Search results for: Computational Intelligence techniques

Authors: Divya Rajavathsavai, Akhilesh Khapre, Basudeb Munshi

Abstract:

The computational fluid dynamics (CFD) study of stirred tank with the air-water interface are carried out in the presence of different types of the impeller and with or without baffles. A multiple reference frame (MRF) approach with the volume of fluid (VOF) method is used to capture the air-water interface. The RANS (Reynolds Averaged Navier-Stokes) equations with k-ε turbulence model are solved to predict the flow behavior of water and air phase which are treated as a different phases. The predicted results have shown that the VOF method is able to capture the interface in the unbaffled tank. While, the VOF method is showing an unfeasible results in the baffled tank with high rotational impeller speed. For continuous stirred tank, the air-water interface is disturbed by the inflow and the level of water is also increased with time.

Keywords: Computational Fluid Dynamics, stirred tank, airwater interface, multiple reference frame, volume of fluid, Reynolds Averaged Navier-Stokes equations.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4364

Authors: Andrea Macruz

Abstract:

This paper explores computation as a process for design by examining how computers can become more than an operative strategy in a designer's toolkit. It documents this, building upon concepts of neuroscience and Antonio Damasio's Homeostasis Theory, which is the control of bodily states through feedback intended to keep conditions favorable for life. To do this, it follows a methodology through algorithmic drawing and discusses the outcomes of three multi-sensory design installations, which culminated from a course in an academic setting. It explains both the studio process that took place to create the installations and the computational process that was developed, related to the fields of algorithmic design and tangible computing. It discusses how designers can use computational range to achieve homeostasis related to sensory data in a multi-sensory installation. The outcomes show clearly how people and computers interact with different sensory modalities and affordances. They propose using computers as meta-physical stabilizers rather than tools.

Keywords: Antonio Damasio, emotional feedback, algorithmic drawing, homeostasis, multi-sensory installation, neuroscience.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 350

Authors: Vladimira Hornackova, Jana Kottasova, Zuzana Vanova, Anna Jungrova

Abstract:

Present study deals with drama education in preschool education. The research made in this field brings a qualitative comparative survey with the aim to find out the use of methods and techniques of drama education in preschool education at university or secondary school graduate preschool teachers. The research uses a content analysis and an unstandardized questionnaire for preschool teachers and obtained data are processed with the help of descriptive methods and correlations. The results allow a comparison of aspects applied through drama in preschool education. The research brings impulses for education improvement in kindergartens and inspiration for university study programs of drama education in the professional training of preschool teachers.

Keywords: Drama education, preschool education, preschool teacher, research.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1372

Authors: Z. Pavlík, M. Čáchová, E. Vejmelková, T. Korecký, J. Fořt, M. Pavlíková, R. Černý

Abstract:

The effect of waste ceramic powder on the thermal properties of lime-pozzolana composites is investigated. At first, the measurements of effective thermal conductivity of lime-pozzolan composites are performed in dependence on moisture content from the dry state to fully water saturated state using a pulse method. Then, the obtained data are analyzed using two different homogenization techniques, namely the Lichtenecker’s and Dobson’s formulas, taking into account Wiener’s and Hashin/Shtrikman bounds. 

Keywords: Waste ceramic powder, lime-pozzolan plasters, effective thermal conductivity, homogenization techniques.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2255

Authors: Yu T. Tsai, Jin H. Huang

Abstract:

In this paper, the specific sound Transmission Loss (TL) of the Laminated Composite Plate (LCP) with different material properties in each layer is investigated. The numerical method to obtain the TL of the LCP is proposed by using elastic plate theory. The transfer matrix approach is novelty presented for computational efficiency in solving the numerous layers of dynamic stiffness matrix (D-matrix) of the LCP. Besides the numerical simulations for calculating the TL of the LCP, the material properties inverse method is presented for the design of a laminated composite plate analogous to a metallic plate with a specified TL. As a result, it demonstrates that the proposed computational algorithm exhibits high efficiency with a small number of iterations for achieving the goal. This method can be effectively employed to design and develop tailor-made materials for various applications.

