaptation.

Keywords: speaker adaptation; environment adaptation; robust speech recognition; SVD; non-native speech recognition

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3177

Authors: H. B. Mehta, Vipul M. Patel, Jyotirmay Banerjee

Abstract:

The present paper discusses the prediction of gas-liquid two-phase frictional pressure drop in a 2.12 mm horizontal circular minichannel using Artificial Neural Network (ANN). The experimental results are obtained with air as gas phase and water as liquid phase. The superficial gas velocity is kept in the range of 0.0236 m/s to 0.4722 m/s while the values of 0.0944 m/s, 0.1416 m/s and 0.1889 m/s are considered for superficial liquid velocity. The experimental results are predicted using different Artificial Neural Network (ANN) models. Networks used for prediction are radial basis, generalised regression, linear layer, cascade forward back propagation, feed forward back propagation, feed forward distributed time delay, layer recurrent, and Elman back propagation. Transfer functions used for networks are Linear (PURELIN), Logistic sigmoid (LOGSIG), tangent sigmoid (TANSIG) and Gaussian RBF. Combination of networks and transfer functions give different possible neural network models. These models are compared for Mean Absolute Relative Deviation (MARD) and Mean Relative Deviation (MRD) to identify the best predictive model of ANN.

Keywords: Minichannel, Two-Phase Flow, Frictional Pressure Drop, ANN, MARD, MRD.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1365

Authors: Nadya Hajar, Zainal, S., Atikah, O., Tengku Elida, T. Z. M.

Abstract:

Ethanol has been known for a long time, being perhaps the oldest product obtained through traditional biotechnology fermentation. Agriculture waste as substrate in fermentation is vastly discussed as alternative to replace edible food and utilization of organic material. Pineapple peel, highly potential source as substrate is a by-product of the pineapple processing industry. Bio-ethanol from pineapple (Ananas comosus) peel extract was carried out by controlling fermentation without any treatment. Saccharomyces ellipsoides was used as inoculum in this fermentation process as it is naturally found at the pineapple skin. In this study, the capability of Response Surface Methodology (RSM) for optimization of ethanol production from pineapple peel extract using Saccharomyces ellipsoideus in batch fermentation process was investigated. Effect of five test variables in a defined range of inoculum concentration 6- 14% (v/v), pH (4.0-6.0), sugar concentration (14-22°Brix), temperature (24-32°C) and time of incubation (30-54 hrs) on the ethanol production were evaluated. Data obtained from experiment were analyzed with RSM of MINITAB Software (Version 15) whereby optimum ethanol concentration of 8.637% (v/v) was determined. The optimum condition of 14% (v/v) inoculum concentration, pH 6, 22°Brix, 26°C and 30hours of incubation. The significant regression equation or model at the 5% level with correlation value of 99.96% was also obtained.

Keywords: Bio-ethanol, pineapple peel extract, Response Surface Methodology (RSM), Saccharomyces ellipsoideus.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6011

Authors: Yeonjeong Lee, Kyoung-jae Kim, Youngtae Kim

Abstract:

This study proposes a novel recommender system that uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user’s preference. The proposed model consists of two steps. In the first step, this study uses logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. Then, this study combines the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. In the second step, this study uses the market basket analysis to extract association rules for co-purchased products. Finally, the system selects customers who have high likelihood to purchase products in each product group and recommends proper products from same or different product groups to them through above two steps. We test the usability of the proposed system by using prototype and real-world transaction and profile data. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The results also show that the proposed system may be useful in real-world online shopping store.

