Search results for: learning coefficients

Authors: Amir Rastegarnia, Mohammad Ali Tinati, Azam Khalili

Abstract:

In this paper we consider the issue of distributed adaptive estimation over sensor networks. To deal with more realistic scenario, different variance for observation noise is assumed for sensors in the network. To solve the problem of different variance of observation noise, the proposed method is divided into two phases: I) Estimating each sensor-s observation noise variance and II) using the estimated variances to obtain the desired parameter. Our proposed algorithm is based on a diffusion least mean square (LMS) implementation with linear combiner model. In the proposed algorithm, the step-size parameter the coefficients of linear combiner are adjusted according to estimated observation noise variances. As the simulation results show, the proposed algorithm considerably improves the diffusion LMS algorithm given in literature.

Keywords: Adaptive filter, distributed estimation, sensor network, diffusion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1868

Authors: Karima Siham Aoubid, Mohamed Boulemden

Abstract:

The development of the signal compression algorithms is having compressive progress. These algorithms are continuously improved by new tools and aim to reduce, an average, the number of bits necessary to the signal representation by means of minimizing the reconstruction error. The following article proposes the compression of Arabic speech signal by a hybrid method combining the wavelet transform and the linear prediction. The adopted approach rests, on one hand, on the original signal decomposition by ways of analysis filters, which is followed by the compression stage, and on the other hand, on the application of the order 5, as well as, the compression signal coefficients. The aim of this approach is the estimation of the predicted error, which will be coded and transmitted. The decoding operation is then used to reconstitute the original signal. Thus, the adequate choice of the bench of filters is useful to the transform in necessary to increase the compression rate and induce an impercevable distortion from an auditive point of view.

Keywords: Compression, linear prediction analysis, multiresolution analysis, speech signal.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1341

Authors: Khalid A. Kaabneh

Abstract:

This paper introduces and studies new indexing techniques for content-based queries in images databases. Indexing is the key to providing sophisticated, accurate and fast searches for queries in image data. This research describes a new indexing approach, which depends on linear modeling of signals, using bases for modeling. A basis is a set of chosen images, and modeling an image is a least-squares approximation of the image as a linear combination of the basis images. The coefficients of the basis images are taken together to serve as index for that image. The paper describes the implementation of the indexing scheme, and presents the findings of our extensive evaluation that was conducted to optimize (1) the choice of the basis matrix (B), and (2) the size of the index A (N). Furthermore, we compare the performance of our indexing scheme with other schemes. Our results show that our scheme has significantly higher performance.

Keywords: Axial Projection, images, indexing, multimedia database, searching.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1390

Authors: Shigeaki Sakurai, Ryohei Orihara

Abstract:

This paper proposes an improvement method of classification efficiency in a classification model. The model is used in a risk search system and extracts specific labels from articles posted at bulletin board sites. The system can analyze the important discussions composed of the articles. The improvement method introduces ensemble learning methods that use multiple classification models. Also, it introduces expressions related to the specific labels into generation of word vectors. The paper applies the improvement method to articles collected from three bulletin board sites selected by users and verifies the effectiveness of the improvement method.

Keywords: Text mining, Risk search system, Corporate reputation, Bulletin board site, Ensemble learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1328

Authors: Ratchakit Sakuldee, Somkait Udomhunsakul

Abstract:

Measurement of the quality of image compression is important for image processing application. In this paper, we propose an objective image quality assessment to measure the quality of gray scale compressed image, which is correlation well with subjective quality measurement (MOS) and least time taken. The new objective image quality measurement is developed from a few fundamental of objective measurements to evaluate the compressed image quality based on JPEG and JPEG2000. The reliability between each fundamental objective measurement and subjective measurement (MOS) is found. From the experimental results, we found that the Maximum Difference measurement (MD) and a new proposed measurement, Structural Content Laplacian Mean Square Error (SCLMSE), are the suitable measurements that can be used to evaluate the quality of JPEG200 and JPEG compressed image, respectively. In addition, MD and SCLMSE measurements are scaled to make them equivalent to MOS, given the rate of compressed image quality from 1 to 5 (unacceptable to excellent quality).