Keywords: Sound transmission loss, laminated composite plate, transfer matrix approach, inverse problem, elastic plate theory, material properties.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1969

Authors: Ritu Vijay, Rekha Govil

Abstract:

The design of a complete expansion that allows for compact representation of certain relevant classes of signals is a central problem in signal processing applications. Achieving such a representation means knowing the signal features for the purpose of denoising, classification, interpolation and forecasting. Multilayer Neural Networks are relatively a new class of techniques that are mathematically proven to approximate any continuous function arbitrarily well. Radial Basis Function Networks, which make use of Gaussian activation function, are also shown to be a universal approximator. In this age of ever-increasing digitization in the storage, processing, analysis and communication of information, there are numerous examples of applications where one needs to construct a continuously defined function or numerical algorithm to approximate, represent and reconstruct the given discrete data of a signal. Many a times one wishes to manipulate the data in a way that requires information not included explicitly in the data, which is done through interpolation and/or extrapolation. Tidal data are a very perfect example of time series and many statistical techniques have been applied for tidal data analysis and representation. ANN is recent addition to such techniques. In the present paper we describe the time series representation capabilities of a special type of ANN- Radial Basis Function networks and present the results of tidal data representation using RBF. Tidal data analysis & representation is one of the important requirements in marine science for forecasting.

Keywords: ANN, RBF, Tidal Data.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1652

Authors: Lívia B. Meirelles, Erika C. A. N. Chrisman, Flávia B. de Andrade, Lilian C. M. de Oliveira

Abstract:

True Boiling Point distillation (TBP) is one of the most common experimental techniques for the determination of petroleum properties. This curve provides information about the performance of petroleum in terms of its cuts. The experiment is performed in a few days. Techniques are used to determine the properties faster with a software that calculates the distillation curve when a little information about crude oil is known. In order to evaluate the accuracy of distillation curve prediction, eight points of the TBP curve and specific gravity curve (348 K and 523 K) were inserted into the HYSYS Oil Manager, and the extended curve was evaluated up to 748 K. The methods were able to predict the curve with the accuracy of 0.6%-9.2% error (Software X ASTM), 0.2%-5.1% error (Software X Spaltrohr).

Keywords: Distillation curve, petroleum distillation, simulation, true boiling point curve.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1616

Authors: N. Ahmed, A.J. Day, J.L. Victory L. Zeall, B. Young

Abstract:

The manufacture of large-scale precision aerospace components using CNC requires a highly effective maintenance strategy to ensure that the required accuracy can be achieved over many hours of production. This paper reviews a strategy for a maintenance management system based on Failure Mode Avoidance, which uses advanced techniques and technologies to underpin a predictive maintenance strategy. It is shown how condition monitoring (CM) is important to predict potential failures in high precision machining facilities and achieve intelligent and integrated maintenance management. There are two distinct ways in which CM can be applied. One is to monitor key process parameters and observe trends which may indicate a gradual deterioration of accuracy in the product. The other is the use of CM techniques to monitor high status machine parameters enables trends to be observed which can be corrected before machine failure and downtime occurs. It is concluded that the key to developing a flexible and intelligent maintenance framework in any precision manufacturing operation is the ability to evaluate reliably and routinely machine tool condition using condition monitoring techniques within a framework of Failure Mode Avoidance.

Keywords: Maintenance, Condition Monitoring, CNC, Machining, Accuracy, Capability, Key Process Parameters, Critical Parameters

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2224

Authors: Hy Dang, Bo Mei

Abstract:

The development of machine learning methods and techniques has opened doors for investigation in many areas such as medicines, economics, finance, etc. One active research area involving machine learning is stock market prediction. This research paper tries to consider multiple techniques and methods for stock movement prediction using historical price or price factors. The paper explores the effectiveness of some deep learning frameworks for forecasting stock. Moreover, an architecture (TimeStock) is proposed which takes the representation of time into account apart from the price information itself. Our model achieves a promising result that shows a potential approach for the stock movement prediction problem.