Keywords: Product recommender system, Ensemble technique, Association rules, Decision tree, Artificial neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4177

Authors: Ikumapayi Catherine Mayowa

Abstract:

The well been of human beings on construction site is very important, many man power had been lost through accidents which kills or make workers physically unfit to carry out construction activities, these in turn have multiple effects on the whole economy. Thus it is necessary to put all safety items and regulations in place before construction activities can commence. This study was carried out in Ondo state of Nigeria to known and analyse the state of health and safety of construction workers in the state. The study was done using first hand observation method, 50 construction project sites were visited in 10 major towns of Ondo state, questionnaires were distributed and the results were analysed. The result show that construction workers are being exposed to a lot of construction site hazards due to lack of inadequate safety programmes and nonprovision of appropriate safety materials for workers on site. From the data gotten for each site visited and the statistical analysis, it can be concluded that occurrence of accident on construction sites depends significantly on the available safety facilities on the sites. The result of the regression statistics show that the level of significant of the dependence of occurrence of accident on the availability of safety items on site is 0.0362 which is less than 0.05 maximum significant level required. Therefore a vital way of sustaining our building strategy is by given a detail attention to provision of adequate health and safety items on construction sites which will reduce the occurrence of accident, loss of man power and death of skilled workers among others.

Keywords: Construction sites, health, safety, welfare.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1665

Authors: J. Cabral, C. Barreto Carvalho, C. da Motta, M. Sousa

Abstract:

Community integration is a construct that an increasing body of research has shown to have a significant impact on the wellbeing and recovery of people with psychiatric problems. However, there are few studies that explore which factors can be associated and predict community integration. Moreover, community integration has been mostly studied in minority groups, and current literature on the definition and manifestation of community integration in the general population is scarcer. Thus, the current study aims to characterize community integration and explore possible predictor variables in a sample of participants with psychiatric problems (PP, N=183) and a sample of participants from the general population (GP, N=211). Results show that people with psychiatric problems present above average values of community integration, but are significantly lower than their healthy counterparts. It was also possible to observe that community integration does not vary in terms of the sociodemographic characteristics of both groups in this study. Correlation and multiple regression showed that, among several variables that literature present as relevant in the community integration process, only three variables emerged as having the most explanatory value in community integration of both groups: sense of community, basic needs satisfaction and submission. These results also shown that those variables have increased explanatory power in the PP sample, which leads us to emphasize the need to address this issue in future studies and increase the understanding of the factors that can be involved in the promotion of community integration, in order to devise more effective interventions in this field.

Keywords: Community integration, mental illness, predictors.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1786

Authors: Li Yu, Chenlu Jiao, Hongrun Xin, Yan Wang, Kaiyang Wang

Abstract:

In order to study the impact of various factors on the housing price, we propose to build different prediction models based on deep learning to determine the existing data of the real estate in order to more accurately predict the housing price or its changing trend in the future. Considering that the factors which affect the housing price vary widely, the proposed prediction models include two categories. The first one is based on multiple characteristic factors of the real estate. We built Convolution Neural Network (CNN) prediction model and Long Short-Term Memory (LSTM) neural network prediction model based on deep learning, and logical regression model was implemented to make a comparison between these three models. Another prediction model is time series model. Based on deep learning, we proposed an LSTM-1 model purely regard to time series, then implementing and comparing the LSTM model and the Auto-Regressive and Moving Average (ARMA) model. In this paper, comprehensive study of the second-hand housing price in Beijing has been conducted from three aspects: crawling and analyzing, housing price predicting, and the result comparing. Ultimately the best model program was produced, which is of great significance to evaluation and prediction of the housing price in the real estate industry.

Keywords: Deep learning, convolutional neural network, LSTM, housing prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4890

Authors: Liping Jing, Michael K. Ng, Tieyong Zeng

Abstract:

Microarray data profiles gene expression on a whole genome scale, therefore, it provides a good way to study associations between gene expression and occurrence or progression of cancer. More and more researchers realized that microarray data is helpful to predict cancer sample. However, the high dimension of gene expressions is much larger than the sample size, which makes this task very difficult. Therefore, how to identify the significant genes causing cancer becomes emergency and also a hot and hard research topic. Many feature selection algorithms have been proposed in the past focusing on improving cancer predictive accuracy at the expense of ignoring the correlations between the features. In this work, a novel framework (named by SGS) is presented for stable gene selection and efficient cancer prediction . The proposed framework first performs clustering algorithm to find the gene groups where genes in each group have higher correlation coefficient, and then selects the significant genes in each group with Bayesian Lasso and important gene groups with group Lasso, and finally builds prediction model based on the shrinkage gene space with efficient classification algorithm (such as, SVM, 1NN, Regression and etc.). Experiment results on real world data show that the proposed framework often outperforms the existing feature selection and prediction methods, say SAM, IG and Lasso-type prediction model.