Keywords: JPEG, JPEG2000, objective image quality measurement, subjective image quality measurement, correlation coefficients.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2191

Authors: Maxence Queyrel, Edi Prifti, Alexandre Templier, Jean-Daniel Zucker

Abstract:

Analysis of the human microbiome using metagenomic sequencing data has demonstrated high ability in discriminating various human diseases. Raw metagenomic sequencing data require multiple complex and computationally heavy bioinformatics steps prior to data analysis. Such data contain millions of short sequences read from the fragmented DNA sequences and stored as fastq files. Conventional processing pipelines consist in multiple steps including quality control, filtering, alignment of sequences against genomic catalogs (genes, species, taxonomic levels, functional pathways, etc.). These pipelines are complex to use, time consuming and rely on a large number of parameters that often provide variability and impact the estimation of the microbiome elements. Training Deep Neural Networks directly from raw sequencing data is a promising approach to bypass some of the challenges associated with mainstream bioinformatics pipelines. Most of these methods use the concept of word and sentence embeddings that create a meaningful and numerical representation of DNA sequences, while extracting features and reducing the dimensionality of the data. In this paper we present an end-to-end approach that classifies patients into disease groups directly from raw metagenomic reads: metagenome2vec. This approach is composed of four steps (i) generating a vocabulary of k-mers and learning their numerical embeddings; (ii) learning DNA sequence (read) embeddings; (iii) identifying the genome from which the sequence is most likely to come and (iv) training a multiple instance learning classifier which predicts the phenotype based on the vector representation of the raw data. An attention mechanism is applied in the network so that the model can be interpreted, assigning a weight to the influence of the prediction for each genome. Using two public real-life data-sets as well a simulated one, we demonstrated that this original approach reaches high performance, comparable with the state-of-the-art methods applied directly on processed data though mainstream bioinformatics workflows. These results are encouraging for this proof of concept work. We believe that with further dedication, the DNN models have the potential to surpass mainstream bioinformatics workflows in disease classification tasks.

Keywords: Metagenomics, phenotype prediction, deep learning, embeddings, multiple instance learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 919

Authors: A. T. Zaki

Abstract:

The flipped classroom approach as a mode of blended learning was formally introduced to students of the English language modules at the British University in Egypt (BUE) at the start of the academic year 2015/2016. This paper aims to study the impact of the flipped classroom approach after three semesters of implementation. It will restrict itself to the examination of students’ achievement rates, student satisfaction, and how different student cohorts have benefited differently from the flipped practice. The paper concludes with recommendations of how the experience can be further developed.

Keywords: Achievement rates, developmental experience, Egypt, flipped classroom, higher education, student cohorts, student satisfaction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1087

Authors: Niloufar Ghoreishi, Ali Nekouzadeh

Abstract:

The stability of the flight during maneuvering and in response to probable perturbations is one of the most essential features of an aircraft that should be analyzed and designed for. In this study, we derived the non-linear governing equations of aircraft dynamics during the climb/descend phase and simulated a model aircraft. The corresponding force and moment dimensionless coefficients of the model and their variations with elevator angle and other relevant aerodynamic parameters were measured experimentally. The short-period mode and phugoid mode response were simulated by solving the governing equations numerically and then compared with the desired stability parameters for the particular level, category, and class of the aircraft model. To meet the target stability, a controller was designed and used. This resulted in significant improvement in the stability parameters of the flight.

