Search results for: adaptive learning rate.

Authors: C. Pongcharoen, K. Kaiyavongand T. Satapanajaru

Abstract:

Theobjective of this study was to evaluate the optimal treatment condition of Fenton oxidation process to removal contaminant in soil slurry contaminated by petroleum hydrocarbons. This research studied somefactors that affect the removal efficiency of petroleum hydrocarbons in soil slurry including molar ratio of hydrogen peroxide (H2O2) to ferrous ion(Fe2+), pH condition and reaction time.The resultsdemonstrated that the optimum condition was that the molar ratio of H2O2:Fe3+ was 200:1,the pHwas 4.0and the rate of reaction was increasing rapidly from starting point to 7th hour and destruction kinetic rate (k) was 0.24 h-1. Approximately 96% of petroleum hydrocarbon was observed(initialtotal petroleum hydrocarbon (TPH) concentration = 70±7gkg-1)

Keywords: Contaminated soil, Fenton oxidation, Petroleumhydrocarbon, Remediation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2739

Authors: E. S. Gower, M. O. J. Hawksford

Abstract:

An algorithm for learning an overcomplete dictionary using a Cauchy mixture model for sparse decomposition of an underdetermined mixing system is introduced. The mixture density function is derived from a ratio sample of the observed mixture signals where 1) there are at least two but not necessarily more mixture signals observed, 2) the source signals are statistically independent and 3) the sources are sparse. The basis vectors of the dictionary are learned via the optimization of the location parameters of the Cauchy mixture components, which is shown to be more accurate and robust than the conventional data mining methods usually employed for this task. Using a well known sparse decomposition algorithm, we extract three speech signals from two mixtures based on the estimated dictionary. Further tests with additive Gaussian noise are used to demonstrate the proposed algorithm-s robustness to outliers.

Keywords: expectation-maximization, Pitman estimator, sparsedecomposition

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1957

Authors: C. Rogerson, E. Scott

Abstract:

The purpose of this paper is to consider the introduction of online courses to replace the current classroom-based staff training. The current training is practical, and must be completed before access to the financial computer system is authorized. The long term objective is to measure the efficacy, effectiveness and efficiency of the training, and to establish whether a transfer of knowledge back to the workplace has occurred. This paper begins with an overview explaining the importance of staff training in an evolving, competitive business environment and defines the problem facing this particular organization. A summary of the literature review is followed by a brief discussion of the research methodology and objective. The implementation of the alpha version of the online course is then described. This paper may be of interest to those seeking insights into, or new theory regarding, practical interventions of online learning in the real world.

Keywords: Computer-based courses, e-learning, online training, workplace training.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1686

Authors: Nikolaos Sariannidis, Grigoris Giannarakis, Nikolaos Litinas, Nikos Kartalis

Abstract:

This study investigates the relationship between 10 year bond value, Yen/U.S dollar exchange rate, non-farm payrolls (all employs) and crude oil to U.S. Dow Jones Sustainability Index. A GARCH model is used to test these relationships for the period January 1st 1999 to January 31st 2008 using monthly data. Results show that an increase of the 10 year bond and non farm payrolls (all employs) lead to an increase of the D.J.S.I returns. On the contrary the volatility of the Yen/U.S dollar exchange rates as well as the increase of crude oil returns has negative effects on the U.S D.J.S.I returns. This study aims at assisting investors to understand the influences certain macroeconomic indicators have on the companies- stock returns as reported by the D.J.S.I.

Keywords: Bond value, Corporate Social Responsibility, Crudeoil, D.J.S.I United States, Exchange rate, GARCH, Non-farmpayrolls.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1534

Authors: Simon Brown

Abstract:

Glomerular filtration rate (GFR) is a measure of kidney function. It is usually estimated from serum concentrations of cystatin C or creatinine although there has been considerable debate in the literature about (i) the best equation to use and (ii) the variability in the correlation between the concentrations of creatinine and cystatin C. The equations for GFR can be written in a general form and from these I calculate the error of the GFR estimates associated with analyte measurement error. These show that the error of the GFR estimates is such that it is not possible to distinguish between the equations over much of the concentration range of either analyte. The general forms of the equations are also used to derive an expression for the concentration of cystatin C as a function of the concentration of creatinine. This equation shows that these analyte concentrations are not linearly related. Clinical reports of cystatin C and creatinine concentration are consistent with the expression derived.