Keywords: Gene Selection, Cancer Prediction, Lasso, Clustering, Classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1997

Authors: Yong Zhao, Jian He, Cheng Zhang

Abstract:

Cardiovascular disease resulting from hypertension poses a significant threat to human health, and early detection of hypertension can potentially save numerous lives. Traditional methods for detecting hypertension require specialized equipment and are often incapable of capturing continuous blood pressure fluctuations. To address this issue, this study starts by analyzing the principle of heart rate variability (HRV) and introduces the utilization of sliding window and power spectral density (PSD) techniques to analyze both temporal and frequency domain features of HRV. Subsequently, a hypertension prediction network that relies on HRV is proposed, combining Resnet, attention mechanisms, and a multi-layer perceptron. The network leverages a modified ResNet18 to extract frequency domain features, while employing an attention mechanism to integrate temporal domain features, thus enabling auxiliary hypertension prediction through the multi-layer perceptron. The proposed network is trained and tested using the publicly available SHAREE dataset from PhysioNet. The results demonstrate that the network achieves a high prediction accuracy of 92.06% for hypertension, surpassing traditional models such as K Near Neighbor (KNN), Bayes, Logistic regression, and traditional Convolutional Neural Network (CNN).

Keywords: Feature extraction, heart rate variability, hypertension, residual networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 104

Authors: P. Manivannan, M. Rajasimman

Abstract:

Response surface methodology was used for quantitative investigation of water and solids transfer during osmotic dehydration of beetroot in aqueous solution of salt. Effects of temperature (25 – 45oC), processing time (30–150 min), salt concentration (5–25%, w/w) and solution to sample ratio (5:1 – 25:1) on osmotic dehydration of beetroot were estimated. Quadratic regression equations describing the effects of these factors on the water loss and solids gain were developed. It was found that effects of temperature and salt concentrations were more significant on the water loss than the effects of processing time and solution to sample ratio. As for solids gain processing time and salt concentration were the most significant factors. The osmotic dehydration process was optimized for water loss, solute gain, and weight reduction. The optimum conditions were found to be: temperature – 35oC, processing time – 90 min, salt concentration – 14.31% and solution to sample ratio 8.5:1. At these optimum values, water loss, solid gain and weight reduction were found to be 30.86 (g/100 g initial sample), 9.43 (g/100 g initial sample) and 21.43 (g/100 g initial sample) respectively.

Keywords: Optimization, Osmotic dehydration, Beetroot, saltsolution, response surface methodology

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3414

Authors: Heba Mohammed Nagy, Walid Mohamed Aly, Osama Fathy Hegazy

Abstract:

Educational  data mining  is  a  specific  data   mining field applied to data originating from educational environments, it relies on different  approaches to discover hidden knowledge  from  the  available   data. Among these approaches are   machine   learning techniques which are used to build a system that acquires learning from previous data. Machine learning can be applied to solve different regression, classification, clustering and optimization problems.

In  our  research, we propose  a “Student  Advisory  Framework” that  utilizes  classification  and  clustering  to  build  an  intelligent system. This system can be used to provide pieces of consultations to a first year  university  student to  pursue a  certain   education   track   where  he/she  will  likely  succeed  in, aiming  to  decrease   the  high  rate   of  academic  failure   among these  students.  A real case study  in Cairo  Higher  Institute  for Engineering, Computer  Science  and  Management  is  presented using  real  dataset   collected  from  2000−2012.The dataset has two main components: pre-higher education dataset and first year courses results dataset. Results have proved the efficiency of the suggested framework.