Keywords: Classification, machine learning, time representation, stock prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1140

Authors: Parvinder S. Sandhu, Roma Jaswal, Sandeep Khimta, Shailendra Singh

Abstract:

As the majority of faults are found in a few of its modules so there is a need to investigate the modules that are affected severely as compared to other modules and proper maintenance need to be done in time especially for the critical applications. As, Neural networks, which have been already applied in software engineering applications to build reliability growth models predict the gross change or reusability metrics. Neural networks are non-linear sophisticated modeling techniques that are able to model complex functions. Neural network techniques are used when exact nature of input and outputs is not known. A key feature is that they learn the relationship between input and output through training. In this present work, various Neural Network Based techniques are explored and comparative analysis is performed for the prediction of level of need of maintenance by predicting level severity of faults present in NASA-s public domain defect dataset. The comparison of different algorithms is made on the basis of Mean Absolute Error, Root Mean Square Error and Accuracy Values. It is concluded that Generalized Regression Networks is the best algorithm for classification of the software components into different level of severity of impact of the faults. The algorithm can be used to develop model that can be used for identifying modules that are heavily affected by the faults.

Keywords: Neural Network, Software faults, Software Metric.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1571

Authors: Mansour Nikpour, Mohsen Ghasemi, Elahe Mosavi, Mohd Zin Kandar

Abstract:

lack of convenience condition is one of the problems in open spaces in hot and dry regions. Nowadays parks and green landscapes was designed and constructed without any attention to convenience condition. If this process continues, Citizens will encounter with some problems. Harsh climatic condition decreases the efficiency of people-s activities. However there is hard environment condition in hot and dry regions, Convenience condition has been provided in Iranian traditional architecture by using techniques and methods. In this research at the first step characteristics of Iranian garden that can effect on creating sustainable spaces were investigated through observation method. Pleasure space in cities will be created with using these methods and techniques in future cities. Furthermore the comparison between Iranian garden and landscape in today-s cities demonstrate the effectiveness of Iranian garden characteristics on sustainable spaces. Iranian architects used simple and available methods for creating open architectural spaces. In addition desirable conditions were provided with taking in to account both physically and spiritually. Parks and landscapes in future cities can be designed and constructed with respect to architectural techniques that used in Iranian gardens in hot and arid regions.

Keywords: Iranian garden, convenience condition, landscape, sustainable

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1842

Authors: W. P. Hu, J. V. Kumar, Jeffrey J. P. Tsai

Abstract:

The inhibition of SH2 domain regulated protein-protein interactions is an attractive target for developing an effective chemotherapeutic approach in the treatment of disease. Molecular simulation is a useful tool for developing new drugs and for studying molecular recognition. In this study, we searched potential drug compounds for the inhibition of SH2 domain by performing structural similarity search in PubChem Compound Database. A total of 37 compounds were screened from the database, and then we used the LibDock docking program to evaluate the inhibition effect. The best three compounds (AP22408, CID 71463546 and CID 9917321) were chosen for MD simulations after the LibDock docking. Our results show that the compound CID 9917321 can produce a more stable protein-ligand complex compared to other two currently known inhibitors of Src SH2 domain. The compound CID 9917321 may be useful for the inhibition of SH2 domain based on these computational results. Subsequently experiments are needed to verify the effect of compound CID 9917321 on the SH2 domain in the future studies.

Keywords: Nonpeptide inhibitor, Src SH2 domain, LibDock, molecular dynamics simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2072

Authors: Kaumil B. Shah, Hina Chandwani

Abstract:

The modular multilevel converter (MMC) is one of the advanced topologies for medium and high-voltage applications. In high-power, high-voltage MMC, a large number of switching power devices are required. These switching power devices (IGBT) considerable switching losses. This paper analyzes the performance of different discontinuous pulse width modulation (DPWM) techniques and compares the results against a conventional carrier based pulse width modulation method, in order to reduce the switching losses of an MMC. The DPWM reference wave can be generated by adding the zero-sequence component to the original (sine) reference modulation signal. The result of the addition gives the reference signal of DPWM techniques. To minimize the switching losses of the MMC, the clamping period is controlled according to the absolute value of the output load current. No switching is generated in the clamping period so overall switching of the power device is reduced. The simulation result of the different DPWM techniques is compared with conventional carrier-based pulse-width modulation technique.