Keywords: creatinine, cystatin C, error analysis, glomerularfiltration rate, measurement error.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1528

Authors: Leila Vafajoo, Farhad Khorasheh, Mehrnoosh Hamzezadeh Nakhjavani, Moslem Fattahi

Abstract:

In the present study, a procedure was developed to determine the optimum reaction rate constants in generalized Arrhenius form and optimized through the Nelder-Mead method. For this purpose, a comprehensive mathematical model of a fixed bed reactor for dehydrogenation of heavy paraffins over Pt–Sn/Al2O3 catalyst was developed. Utilizing appropriate kinetic rate expressions for the main dehydrogenation reaction as well as side reactions and catalyst deactivation, a detailed model for the radial flow reactor was obtained. The reactor model composed of a set of partial differential equations (PDE), ordinary differential equations (ODE) as well as algebraic equations all of which were solved numerically to determine variations in components- concentrations in term of mole percents as a function of time and reactor radius. It was demonstrated that most significant variations observed at the entrance of the bed and the initial olefin production obtained was rather high. The aforementioned method utilized a direct-search optimization algorithm along with the numerical solution of the governing differential equations. The usefulness and validity of the method was demonstrated by comparing the predicted values of the kinetic constants using the proposed method with a series of experimental values reported in the literature for different systems.

Keywords: Dehydrogenation, Pt-Sn/Al2O3 Catalyst, Modeling, Nelder-Mead, Optimization

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2751

Authors: Mohammad H. Taheri, David J. Brown, Nasser Sherkat

Abstract:

Engagement is one of the most important factors in determining successful outcomes and deep learning in students. Existing approaches to detect student engagement involve periodic human observations that are subject to inter-rater reliability. Our solution uses real-time multimodal multisensor data labeled by objective performance outcomes to infer the engagement of students. The study involves four students with a combined diagnosis of cerebral palsy and a learning disability who took part in a 3-month trial over 59 sessions. Multimodal multisensor data were collected while they participated in a continuous performance test. Eye gaze, electroencephalogram, body pose, and interaction data were used to create a model of student engagement through objective labeling from the continuous performance test outcomes. In order to achieve this, a type of continuous performance test is introduced, the Seek-X type. Nine features were extracted including high-level handpicked compound features. Using leave-one-out cross-validation, a series of different machine learning approaches were evaluated. Overall, the random forest classification approach achieved the best classification results. Using random forest, 93.3% classification for engagement and 42.9% accuracy for disengagement were achieved. We compared these results to outcomes from different models: AdaBoost, decision tree, k-Nearest Neighbor, naïve Bayes, neural network, and support vector machine. We showed that using a multisensor approach achieved higher accuracy than using features from any reduced set of sensors. We found that using high-level handpicked features can improve the classification accuracy in every sensor mode. Our approach is robust to both sensor fallout and occlusions. The single most important sensor feature to the classification of engagement and distraction was shown to be eye gaze. It has been shown that we can accurately predict the level of engagement of students with learning disabilities in a real-time approach that is not subject to inter-rater reliability, human observation or reliant on a single mode of sensor input. This will help teachers design interventions for a heterogeneous group of students, where teachers cannot possibly attend to each of their individual needs. Our approach can be used to identify those with the greatest learning challenges so that all students are supported to reach their full potential.