Keywords: Classification, Clustering, Educational Data Mining (EDM), Machine Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5165

Authors: Ujjwala Bhand, Mridula Goel

Abstract:

Global Competitiveness Index (GCI) prepared by World Economic Forum has become a benchmark in studying the competitiveness of countries and for understanding the factors that enable competitiveness. Innovation is a key pillar in competitiveness and has the unique property of enabling exponential economic growth. This paper attempts to analyze how the pillars comprising the Global Competitiveness Index affect innovation and whether GDP growth can directly affect innovation outcomes for a country. The key objective of the study is to identify areas on which governments of developing countries can focus policies and programs to improve their country’s innovativeness. We have compiled a panel data set for top innovating countries and large emerging economies called BRICS from 2007-08 to 2014-15 in order to find the significant factors that affect innovation. The results of the regression analysis suggest that government should make policies to improve labor market efficiency, establish sophisticated business networks, provide basic health and primary education to its people and strengthen the quality of higher education and training services in the economy. The achievements of smaller economies on innovation suggest that concerted efforts by governments can counter any size related disadvantage, and in fact can provide greater flexibility and speed in encouraging innovation.

Keywords: Innovation, Global Competitiveness Index, BRICS, economic growth.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 996

Authors: Mokhtar Kouki Inès Rekik

Abstract:

This paper focuses on the assessment of the air pollution and morbidity relationship in Tunisia. Air pollution is measured by ozone air concentration and the morbidity is measured by the number of respiratory-related restricted activity days during the 2-week period prior to the interview. Socioeconomic data are also collected in order to adjust for any confounding covariates. Our sample is composed by 407 Tunisian respondents; 44.7% are women, the average age is 35.2, near 69% are living in a house built after 1980, and 27.8% have reported at least one day of respiratory-related restricted activity. The model consists on the regression of the number of respiratory-related restricted activity days on the air quality measure and the socioeconomic covariates. In order to correct for zero-inflation and heterogeneity, we estimate several models (Poisson, negative binomial, zero inflated Poisson, Poisson hurdle, negative binomial hurdle and finite mixture Poisson models). Bootstrapping and post-stratification techniques are used in order to correct for any sample bias. According to the Akaike information criteria, the hurdle negative binomial model has the greatest goodness of fit. The main result indicates that, after adjusting for socioeconomic data, the ozone concentration increases the probability of positive number of restricted activity days.

Keywords: Bootstrapping, hurdle negbin model, overdispersion, ozone concentration, respiratory-related restricted activity days.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2085

Authors: Pongsatorn Tantrabundit, Lersak Phothong, Ong-art Chanprasitchai

Abstract:

Due to the emergence of the Internet, it has extended the traditional Word-of-Mouth (WOM) to a new form called “Electronic Word-of-Mouth (eWOM).” Unlike traditional WOM, eWOM is able to present information in various ways by applying different components. Each eWOM component generates different effects on online consumer behavior. This research investigates the effects of Webcare (responding message) from product/ service providers on negative eWOM by applying two types of products (search and experience). The proposed conceptual model was developed based on the combination of the stages in consumer decision-making process, theory of reasoned action (TRA), theory of planned behavior (TPB), the technology acceptance model (TAM), the information integration theory and the elaboration likelihood model. The methodology techniques used in this study included multivariate analysis of variance (MANOVA) and multiple regression analysis. The results suggest that Webcare does slightly increase Thai online consumer’s perceptions on perceived eWOM trustworthiness, information diagnosticity and quality. For negative eWOM, we also found that perceived eWOM Trustworthiness, perceived eWOM diagnosticity and quality have a positive relationship with eWOM influence whereas perceived valence has a negative relationship with eWOM influence in Thai online consumers.