Keywords: Flight stability, phugoid mode, short period mode, climb phase, damping coefficient.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 207

Authors: Amogh Katti, J. Sai Asritha, D. Nivedh, M. Kalyan Srinivas, B. Somnath Chakravarthi

Abstract:

Today's modern education system uses Learning Management System (LMS) portals for the scoring and grading of student performances, to maintain student records, and teachers are instructed to accept assignments through online submissions of .pdf, .doc, .ppt, etc. There is a risk of data tampering in the traditional portals; we will apply the Blockchain model instead of this traditional model to avoid data tampering and also provide a decentralized mechanism for overall fairness. Blockchain technology is a better and also recommended model because of the following features: consensus mechanism, decentralized system, cryptographic encryption, smart contracts, Ethereum blockchain. The proposed system ensures data integrity and tamper-proof assignment submission and grading, which will be helpful for both students and also educators.

Keywords: Education technology, learning management system, decentralized applications, blockchain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 178

Authors: Yaojun Wang, Yaoqing Wang

Abstract:

Stock selection is an important decision-making problem. Many machine learning and data mining technologies are employed to build automatic stock-selection system. A profitable stock-selection system should consider the stock’s investment value and the market timing. In this paper, we present a hybrid system including both engage for stock selection. This system uses a case-based reasoning (CBR) model to execute the stock classification, uses a decision-tree model to help with market timing and stock selection. The experiments show that the performance of this hybrid system is better than that of other techniques regarding to the classification accuracy, the average return and the Sharpe ratio.

Keywords: Case-based reasoning, decision tree, stock selection, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1712

Authors: Rustam Asnawi, Wan Fatimah Wan Ahmad

Abstract:

Currently electronic slide (e-slide) is one of the most common styles in educational presentation. Unfortunately, the utilization of e-slide for the visually impaired is uncommon since they are unable to see the content of such e-slides which are usually composed of text, images and animation. This paper proposes a model for presenting e-slide in multimodal presentation i.e. using conventional slide concurrent with voicing, in both languages Malay and English. At the design level, live multimedia presentation concept is used, while at the implementation level several components are used. The text content of each slide is extracted using COM component, Microsoft Speech API for voicing the text in English language and the text in Malay language is voiced using dictionary approach. To support the accessibility, an auditory user interface is provided as an additional feature. A prototype of such model named as VSlide has been developed and introduced.

Keywords: presentation, self-learning, slide, visually impaired

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1572

Authors: Tatjana Eitrich, Bruno Lang

Abstract:

This work deals with aspects of support vector learning for large-scale data mining tasks. Based on a decomposition algorithm that can be run in serial and parallel mode we introduce a data transformation that allows for the usage of an expensive generalized kernel without additional costs. In order to speed up the decomposition algorithm we analyze the problem of working set selection for large data sets and analyze the influence of the working set sizes onto the scalability of the parallel decomposition scheme. Our modifications and settings lead to improvement of support vector learning performance and thus allow using extensive parameter search methods to optimize classification accuracy.

Keywords: Support Vector Machines, Shared Memory Parallel Computing, Large Data

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1580

Authors: M-J. Huang, C-J. Huang, L-C. Chen

Abstract:

In a previously developed fast vortex method, the diffusion of the vortex sheet induced at the solid wall by the no-slip boundary conditions was modeled according to the approximation solution of Koumoutsakos and converted into discrete blobs in the vicinity of the wall. This scheme had been successfully applied to a simulation of the flow induced with an impulsively initiated circular cylinder. In this work, further modifications on this vortex method are attempted, including replacing the approximation solution by the boundary-element-method solution, incorporating a new algorithm for handling the over-weak vortex blobs, and diffusing the vortex sheet circulation in a new way suitable for high-curvature solid bodies. The accuracy is thus largely improved. The predictions of lift and drag coefficients for a uniform flow past a NASA airfoil agree well with the existing literature.