Keywords: Affective computing in education, affect detection, continuous performance test, engagement, flow, HCI, interaction, learning disabilities, machine learning, multimodal, multisensor, physiological sensors, Signal Detection Theory, student engagement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1276

Authors: Kenneth M. Oba

Abstract:

This study investigated factors affecting the price of cement in Nigeria, and developed a mathematical model that can predict future cement prices. Cement is key in the Nigerian construction industry. The changes in price caused by certain factors could affect economic and infrastructural development; hence there is need for proper proactive planning. Secondary data were collected from published information on cement between 2014 and 2019. In addition, questionnaires were sent to some domestic cement retailers in Port Harcourt in Nigeria, to obtain the actual prices of cement between the same periods. The study revealed that the most critical factors affecting the price of cement in Nigeria are inflation rate, population growth rate, and Gross Domestic Product (GDP) growth rate. With the use of data from United Nations, International Monetary Fund, and Central Bank of Nigeria databases, amongst others, a Multiple Linear Regression model was formulated. The model was used to predict the price of cement for 2020-2025. The model was then tested with 95% confidence level, using a two-tailed t-test and an F-test, resulting in an R² of 0.8428 and R² (adj.) of 0.6069. The results of the tests and the correlation factors confirm the model to be fit and adequate. This study will equip researchers and stakeholders in the construction industry with information for planning, monitoring, and management of present and future construction projects that involve the use of cement.

Keywords: Cement price, multiple linear regression model, Nigerian Construction Industry, price prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 803

Authors: Georgi I. Petkov, Ivan I. Vankov, Yolina A. Petrova

Abstract:

A structure-based model of category learning and categorization at different levels of abstraction is presented. The model compares different structures and expresses their similarity implicitly in the forms of mappings. Based on this similarity, the model can categorize different targets either as members of categories that it already has or creates new categories. The model is novel using two threshold parameters to evaluate the structural correspondence. If the similarity between two structures exceeds the higher threshold, a new sub-ordinate category is created. Vice versa, if the similarity does not exceed the higher threshold but does the lower one, the model creates a new category on higher level of abstraction.

Keywords: Analogy-making, categorization, learning of categories, abstraction, hierarchical structure.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 791

Authors: M. Govindarajan

Abstract:

Text Mining is around applying knowledge discovery techniques to unstructured text is termed knowledge discovery in text (KDT), or Text data mining or Text Mining. In decision tree approach is most useful in classification problem. With this technique, tree is constructed to model the classification process. There are two basic steps in the technique: building the tree and applying the tree to the database. This paper describes a proposed C5.0 classifier that performs rulesets, cross validation and boosting for original C5.0 in order to reduce the optimization of error ratio. The feasibility and the benefits of the proposed approach are demonstrated by means of medial data set like hypothyroid. It is shown that, the performance of a classifier on the training cases from which it was constructed gives a poor estimate by sampling or using a separate test file, either way, the classifier is evaluated on cases that were not used to build and evaluate the classifier are both are large. If the cases in hypothyroid.data and hypothyroid.test were to be shuffled and divided into a new 2772 case training set and a 1000 case test set, C5.0 might construct a different classifier with a lower or higher error rate on the test cases. An important feature of see5 is its ability to classifiers called rulesets. The ruleset has an error rate 0.5 % on the test cases. The standard errors of the means provide an estimate of the variability of results. One way to get a more reliable estimate of predictive is by f-fold –cross- validation. The error rate of a classifier produced from all the cases is estimated as the ratio of the total number of errors on the hold-out cases to the total number of cases. The Boost option with x trials instructs See5 to construct up to x classifiers in this manner. Trials over numerous datasets, large and small, show that on average 10-classifier boosting reduces the error rate for test cases by about 25%.