Keywords:

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1353

Authors: Mehdi Modabberifar, Milad Roodi, Ehsan Souri

Abstract:

In recent years, honeycomb fiber reinforced plastic (FRP) sandwich panels have been increasingly used in various industries. Low weight, low price and high mechanical strength are the benefits of these structures. However, their mechanical properties and behavior have not been fully explored. The objective of this study is to conduct a combined numerical-statistical investigation of honeycomb FRP sandwich beams subject to torsion load. In this paper, the effect of geometric parameters of sandwich panel on maximum shear strain in both face and core and angle of torsion in a honeycomb FRP sandwich structures in torsion is investigated. The effect of Parameters including core thickness, face skin thickness, cell shape, cell size, and cell thickness on mechanical behavior of the structure were numerically investigated. Main effects of factors were considered in this paper and regression equations were derived. Taguchi method was employed as experimental design and an optimum parameter combination for the maximum structure stiffness has been obtained. The results showed that cell size and face skin thickness have the most significant impacts on torsion angle, maximum shear strain in face and core.

Keywords: Finite element, honeycomb FRP sandwich panel, torsion, civil engineering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2569

Authors: Seongcheol Kwon, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

We assume an IoT-based smart-home environment where the on-off status of each of the electrical appliances including the room lights can be recognized in a real time by monitoring and analyzing the smart meter data. At any moment in such an environment, we can recognize what the household or the user is doing by referring to the status data of the appliances. In this paper, we focus on a smart-home service that is to activate a robot vacuum cleaner at right time by recognizing the user situation, which requires a situation-aware model that can distinguish the situations that allow vacuum cleaning (Yes) from those that do not (No). We learn as our candidate models a few classifiers such as naïve Bayes, decision tree, and logistic regression that can map the appliance-status data into Yes and No situations. Our training and test data are obtained from simulations of user behaviors, in which a sequence of user situations such as cooking, eating, dish washing, and so on is generated with the status of the relevant appliances changed in accordance with the situation changes. During the simulation, both the situation transition and the resulting appliance status are determined stochastically. To compare the performances of the aforementioned classifiers we obtain their learning curves for different types of users through simulations. The result of our empirical study reveals that naïve Bayes achieves a slightly better classification accuracy than the other compared classifiers.

Keywords: Situation-awareness, Smart home, IoT, Machine learning, Classifier.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1810

Authors: S. Sharma, U. Batra, S. Kapoor, A. Dua

Abstract:

In this study, the effects and interactions of reaction time and capping agent assistance during sol-gel synthesis of magnesium substituted hydroxyapatite nanopowder (MgHA) on hydroxyapatite (HA) to β-tricalcium phosphate (β-TCP) ratio, Ca/P ratio and mean crystallite size was examined experimentally as well as through statistical analysis. MgHA nanopowders were synthesized by sol-gel technique at room temperature using aqueous solution of calcium nitrate tetrahydrate, magnesium nitrate hexahydrate and potassium dihydrogen phosphate as starting materials. The reaction time for sol-gel synthesis was varied between 15 to 60 minutes. Two process routes were followed with and without addition of triethanolamine (TEA) in the solutions. The elemental compositions of as-synthesized powders were determined using X-ray fluorescence (XRF) spectroscopy. The functional groups present in the assynthesized MgHA nanopowders were established through Fourier Transform Infrared Spectroscopy (FTIR). The amounts of phases present, Ca/P ratio and mean crystallite sizes of MgHA nanopowders were determined using X-ray diffraction (XRD). The HA content in biphasic mixture of HA and β-TCP and Ca/P ratio in as-synthesized MgHA nanopowders increased effectively with reaction time of sols (p<0.0001, two way ANOVA), however, these were independent of TEA addition (p>0.15, two way ANOVA). The MgHA nanopowders synthesized with TEA assistance exhibited 14 nm lower crystallite size (p<0.018, 2 sample t-test) compared to the powder synthesized without TEA assistance.