Keywords: Resurrected core-spreading vortex method, Boundaryelement method, Vortex sheet, Over-weak vortex blobs.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1419

Authors: Omnia F. Elkommos

Abstract:

In the course of teaching stylistics to undergraduate students of the Department of English Language and Literature, Faculty of Arts and Humanities, the linguistic tool kit of theories comes in handy and useful for the better understanding of the different literary genres: Poetry, drama, and short stories. In the present paper, a model of teaching of stylistics is compiled and suggested. It is a collaborative group project technique for use in the undergraduate diverse specialisms (Literature, Linguistics and Translation tracks) class. Students initially are introduced to the different linguistic tools and theories suitable for each literary genre. The second step is to apply these linguistic tools to texts. Students are required to watch videos performing the poems or play, for example, and search the net for interpretations of the texts by other authorities. They should be using a template (prepared by the researcher) that has guided questions leading students along in their analysis. Finally, a practical analysis would be written up using the practical analysis essay template (also prepared by the researcher). As per collaborative learning, all the steps include activities that are student-centered addressing differentiation and considering their three different specialisms. In the process of selecting the proper tools, the actual application and analysis discussion, students are given tasks that request their collaboration. They also work in small groups and the groups collaborate in seminars and group discussions. At the end of the course/module, students present their work also collaboratively and reflect and comment on their learning experience. The module/course uses a drama play that lends itself to the task: ‘The Bond’ by Amy Lowell and Robert Frost. The project results in an interpretation of its theme, characterization and plot. The linguistic tools are drawn from pragmatics, and discourse analysis among others.

Keywords: Applied linguistic theories, collaborative learning, cooperative principle, discourse analysis, drama analysis, group project, online acting performance, pragmatics, speech act theory, stylistics, technology enhanced learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1085

Authors: Debashish Panda, Kannan A.

Abstract:

Equilibrium and rate based models have been applied in the simulation of methyl tertiary-butyl ether (MTBE) synthesis through reactive distillation. Temperature and composition profiles were compared for both the models and found that both the profiles trends, though qualitatively similar are significantly different quantitatively. In the rate based method (RBM), multicomponent mass transfer coefficients have been incorporated to describe interphase mass transfer. MTBE mole fraction in the bottom stream is found to be 0.9914 in the Equilibrium Model (EQM) and only 0.9904 for RBM when the same column configuration was preserved. The individual tray efficiencies were incorporated in the EQM and simulations were carried out. Dynamic simulation have been also carried out for the two column configurations and compared.

Keywords: Aspen Plus, equilibrium stage model, methyl tertiary-butyl ether, rate based model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4916

Authors: Alexandros Leontitsis, Archana P. Sangole

Abstract:

This article presents a short discussion on optimum neighborhood size selection in a spherical selforganizing feature map (SOFM). A majority of the literature on the SOFMs have addressed the issue of selecting optimal learning parameters in the case of Cartesian topology SOFMs. However, the use of a Spherical SOFM suggested that the learning aspects of Cartesian topology SOFM are not directly translated. This article presents an approach on how to estimate the neighborhood size of a spherical SOFM based on the data. It adopts the L-curve criterion, previously suggested for choosing the regularization parameter on problems of linear equations where their right-hand-side is contaminated with noise. Simulation results are presented on two artificial 4D data sets of the coupled Hénon-Ikeda map.

Keywords: Parameter estimation, self-organizing feature maps, spherical topology.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1526

Authors: Watcharawalee Lertlum, Borworn Papasratorn

Abstract:

Conventional WBL is effective for meaningful student, because rote student learn by repeating without thinking or trying to understand. It is impossible to have full benefit from conventional WBL. Understanding of rote student-s intention and what influences it becomes important. Poorly designed user interface will discourage rote student-s cultivation and intention to use WBL. Thus, user interface design is an important factor especially when WBL is used as comprehensive replacement of conventional teaching. This research proposes the influencing factors that can enhance student-s intention to use the system. The enhanced TAM is used for evaluating the proposed factors. The research result points out that factors influencing rote student-s intention are Perceived Usefulness of Homepage Content Structure, Perceived User Friendly Interface, Perceived Hedonic Component, and Perceived (homepage) Visual Attractiveness.