Keywords: C5.0, Error Ratio, text mining, training data, test data.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2494

Authors: Rochelle Elva

Abstract:

Faculty in Higher Education today are faced with the challenge of convincing their students of the importance of the mastery of skills through learning. This is because most students often have a single motivation -to get high grades. If it appears that this goal will not be met, they lose their motivation and their academic efforts wane. This is true even for students in the competitive fields of STEM, including Computer Science majors. As educators, we have to understand our students and leverage what motivates them, to achieve our learning outcomes. This paper presents a case study that utilizes cognitive psychology’s Expectancy-Value Theory and Motivation Theory, to investigate the effect of sustained expectancy for success on students’ learning outcomes. In our case study, we explore how students’ motivation and persistence in their academic efforts are impacted by providing them with an unexpected path to success, which continues to the end of the semester. The approach was tested in an undergraduate computer science course with n = 56. The results of the study indicate that when presented with the real possibility of success, despite existing low grades, both low and high-scoring students persisted in their efforts to improve their performance. Their final grades were on average one place higher on the +/-letter grade scale, with some students scoring as high as three places above their predicted grade.

Keywords: Expectancy for success and persistence, motivation and performance, computer science education, motivation and performance in computer science.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 363

Authors: Jinwooung Kim, Jae-Hwan Jung, Seong-Jun Kim, Sung-Ah Kim

Abstract:

Because the building envelope has a significant impact on the operation and maintenance stage of the building, designing the facade considering the performance can improve the performance of the building and lower the maintenance cost of the building. In general, however, optimizing two or more performance factors confronts the limits of time and computational tools. The optimization phase typically repeats infinitely until a series of processes that generate alternatives and analyze the generated alternatives achieve the desired performance. In particular, as complex geometry or precision increases, computational resources and time are prohibitive to find the required performance, so an optimization methodology is needed to deal with this. Instead of directly analyzing all the alternatives in the optimization process, applying experimental techniques (heuristic method) learned through experimentation and experience can reduce resource waste. This study proposes and verifies a method to optimize the double envelope of a building composed of a perforated panel using machine learning to the design geometry and quantitative performance. The proposed method is to achieve the required performance with fewer resources by supplementing the existing method which cannot calculate the complex shape of the perforated panel.

Keywords: Building envelope, machine learning, perforated metal, multi-factor optimization, façade.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1233

Authors: Qiangqiang Xu, Xu Ji, Jingyang Han, Changchun Yang, Ming Li

Abstract:

Replacing of complex solar concentrating unit, this paper designs a solar heat-concentrating medium-temperature steam-generating system. Solar radiation is collected by using a large solar collecting and heat concentrating plate and is converged to the metal evaporating pipe with high efficient heat transfer. In the meantime, the heat loss is reduced by employing a double-glazed cover and other heat insulating structures. Thus, a high temperature is reached in the metal evaporating pipe. The influences of the system's structure parameters on system performance are analyzed. The steam production rate and the steam production under different solar irradiance, solar collecting and heat concentrating plate area, solar collecting and heat concentrating plate temperature and heat loss are obtained. The results show that when solar irradiance is higher than 600 W/m², the effective heat collecting area is 7.6 m² and the double-glazing cover is adopted, the system heat loss amount is lower than the solar irradiance value. The stable steam is produced in the metal evaporating pipe at 100 ℃, 110 ℃, and 120 ℃, respectively. When the average solar irradiance is about 896 W/m², and the steaming cumulative time is about 5 hours, the daily steam production of the system is about 6.174 kg. In a single day, the solar irradiance is larger at noon, thus the steam production rate is large at that time. Before 9:00 and after 16:00, the solar irradiance is smaller, and the steam production rate is almost 0.

Keywords: Heat concentrating, heat loss, medium temperature, solar steam production.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1112

Authors: Hazem M. Al-Mofleh, John E. Daniels, Joseph W. McKean

Abstract:

In this paper numerous robust fitting procedures are considered in estimating spatial variograms. In spatial statistics, the conventional variogram fitting procedure (non-linear weighted least squares) suffers from the same outlier problem that has plagued this method from its inception. Even a 3-parameter model, like the variogram, can be adversely affected by a single outlier. This paper uses the Hogg-Type adaptive procedures to select an optimal score function for a rank-based estimator for these non-linear models. Numeric examples and simulation studies will demonstrate the robustness, utility, efficiency, and validity of these estimates.