Keywords: Capping agent, hydroxyapatite, regression analysis, sol-gel, 2- sample t-test, two-way ANOVA.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1575

Authors: J. P. Dubois, O. M. Abdul-Latif

Abstract:

Support Vector Machine (SVM) is a recent class of statistical classification and regression techniques playing an increasing role in applications to detection problems in various engineering problems, notably in statistical signal processing, pattern recognition, image analysis, and communication systems. In this paper, SVM is applied to an infrared (IR) binary communication system with different types of channel models including Ricean multipath fading and partially developed scattering channel with additive white Gaussian noise (AWGN) at the receiver. The structure and performance of SVM in terms of the bit error rate (BER) metric is derived and simulated for these channel stochastic models and the computational complexity of the implementation, in terms of average computational time per bit, is also presented. The performance of SVM is then compared to classical binary signal maximum likelihood detection using a matched filter driven by On-Off keying (OOK) modulation. We found that the performance of SVM is superior to that of the traditional optimal detection schemes used in statistical communication, especially for very low signal-to-noise ratio (SNR) ranges. For large SNR, the performance of the SVM is similar to that of the classical detectors. The implication of these results is that SVM can prove very beneficial to IR communication systems that notoriously suffer from low SNR at the cost of increased computational complexity.

Keywords: Least square-support vector machine, on-off keying, matched filter, maximum likelihood detector, wireless infrared communication.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1917

Authors: Joseph E. Estevez, Mahdi Ghazizadeh, James G. Ryan, Ajit D. Kelkar

Abstract:

Radiation shielding is an obstacle in long duration space exploration. Boron Nitride Nanotubes (BNNTs) have attracted attention as an additive to radiation shielding material due to B¹⁰’s large neutron capture cross section. The B¹⁰ has an effective neutron capture cross section suitable for low energy neutrons ranging from 10^-5 to 10⁴ eV and hydrogen is effective at slowing down high energy neutrons. Hydrogenated BNNTs are potentially an ideal nanofiller for radiation shielding composites. We use Molecular Dynamics (MD) Simulation via Material Studios Accelrys 6.0 to model the Young’s Modulus of Hydrogenated BNNTs. An extrapolation technique was employed to determine the Young’s Modulus due to the deformation of the nanostructure at its theoretical density. A linear regression was used to extrapolate the data to the theoretical density of 2.62g/cm³. Simulation data shows that the hydrogenated BNNTs will experience a 11% decrease in the Young’s Modulus for (6,6) BNNTs and 8.5% decrease for (8,8) BNNTs compared to non-hydrogenated BNNT’s. Hydrogenated BNNTs are a viable option as a nanofiller for radiation shielding nanocomposite materials for long range and long duration space exploration.

Keywords: Boron Nitride Nanotube, Radiation Shielding, Young Modulus, Atomistic Modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6619

Authors: Haifeng Wang, Haili Zhang

Abstract:

Most movie recommendation systems have been developed for customers to find items of interest. This work introduces a predictive model usable by small and medium-sized enterprises (SMEs) who are in need of a data-based and analytical approach to stock proper movies for local audiences and retain more customers. We used classification models to extract features from thousands of customers’ demographic, behavioral and social information to predict their movie genre preference. In the implementation, a Gaussian kernel support vector machine (SVM) classification model and a logistic regression model were established to extract features from sample data and their test error-in-sample were compared. Comparison of error-out-sample was also made under different Vapnik–Chervonenkis (VC) dimensions in the machine learning algorithm to find and prevent overfitting. Gaussian kernel SVM prediction model can correctly predict movie genre preferences in 85% of positive cases. The accuracy of the algorithm increased to 93% with a smaller VC dimension and less overfitting. These findings advance our understanding of how to use machine learning approach to predict customers’ preferences with a small data set and design prediction tools for these enterprises.

Keywords: Computational social science, movie preference, machine learning, SVM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1598

Authors: A. Nasiri Pour, B. Rostami Tabar, A.Rahimzadeh

Abstract:

Accurate demand forecasting is one of the most key issues in inventory management of spare parts. The problem of modeling future consumption becomes especially difficult for lumpy patterns, which characterized by intervals in which there is no demand and, periods with actual demand occurrences with large variation in demand levels. However, many of the forecasting methods may perform poorly when demand for an item is lumpy. In this study based on the characteristic of lumpy demand patterns of spare parts a hybrid forecasting approach has been developed, which use a multi-layered perceptron neural network and a traditional recursive method for forecasting future demands. In the described approach the multi-layered perceptron are adapted to forecast occurrences of non-zero demands, and then a conventional recursive method is used to estimate the quantity of non-zero demands. In order to evaluate the performance of the proposed approach, their forecasts were compared to those obtained by using Syntetos & Boylan approximation, recently employed multi-layered perceptron neural network, generalized regression neural network and elman recurrent neural network in this area. The models were applied to forecast future demand of spare parts of Arak Petrochemical Company in Iran, using 30 types of real data sets. The results indicate that the forecasts obtained by using our proposed mode are superior to those obtained by using other methods.