Keywords: E-learning, Web-Based learning, Intention to use, Rote student, Influencing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1628

Authors: A. Kumar, G. K. Singh, R. S. Anand

Abstract:

In this paper, various algorithms for designing quadrature mirror filter are reviewed and a new algorithm is presented for the design of near perfect reconstruction quadrature mirror filter bank. In the proposed algorithm, objective function is formulated using the perfect reconstruction condition or magnitude response condition of prototype filter at frequency (ω = 0.5π) in ideal condition. The cutoff frequency is iteratively changed to adjust the filters coefficients using optimization algorithm. The performances of the proposed algorithm are evaluated in term of computation time, reconstruction error and number of iterations. The design examples illustrate that the proposed algorithm is superior in term of peak reconstruction error, computation time, and number of iterations. The proposed algorithm is simple, easy to implement, and linear in nature.

Keywords: Aliasing cancellations filter bank, Filter banks, quadrature mirror filter (QMF), subband coding.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2533

Authors: Rachel Baruch

Abstract:

This article describes the implementation of an experimental model for teaching ICT tools and digital environments in teachers training college. In most educational systems in the Western world, new programs were developed in order to bridge the digital gap between teachers and students. In spite of their achievements, these programs are limited due to several factors: The teachers in the schools implement new methods incorporating technological tools into the curriculum, but meanwhile the technology changes and advances. The interface of tools changes frequently, some tools disappear and new ones are invented. These conditions require an experimental model of training the pre-service teachers. The appropriate method for instruction within the domain of ICT tools should be based on exposing the learners to innovations, helping them to gain experience, teaching them how to deal with challenges and difficulties on their own, and training them. This study suggests some principles for this approach and describes step by step the implementation of this model.

Keywords: ICT tools, e-learning, pre-service teachers.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1096

Authors: Farhad Sedaghati, Shahram Pezeshk

Abstract:

Regional variations in strong ground motions for the Iranian Plateau have been investigated by using a simple statistical method called Analysis of Variance (ANOVA). In this respect, a large database consisting of 1157 records occurring within the Iranian Plateau with moment magnitudes of greater than or equal to 5 and Joyner-Boore distances up to 200 km has been considered. Geometric averages of horizontal peak ground accelerations (PGA) as well as 5% damped linear elastic response spectral accelerations (SA) at periods of 0.2, 0.5, 1.0, and 2.0 sec are used as strong motion parameters. The initial database is divided into two different datasets, for Northern Iran (NI) and Central and Southern Iran (CSI). The comparison between strong ground motions of these two regions reveals that there is no evidence for significant differences; therefore, data from these two regions may be combined to estimate the unknown coefficients of attenuation relationships.

Keywords: ANOVA, attenuation relationships, Iranian Plateau, PGA, regional variation, SA, strong ground motion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1299

Authors: Guy Leshem, Ya'acov Ritov

Abstract:

Traffic Management and Information Systems, which rely on a system of sensors, aim to describe in real-time traffic in urban areas using a set of parameters and estimating them. Though the state of the art focuses on data analysis, little is done in the sense of prediction. In this paper, we describe a machine learning system for traffic flow management and control for a prediction of traffic flow problem. This new algorithm is obtained by combining Random Forests algorithm into Adaboost algorithm as a weak learner. We show that our algorithm performs relatively well on real data, and enables, according to the Traffic Flow Evaluation model, to estimate and predict whether there is congestion or not at a given time on road intersections.

Keywords: Machine Learning, Boosting, Classification, TrafficCongestion, Data Collecting, Magnetic Loop Detectors, SignalizedIntersections, Traffic Signal Timing Optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3915

Authors: Bruno Trstenjak, Dzenana Donko

Abstract:

Data mining and classification of objects is the process of data analysis, using various machine learning techniques, which is used today in various fields of research. This paper presents a concept of hybrid classification model improved with the expert knowledge. The hybrid model in its algorithm has integrated several machine learning techniques (Information Gain, K-means, and Case-Based Reasoning) and the expert’s knowledge into one. The knowledge of experts is used to determine the importance of features. The paper presents the model algorithm and the results of the case study in which the emphasis was put on achieving the maximum classification accuracy without reducing the number of features.