Keywords: Asymptotic relative efficiency, non-linear rank-based, robust, rank estimates, variogram.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1592

Authors: F. P. Chew, Z. Ishak

Abstract:

Malay Folk Literature in early childhood education served as an important agent in child development that involved emotional, thinking and language aspects. Up to this moment not much research has been carried out in Malaysia particularly in the teaching and learning aspects nor has there been an effort to publish “big books." Hence this article will discuss the stance taken by university undergraduate students, teachers and parents in evaluating Malay Folk Literature in early childhood education to be used as big books. The data collated and analyzed were taken from 646 respondents comprising 347 undergraduates and 299 teachers. Results of the study indicated that Malay Folk Literature can be absorbed into teaching and learning for early childhood with a mean of 4.25 while it can be in big books with a mean of 4.14. Meanwhile the highest mean value required for placing Malay Folk Literature genre as big books in early childhood education rests on exemplary stories for undergraduates with mean of 4.47; animal fables for teachers with a mean of 4.38. The lowest mean value of 3.57 is given to lipurlara stories. The most popular Malay Folk Literature found suitable for early children is Sang Kancil and the Crocodile, followed by Bawang Putih Bawang Merah. Pak Padir, Legends of Mahsuri, Origin of Malacca, and Origin of Rainbow are among the popular stories as well. Overall the undergraduates show a positive attitude toward all the items compared to teachers. The t-test analysis has revealed a non significant relationship between the undergraduate students and teachers with all the items for the teaching and learning of Malay Folk Literature.

Keywords: Big Book, Early Childhood Education, Malay FolkLiterature

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4316

Authors: Min-Chuan Huang, I-Ping Chen, Shu-Ying Chung

Abstract:

Taking the medical staff in an emergency ward of a medical center in Central Taiwan as the research object, the questionnaire data were collected by anonymous and voluntary reporting methods with structured questionnaires to explore organ donation’s actual situation, willingness, and attitude. Only 80 valid questionnaires were gathered. Of the 8 questions, the correct mean rate was 5.9 and the correct rate was 73.13%. According to the statistics of organ donation survey, only 8.7% have signed the consent for organ donation, 21.3% are willing but have not yet signed the consent for organ donation, 62.5% have not yet decided, and 7.5% are unwilling. The average total score (standard deviation) of attitude towards organ donation was 36.2. There is no significant difference between the demographic variables and the awareness and willingness of organ donation, but there is a significant correlation between marital status and the attitude toward organ donation.

Keywords: clinical psychology, organ donation, factors affecting psychological disorders, commitment

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1222

Authors: Åsa Smedberg

Abstract:

There are different kinds of online systems on the Internet for people who need support and develop new knowledge. Online communities and Ask the Expert systems are two such systems. In the health care area, the number of users of these systems has increased at a rapid pace. Interactions with medical trained experts take place online, and people with concerns about similar health problems come together to share experiences and advice. The systems are also used as storages and browsed for health information. Over the years, studies have been conducted of the usage of the different systems. However, in what ways the systems can be used together to enhance learning has not been explored. This paper presents results from a study of online health-communities and an Ask the Expert system for people who suffer from overweight. Differences and similarities in regards to posted issues and replies are discussed, and suggestions for a new holistic design of the two systems are presented.

Keywords: Learning, Ask the Expert, online community, healthcare, holistic, overweight.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1434

Authors: Feng Wang, Shencheng Ni, Shuying Han, Shanhong You

Abstract:

With the development of optical communication, optical performance monitoring (OPM) has received more and more attentions. Since optical signal-to-noise ratio (OSNR) is directly related to bit error rate (BER), it is one of the important parameters in optical networks. Recently, artificial neural network (ANN) has been greatly developed. ANN has strong learning and generalization ability. In this paper, a method of OSNR monitoring based on delay-tap sampling (DTS) and ANN has been proposed. DTS technique is used to extract the eigenvalues of the signal. Then, the eigenvalues are input into the ANN to realize the OSNR monitoring. The experiments of 10 Gb/s non-return-to-zero (NRZ) on–off keying (OOK), 20 Gb/s pulse amplitude modulation (PAM4) and 20 Gb/s return-to-zero (RZ) differential phase-shift keying (DPSK) systems are demonstrated for the OSNR monitoring based on the proposed method. The experimental results show that the range of OSNR monitoring is from 15 to 30 dB and the root-mean-square errors (RMSEs) for 10 Gb/s NRZ-OOK, 20 Gb/s PAM4 and 20 Gb/s RZ-DPSK systems are 0.36 dB, 0.45 dB and 0.48 dB respectively. The impact of chromatic dispersion (CD) on the accuracy of OSNR monitoring is also investigated in the three experimental systems mentioned above.

Keywords: Artificial neural network, ANN, chromatic dispersion, delay-tap sampling, optical signal-to-noise ratio, OSNR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 722

Authors: Rajaram Kr. Gupta, Bhupendra Kumar, T. V. K. Gupta, D. S. Ramteke

Abstract:

Machining of hard materials is a recent technology for direct production of work-pieces. The primary challenge in machining these materials is selection of cutting tool inserts which facilitates an extended tool life and high-precision machining of the component. These materials are widely for making precision parts for the aerospace industry. Nickel-based alloys are typically used in extreme environment applications where a combination of strength, corrosion resistance and oxidation resistance material characteristics are required. The present paper reports the theoretical and experimental investigations carried out to understand the influence of machining parameters on the response parameters. Considering the basic machining parameters (speed, feed and depth of cut) a study has been conducted to observe their influence on material removal rate, surface roughness, cutting forces and corresponding tool wear. Experiments are designed and conducted with the help of Central Composite Rotatable Design technique. The results reveals that for a given range of process parameters, material removal rate is favorable for higher depths of cut and low feed rate for cutting forces. Low feed rates and high values of rotational speeds are suitable for better finish and higher tool life.

Keywords: Speed, feed, depth of cut, roughness, cutting force, flank wear.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1980

Authors: A.R. Ismail, M. R. A. Rani, Z. K. M. Makhbul, M. J. M. Nor, M. N. A. Rahman

Abstract:

The environmental factors such as temperature and relative humidity are very contribute to the effect of comfort, health, performance and worker productivity. To ensure an ergonomics work environment, it is possible to require a specific attention especially in industries. The aim of this study is to show the effect of temperature and relative humidity on worker productivity in automotive industry by taking a workstation in an automotive plant as the location to conduct the study. From the analysis of the data, there were relationship between temperature and relative humidity on worker productivity. Mathematical equation to represent the relationship between temperatures and relative humidity on the production rate is modelled. From the equation model, the production rate for the workstation can be predicted base on the value of temperature and relative humidity.

Keywords: WBGT, Relative Humidity, Comfort, Productivity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2462

Authors: Hai Huu Le, Paul Junor, Moshi Geso, Graeme O’Keefe

Abstract:

In this paper, the authors propose a personal wearable directionally-sensitive radiation dosimeter using multiple semiconductor CdZnTe detectors. The proposed dosimeter not only measures the real-time dose rate but also provide the direction of the radioactive source. A linear relationship between radioactive source direction and the radiation intensity measured by each detectors is established and an equation to determine the source direction is derived by the authors. The efficiency and accuracy of the proposed dosimeter is verified by simulation using Geant4 package. Results have indicated that in a measurement duration of about 7 seconds, the proposed dosimeter was able to estimate the direction of a 10μCi 137/55Cs radioactive source to within 2 degrees.

Keywords: Dose rate, Geant4 package, radiation detectors, radioactive source direction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1204

Authors: Nadia Hmad, Tony Allen

Abstract:

This paper presents an ESN-based Arabic phoneme recognition system trained with supervised, forced and combined supervised/forced supervised learning algorithms. Mel-Frequency Cepstrum Coefficients (MFCCs) and Linear Predictive Code (LPC) techniques are used and compared as the input feature extraction technique. The system is evaluated using 6 speakers from the King Abdulaziz Arabic Phonetics Database (KAPD) for Saudi Arabia dialectic and 34 speakers from the Center for Spoken Language Understanding (CSLU2002) database of speakers with different dialectics from 12 Arabic countries. Results for the KAPD and CSLU2002 Arabic databases show phoneme recognition performances of 72.31% and 38.20% respectively.