Keywords: Lumpy Demand, Neural Network, Forecasting, Hybrid Approach.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2620

Authors: Fl. Loury, P. Sablonière

Abstract:

In this paper a stochastic scenario-based model predictive control applied to molten salt storage systems in concentrated solar tower power plant is presented. The main goal of this study is to build up a tool to analyze current and expected future resources for evaluating the weekly power to be advertised on electricity secondary market. This tool will allow plant operator to maximize profits while hedging the impact on the system of stochastic variables such as resources or sunlight shortage.

Solving the problem first requires a mixed logic dynamic modeling of the plant. The two stochastic variables, respectively the sunlight incoming energy and electricity demands from secondary market, are modeled by least square regression. Robustness is achieved by drawing a certain number of random variables realizations and applying the most restrictive one to the system. This scenario approach control technique provides the plant operator a confidence interval containing a given percentage of possible stochastic variable realizations in such a way that robust control is always achieved within its bounds. The results obtained from many trajectory simulations show the existence of a ‘’reliable’’ interval, which experimentally confirms the algorithm robustness.

Keywords: Molten Salt Storage System, Concentrated Solar Tower Power Plant, Robust Stochastic Model Predictive Control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1880

Authors: Aref Aasi, Sahar Ebrahimi Bajgani, Erfan Aasi

Abstract:

Breast cancer (BC) continues to be the most frequent cancer in females and causes the highest number of cancer-related deaths in women worldwide. Inspired by recent advances in studying the relationship between different patient attributes and features and the disease, in this paper, we have tried to investigate the different classification methods for better diagnosis of BC in the early stages. In this regard, datasets from the University Hospital Centre of Coimbra were chosen, and different machine learning (ML)-based and neural network (NN) classifiers have been studied. For this purpose, we have selected favorable features among the nine provided attributes from the clinical dataset by using a random forest algorithm. This dataset consists of both healthy controls and BC patients, and it was noted that glucose, BMI, resistin, and age have the most importance, respectively. Moreover, we have analyzed these features with various ML-based classifier methods, including Decision Tree (DT), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM) along with NN-based Multi-Layer Perceptron (MLP) classifier. The results revealed that among different techniques, the SVM and MLP classifiers have the most accuracy, with amounts of 96% and 92%, respectively. These results divulged that the adopted procedure could be used effectively for the classification of cancer cells, and also it encourages further experimental investigations with more collected data for other types of cancers.

Keywords: Breast cancer, health diagnosis, Machine Learning, biomarker classification, Neural Network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 220

Authors: Revoti Prasad Bora, Nikita Katyal

Abstract:

Promotion is a key element in the retail business. Thus, analysis of promotions to quantify their effectiveness in terms of Revenue and/or Margin is an essential activity in the retail industry. However, measuring the sales/revenue uplift is based on estimations, as the actual sales/revenue without the promotion is not present. Further, the presence of Halo and Cannibalization in a multiple parallel promotions’ scenario complicates the problem. Calculating Baseline by considering inter-brand/competitor items or using Halo and Cannibalization's impact on Revenue calculations by considering Baseline as an interpretation of items’ unit sales in neighboring nonpromotional weeks individually may not capture the overall Revenue uplift in the case of multiple parallel promotions. Hence, this paper proposes a Machine Learning based method for calculating the Revenue uplift by considering the Halo and Cannibalization impact on the Baseline and the Revenue. In the first section of the proposed methodology, Baseline of an item is calculated by incorporating the impact of the promotions on its related items. In the later section, the Revenue of an item is calculated by considering both Halo and Cannibalization impacts. Hence, this methodology enables correct calculation of the overall Revenue uplift due a given promotion.