Keywords: Case based reasoning, classification, expert's knowledge, hybrid model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1421

Authors: Refaat M Mohamed, Ayman El-Baz, Aly A. Farag

Abstract:

This paper introduces a novel approach to estimate the clique potentials of Gibbs Markov random field (GMRF) models using the Support Vector Machines (SVM) algorithm and the Mean Field (MF) theory. The proposed approach is based on modeling the potential function associated with each clique shape of the GMRF model as a Gaussian-shaped kernel. In turn, the energy function of the GMRF will be in the form of a weighted sum of Gaussian kernels. This formulation of the GMRF model urges the use of the SVM with the Mean Field theory applied for its learning for estimating the energy function. The approach has been tested on synthetic texture images and is shown to provide satisfactory results in retrieving the synthesizing parameters.

Keywords: Image Modeling, MRF, Parameters Estimation, SVM Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1639

Authors: John N. Ellinas, Panagiotis Kenterlis

Abstract:

The efficiency of an image watermarking technique depends on the preservation of visually significant information. This is attained by embedding the watermark transparently with the maximum possible strength. The current paper presents an approach for still image digital watermarking in which the watermark embedding process employs the wavelet transform and incorporates Human Visual System (HVS) characteristics. The sensitivity of a human observer to contrast with respect to spatial frequency is described by the Contrast Sensitivity Function (CSF). The strength of the watermark within the decomposition subbands, which occupy an interval on the spatial frequencies, is adjusted according to this sensitivity. Moreover, the watermark embedding process is carried over the subband coefficients that lie on edges where distortions are less noticeable. The experimental evaluation of the proposed method shows very good results in terms of robustness and transparency.

Keywords: Image watermarking, wavelet transform, human visual system, contrast sensitivity function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2094

Authors: Heide Lukosch, Roy Van Bussel, Sebastiaan Meijer

Abstract:

Serious games have proven to be a useful instrument to engage learners and increase motivation. Nevertheless, a broadly accepted, practical instructional design approach to serious games does not exist. In this paper, we introduce the use of an instructional design model that has not been applied to serious games yet, and has some advantages compared to other design approaches. We present the case of mechanics mechatronics education to illustrate the close match with timing and role of knowledge and information that the instructional design model prescribes and how this has been translated to a rigidly structured game design. The structured approach answers the learning needs of applicable knowledge within the target group. It combines advantages of simulations with strengths of entertainment games to foster learner-s motivation in the best possible way. A prototype of the game will be evaluated along a well-respected evaluation method within an advanced test setting including test and control group.

Keywords: Serious Gaming, Simulation, Complex Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1772

Authors: Ghada A. Alfattni

Abstract:

Analysing unbalanced datasets is one of the challenges that practitioners in machine learning field face. However, many researches have been carried out to determine the effectiveness of the use of the synthetic minority over-sampling technique (SMOTE) to address this issue. The aim of this study was therefore to compare the effectiveness of the SMOTE over different models on unbalanced datasets. Three classification models (Logistic Regression, Support Vector Machine and Nearest Neighbour) were tested with multiple datasets, then the same datasets were oversampled by using SMOTE and applied again to the three models to compare the differences in the performances. Results of experiments show that the highest number of nearest neighbours gives lower values of error rates. 

Keywords: Imbalanced datasets, SMOTE, machine learning, logistic regression, support vector machine, nearest neighbour.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1318

Authors: Ion Smeureanu, Marian Dardala, Adriana Reveiu

Abstract:

The new programming technologies allow for the creation of components which can be automatically or manually assembled to reach a new experience in knowledge understanding and mastering or in getting skills for a specific knowledge area. The project proposes an interactive framework that permits the creation, combination and utilization of components that are specific to mathematical training in high schools. The main framework-s objectives are: • authoring lessons by the teacher or the students; all they need are simple operating skills for Equation Editor (or something similar, or Latex); the rest are just drag & drop operations, inserting data into a grid, or navigating through menus • allowing sonorous presentations of mathematical texts and solving hints (easier understood by the students) • offering graphical representations of a mathematical function edited in Equation • storing of learning objects in a database • storing of predefined lessons (efficient for expressions and commands, the rest being calculations; allows a high compression) • viewing and/or modifying predefined lessons, according to the curricula The whole thing is focused on a mathematical expressions minicompiler, storing the code that will be later used for different purposes (tables, graphics, and optimisations). Programming technologies used. A Visual C# .NET implementation is proposed. New and innovative digital learning objects for mathematics will be developed; they are capable to interpret, contextualize and react depending on the architecture where they are assembled.