Keywords: Modular multilevel converter, discontinuous pulse width modulation, switching losses, zero-sequence voltage.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 912

Authors: Hae-Yeoun Lee, In-Koo Kang, Heung-Kyu Lee

Abstract:

This paper addresses an efficient technique to embed and detect digital fingerprint code. Orthogonal modulation method is a straightforward and widely used approach for digital fingerprinting but shows several limitations in computational cost and signal efficiency. Coded modulation method can solve these limitations in theory. However it is difficult to perform well in practice if host signals are not available during tracing colluders, other kinds of attacks are applied, and the size of fingerprint code becomes large. In this paper, we propose a hybrid modulation method, in which the merits of or-thogonal modulation and coded modulation method are combined so that we can achieve low computational cost and high signal efficiency. To analyze the performance, we design a new fingerprint code based on GD-PBIBD theory and modulate this code into images by our method using spread-spectrum watermarking on frequency domain. The results show that the proposed method can efficiently handle large fingerprint code and trace colluders against averaging attacks.

Keywords: Fingerprinting, GD-PBIBD theory, Hybrid modulationtechnique.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1376

Authors: A. Javed, K. Djidjeli, J. T. Xing, S. J. Cox

Abstract:

A method for simulating flow around the solid bodies has been presented using hybrid meshfree and mesh-based schemes. The presented scheme optimizes the computational efficiency by combining the advantages of both meshfree and mesh-based methods. In this approach, a cloud of meshfree nodes has been used in the domain around the solid body. These meshfree nodes have the ability to efficiently adapt to complex geometrical shapes. In the rest of the domain, conventional Cartesian grid has been used beyond the meshfree cloud. Complex geometrical shapes can therefore be dealt efficiently by using meshfree nodal cloud and computational efficiency is maintained through the use of conventional mesh-based scheme on Cartesian grid in the larger part of the domain. Spatial discretization of meshfree nodes has been achieved through local radial basis functions in finite difference mode (RBF-FD). Conventional finite difference scheme has been used in the Cartesian ‘meshed’ domain. Accuracy tests of the hybrid scheme have been conducted to establish the order of accuracy. Numerical tests have been performed by simulating two dimensional steady and unsteady incompressible flows around cylindrical object. Steady flow cases have been run at Reynolds numbers of 10, 20 and 40 and unsteady flow problems have been studied at Reynolds numbers of 100 and 200. Flow Parameters including lift, drag, vortex shedding, and vorticity contours are calculated. Numerical results have been found to be in good agreement with computational and experimental results available in the literature.

Keywords: CFD, Meshfree particle methods, Hybrid grid, Incompressible Navier Strokes equations, RBF-FD.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2899

Authors: M. Sedighizadeh, A. Rezazadeh

Abstract:

In this paper presents a technique for developing the computational efficiency in simulating double output induction generators (DOIG) with two rotor circuits where stator transients are to be included. Iterative decomposition is used to separate the flux– Linkage equations into decoupled fast and slow subsystems, after which the model order of the fast subsystems is reduced by neglecting the heavily damped fast transients caused by the second rotor circuit using integral manifolds theory. The two decoupled subsystems along with the equation for the very slowly changing slip constitute a three time-scale model for the machine which resulted in increasing computational speed. Finally, the proposed method of reduced order in this paper is compared with the other conventional methods in linear and nonlinear modes and it is shown that this method is better than the other methods regarding simulation accuracy and speed.

Keywords: DOIG, Iterative separation, Integral manifolds, Reduced order.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1255

Authors: Parvinder S. Sandhu, Iqbaldeep Kaur, Amit Verma, Samriti Jindal, Shailendra Singh

Abstract:

Biometric measures of one kind or another have been used to identify people since ancient times, with handwritten signatures, facial features, and fingerprints being the traditional methods. Of late, Systems have been built that automate the task of recognition, using these methods and newer ones, such as hand geometry, voiceprints and iris patterns. These systems have different strengths and weaknesses. This work is a two-section composition. In the starting section, we present an analytical and comparative study of common biometric techniques. The performance of each of them has been viewed and then tabularized as a result. The latter section involves the actual implementation of the techniques under consideration that has been done using a state of the art tool called, MATLAB. This tool aids to effectively portray the corresponding results and effects.

Keywords: Matlab, Recognition, Facial Vectors, Functions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3183

Authors: Faruq A. Al-Omari, Nabeel I. Al-Fayoumi

Abstract:

In this paper, we present a new algorithm for clustering data in large datasets using image processing approaches. First the dataset is mapped into a binary image plane. The synthesized image is then processed utilizing efficient image processing techniques to cluster the data in the dataset. Henceforth, the algorithm avoids exhaustive search to identify clusters. The algorithm considers only a small set of the data that contains critical boundary information sufficient to identify contained clusters. Compared to available data clustering techniques, the proposed algorithm produces similar quality results and outperforms them in execution time and storage requirements.