Keywords: Halo, cannibalization, promotion, baseline, temporary price reduction, retail, elasticity, cross price elasticity, machine learning, random forest, linear regression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1231

Authors: Mohd Aftar Abu Bakar, Noratiqah Mohd Ariff, Abdul Aziz Jemain

Abstract:

Storm Event Analysis (SEA) provides a method to define rainfalls events as storms where each storm has its own amount and duration. By modelling daily probability of different types of storms, the onset, offset and cycle of rainfall seasons can be determined and investigated. Furthermore, researchers from the field of meteorology will be able to study the dynamical characteristics of rainfalls and make predictions for future reference. In this study, four categories of storms; short, intermediate, long and very long storms; are introduced based on the length of storm duration. Daily probability models of storms are built for these four categories of storms in Peninsular Malaysia. The models are constructed by using Bernoulli distribution and by applying linear regression on the first Fourier harmonic equation. From the models obtained, it is found that daily probability of storms at the Eastern part of Peninsular Malaysia shows a unimodal pattern with high probability of rain beginning at the end of the year and lasting until early the next year. This is very likely due to the Northeast monsoon season which occurs from November to March every year. Meanwhile, short and intermediate storms at other regions of Peninsular Malaysia experience a bimodal cycle due to the two inter-monsoon seasons. Overall, these models indicate that Peninsular Malaysia can be divided into four distinct regions based on the daily pattern for the probability of various storm events.

Keywords: Daily probability model, monsoon seasons, regions, storm events.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1589

Authors: Nattapong Techarattanased

Abstract:

The purposes of this research are to make comparisons in respect of the behaviors on the use of the services of metered taxi classified by the demographic factor and to study the influence of the recognition on service quality having the effect on usage behaviors of metered taxi services of consumers in Bangkok Metropolitan Areas. The samples used in this research were 400 metered taxi service users in Bangkok Metropolitan Areas and questionnaire was used as the tool for collecting the data. Analysis statistics are mean and multiple regression analysis. Results of the research revealed that the consumers recognize the overall quality of services in each aspect include tangible aspects of the service, responses to customers, assurance on the confidence, understanding and knowing of customers which is rated at the moderate level except the aspect of the assurance on the confidence and trustworthiness which are rated at a high level. For the result of hypothetical test, it is found that the quality in providing the services on the aspect of the assurance given to the customers has the effect on the usage behaviors of metered taxi services and the aspect of the frequency on the use of the services per month which in this connection. Such variable can forecast at one point nine percent (1.9%). In addition, quality in providing the services and the aspect of the responses to customers have the effect on the behaviors on the use of metered taxi services on the aspect of the expenses on the use of services per month which in this connection, such variable can forecast at two point one percent (2.1%).

Keywords: Consumer behavior, metered taxi, satisfaction, service quality.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3497

Authors: Nahla H. Alaswadko, Rayya A. Hassan, Bayar N. Mohammed

Abstract:

Empirical deterministic models have been developed to predict roughness progression of heavy duty spray sealed pavements for a dataset representing rural arterial roads. The dataset provides a good representation of the relevant network and covers a wide range of operating and environmental conditions. A sample with a large size of historical time series data for many pavement sections has been collected and prepared for use in multilevel regression analysis. The modelling parameters include road roughness as performance parameter and traffic loading, time, initial pavement strength, reactivity level of subgrade soil, climate condition, and condition of drainage system as predictor parameters. The purpose of this paper is to report the approaches adopted for models development and validation. The study presents multilevel models that can account for the correlation among time series data of the same section and to capture the effect of unobserved variables. Study results show that the models fit the data very well. The contribution and significance of relevant influencing factors in predicting roughness progression are presented and explained. The paper concludes that the analysis approach used for developing the models confirmed their accuracy and reliability by well-fitting to the validation data.

Keywords: Roughness progression, empirical model, pavement performance, heavy duty pavement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 746