Keywords: Adaptor, automatic assembly learning component and user control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1711

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision making has not been far-fetched. Proper classification of these textual information in a given context has also been very difficult. As a result, a systematic review was conducted from previous literature on sentiment classification and AI-based techniques. The study was done in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that could correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy using the knowledge gain from the evaluation of different artificial intelligence techniques reviewed. The study evaluated over 250 articles from digital sources like ACM digital library, Google Scholar, and IEEE Xplore; and whittled down the number of research to 52 articles. Findings revealed that deep learning approaches such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Bidirectional Encoder Representations from Transformer (BERT), and Long Short-Term Memory (LSTM) outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also required to develop a robust sentiment classifier. Results also revealed that data can be obtained from places like Twitter, movie reviews, Kaggle, Stanford Sentiment Treebank (SST), and SemEval Task4 based on the required domain. The hybrid deep learning techniques like CNN+LSTM, CNN+ Gated Recurrent Unit (GRU), CNN+BERT outperformed single deep learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of development simplicity and AI-based library functionalities. Finally, the study recommended the findings obtained for building robust sentiment classifier in the future.

Keywords: Artificial Intelligence, Natural Language Processing, Sentiment Analysis, Social Network, Text.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 597

Authors: Shih-Bin Wang, Ping Yuan, Syu-Fang Liu, Ming-Jun Kuo

Abstract:

By the application of an improved back-propagation neural network (BPNN), a model of current densities for a solid oxide fuel cell (SOFC) with 10 layers is established in this study. To build the learning data of BPNN, Taguchi orthogonal array is applied to arrange the conditions of operating parameters, which totally 7 factors act as the inputs of BPNN. Also, the average current densities achieved by numerical method acts as the outputs of BPNN. Comparing with the direct solution, the learning errors for all learning data are smaller than 0.117%, and the predicting errors for 27 forecasting cases are less than 0.231%. The results show that the presented model effectively builds a mathematical algorithm to predict performance of a SOFC stack immediately in real time. Also, the calculating algorithms are applied to proceed with the optimization of the average current density for a SOFC stack. The operating performance window of a SOFC stack is found to be between 41137.11 and 53907.89. Furthermore, an inverse predicting model of operating parameters of a SOFC stack is developed here by the calculating algorithms of the improved BPNN, which is proved to effectively predict operating parameters to achieve a desired performance output of a SOFC stack.

Keywords: a SOFC stack, BPNN, inverse predicting model of operating parameters, optimization of the average current density

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

Authors: F. Rasi Maezabadi, M. Masdari, M. R. Soltani

Abstract:

Series of experimental tests were conducted on a section of a 660 kW wind turbine blade to measure the pressure distribution of this model oscillating in plunging motion. In order to minimize the amount of data required to predict aerodynamic loads of the airfoil, a General Regression Neural Network, GRNN, was trained using the measured experimental data. The network once proved to be accurate enough, was used to predict the flow behavior of the airfoil for the desired conditions. Results showed that with using a few of the acquired data, the trained neural network was able to predict accurate results with minimal errors when compared with the corresponding measured values. Therefore with employing this trained network the aerodynamic coefficients of the plunging airfoil, are predicted accurately at different oscillation frequencies, amplitudes, and angles of attack; hence reducing the cost of tests while achieving acceptable accuracy.

Keywords: Airfoil, experimental, GRNN, Neural Network, Plunging.

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