Keywords: Arabic phonemes recognition, echo state networks (ESNs), neural networks (NNs), supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2413

Authors: Arvind Kumar, Rajoo Pandey

Abstract:

For broadband wireless mobile communication systems the orthogonal frequency division multiplexing (OFDM) is a suitable modulation scheme. The frequency offset between transmitter and receiver local oscillator is main drawback of OFDM systems, which causes intercarrier interference (ICI) in the subcarriers of the OFDM system. This ICI degrades the bit error rate (BER) performance of the system. In this paper an improved self-ICI cancellation scheme is proposed to improve the system performance. The proposed scheme is based on discrete Fourier transform-inverse discrete Fourier transform (DFT-IDFT). The simulation results show that there is satisfactory improvement in the bit error rate (BER) performance of the present scheme.

Keywords: OFDM, Intercarrier Interference, InterferenceCoefficients, DFT based Self-ICI Cancellation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1661

Authors: Abdullah H. Özcan, Dilara Hisar, Yetkin Sayar, Cem Ünsalan

Abstract:

In this study, an automated building and tree detection method is proposed using DSM data and true orthophoto image. A multiscale matched filtering is used on DSM data. Therefore, first watershed transform is applied. Then, Otsu’s thresholding method is used as an adaptive threshold to segment each watershed region. Detected objects are masked with NDVI to separate buildings and trees. The proposed method is able to detect buildings and trees without entering any elevation threshold. We tested our method on ISPRS semantic labeling dataset and obtained promising results.

Keywords: Building detection, tree detection, matched filtering, multiscale, local maximum filtering, watershed segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 557

Authors: Justin D. Olmanson, Katrina S. Kennett, Bill Cope

Abstract:

In educational technology, the idea of innovation is usually tethered to contemporary technological inventions and emerging technologies. Yet, using long-known technologies in ways that are pedagogically or experimentially new can reposition them as emerging educational technologies. In this study we explore how a subtle pivot in pedagogical thinking led to an innovative education technology. We describe the design and implementation of an online writing tool that scaffolds students in the evaluation of their own informational texts. We think about how pathways to innovation can emerge from pivots, namely a leveraging of longstanding practices in novel ways has the potential to cultivate new opportunities for learning. We first unpack Infowriter in terms of its design, then we describe some results of a study in which we implemented an intervention which included our designed application.

Keywords: Design, innovation, learning, technology, writing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1698

Authors: Sh. Khalilarya, S. Jafarmadar, H. Khatamnezhad, Gh. Javadirad, M. Pourfallah

Abstract:

One promising way to achieve low temperature combustion regime is the use of a large amount of cooled EGR. In this paper, the effect of injection timing on low temperature combustion process and emissions were investigated via three dimensional computational fluid dynamics (CFD) procedures in a DI diesel engine using high EGR rates. The results show when increasing EGR from low levels to levels corresponding to reduced temperature combustion, soot emission after first increasing, is decreased beyond 40% EGR and get the lowest value at 58% EGR rate. Soot and NOx emissions are simultaneously decreased at advanced injection timing before 20.5 ºCA BTDC in conjunction with 58% cooled EGR rate in compared to baseline case.

Keywords: Diesel Engine, Low Temperature Combustion, High Cooled EGR Rates, Combustion, Emissions

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2040

Authors: Suk-Hyun Yu, Heeyong Kwon

Abstract:

Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.

Keywords: AI, air quality prediction, neural networks, pattern recognition, PM-10.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 832

Authors: Snežana T. Tanasković, Sonja M. Gvozdenac, Branka D. Popović, Vesna M. Đurović, Matthias Erb

Abstract:

Western corn rootworm – WCR (Diabrotica virgifera sp.virgifera, Coleoptera, Chrysomelidae) is economically the most important pest of maize worldwide. WCR natural population is already very abundant on Serbian fields, and keeps increasing each year. Tolerance is recognized by larger root size and bigger root regrowth. Severe larval injuries cause lack of compensatory regrowth and lead to reduction of plant growth and yield. The aim of this research was to evaluate tolerance of commercial Serbian maize hybrid NS 640, under natural WCR infestation and under conditions of artificial infestation, and to obtain the information about its tolerance to WCR larval feeding in two consecutive years. Field experiments were conducted in 2015 and 2016, in Bečej (Vojvodina province, Serbia). In experimental field, 96 plants were selected, marked and arranged in 48 pairs. Each pair represented two plants. The first plant was artificially infested with 4 mL WCR egg suspension in agar (550 eggs plant^-1) in the root zone (D plant). The second plant represented control plant (C plant) with injection of 4 mL distilled water in root zone. The experimental field was inspected weekly. A hybrid tolerance was assessed based on root injury level and root mass. Root injury was rated using the Node-Injury Scale 1-6, during the last field inspection (September – October). Comparing the root injuries on D and C plants in 2015, more severe damages were recorded on D plants (12 plants - rate 5 and 17 plants - rate 6) compared to C plants (2 plants - rate 5 and 8 plants - rate 6). Also, the highest number of plants with healthy roots (rate 1), was registered in the control (25 plants), while only 4 D plants were rated as injury level 1. In 2016, root injuries caused by WCR larvae on D and C plants did not differ significantly. The reason is the difference in climatic conditions between the years. The 2015 was extremely dry and more suitable for WCR larval development and movement in the soil, compared to 2016. Thus, more severe damages appeared on artificially infested plants (D plants). Root mass was in strong correlation with the level of root injury, but did not differ significantly between D and C plants, in both years.

Keywords: D. v. virgifera, maize, root injury, tolerance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 885

Authors: F. Lazzeri, I. Reiter

Abstract:

Energy production optimization has been traditionally very important for utilities in order to improve resource consumption. However, load forecasting is a challenging task, as there are a large number of relevant variables that must be considered, and several strategies have been used to deal with this complex problem. This is especially true also in microgrids where many elements have to adjust their performance depending on the future generation and consumption conditions. The goal of this paper is to present a solution for short-term load forecasting in microgrids, based on three machine learning experiments developed in R and web services built and deployed with different components of Cortana Intelligence Suite: Azure Machine Learning, a fully managed cloud service that enables to easily build, deploy, and share predictive analytics solutions; SQL database, a Microsoft database service for app developers; and PowerBI, a suite of business analytics tools to analyze data and share insights. Our results show that Boosted Decision Tree and Fast Forest Quantile regression methods can be very useful to predict hourly short-term consumption in microgrids; moreover, we found that for these types of forecasting models, weather data (temperature, wind, humidity and dew point) can play a crucial role in improving the accuracy of the forecasting solution. Data cleaning and feature engineering methods performed in R and different types of machine learning algorithms (Boosted Decision Tree, Fast Forest Quantile and ARIMA) will be presented, and results and performance metrics discussed.

Keywords: Time-series, features engineering methods for forecasting, energy demand forecasting, Azure machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1305

Authors: Jianhua Wang, Yan Yu

Abstract:

This paper presents an intrusion detection system of hybrid neural network model based on RBF and Elman. It is used for anomaly detection and misuse detection. This model has the memory function .It can detect discrete and related aggressive behavior effectively. RBF network is a real-time pattern classifier, and Elman network achieves the memory ability for former event. Based on the hybrid model intrusion detection system uses DARPA data set to do test evaluation. It uses ROC curve to display the test result intuitively. After the experiment it proves this hybrid model intrusion detection system can effectively improve the detection rate, and reduce the rate of false alarm and fail.

Keywords: RBF, Elman, anomaly detection, misuse detection, hybrid neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2335