Keywords: Data clustering, Data mining, Image-mapping, Pattern discovery, Predictive analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1496

Authors: Andrew R.H. Rigit, Patrick T.K. Low

Abstract:

Majority of pepper farmers in Malaysia are using the open-sun method for drying the pepper berries. This method is time consuming and exposed the berries to rain and contamination. A maintenance-friendly and properly enclosed dryer is therefore desired. A dryer design with a solar collector and a chimney was studied and adapted to suit the needs of small-scale pepper farmers in Malaysia. The dryer will provide an environment with an optimum operating temperature meant for drying pepper berries. The dryer model was evaluated by using commercially available computational fluid dynamic (CFD) software in order to understand the heat and mass transfer inside the dryer. Natural convection was the only mode of heat transportation considered in this study as in accordance to the idea of having a simple and maintenance-friendly design. To accommodate the effect of low buoyancy found in natural convection driers, a biomass burner was integrated into the solar dryer design.

Keywords: Computational fluid dynamics, heat and masstransfer, solar dryer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3662

Authors: Abeer Aljohani

Abstract:

The COVID-19 virus spread has been one of the extreme pandemics across the globe. It is also referred as corona virus which is a contagious disease that continuously mutates into numerous variants. Currently, the B.1.1.529 variant labeled as Omicron is detected in South Africa. The huge spread of COVID-19 disease has affected several lives and has surged exceptional pressure on the healthcare systems worldwide. Also, everyday life and the global economy have been at stake. Numerous COVID-19 cases have produced a huge burden on hospitals as well as health workers. To reduce this burden, this paper predicts COVID-19 disease based on the symptoms and medical history of the patient. As machine learning is a widely accepted area and gives promising results for healthcare, this research presents an architecture for COVID-19 detection using ML techniques integrated with feature dimensionality reduction. This paper uses a standard University of California Irvine (UCI) dataset for predicting COVID-19 disease. This dataset comprises symptoms of 5434 patients. This paper also compares several supervised ML techniques on the presented architecture. The architecture has also utilized 10-fold cross validation process for generalization and Principal Component Analysis (PCA) technique for feature reduction. Standard parameters are used to evaluate the proposed architecture including F1-Score, precision, accuracy, recall, Receiver Operating Characteristic (ROC) and Area under Curve (AUC). The results depict that Decision tree, Random Forest and neural networks outperform all other state-of-the-art ML techniques. This result can be used to effectively identify COVID-19 infection cases.

Keywords: Supervised machine learning, COVID-19 prediction, healthcare analytics, Random Forest, Neural Network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 372

Authors: S. Kotsiantis, A. Kostoulas, S. Lykoudis, A. Argiriou, K. Menagias

Abstract:

Estimates of temperature values at a specific time of day, from daytime and daily profiles, are needed for a number of environmental, ecological, agricultural and technical applications, ranging from natural hazards assessments, crop growth forecasting to design of solar energy systems. The scope of this research is to investigate the efficiency of data mining techniques in estimating minimum, maximum and mean temperature values. For this reason, a number of experiments have been conducted with well-known regression algorithms using temperature data from the city of Patras in Greece. The performance of these algorithms has been evaluated using standard statistical indicators, such as Correlation Coefficient, Root Mean Squared Error, etc.

Keywords: regression algorithms, supervised machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3411

Authors: Aboamama Atahar Ahmed, Muhammad Shafie Abd Latiff, Kamalrulnizam Abu Bakar, Zainul AhmadRajion

Abstract:

Distance visualization of large datasets often takes the direction of remote viewing and zooming techniques of stored static images. However, the continuous increase in the size of datasets and visualization operation causes insufficient performance with traditional desktop computers. Additionally, the visualization techniques such as Isosurface depend on the available resources of the running machine and the size of datasets. Moreover, the continuous demand for powerful computing powers and continuous increase in the size of datasets results an urgent need for a grid computing infrastructure. However, some issues arise in current grid such as resources availability at the client machines which are not sufficient enough to process large datasets. On top of that, different output devices and different network bandwidth between the visualization pipeline components often result output suitable for one machine and not suitable for another. In this paper we investigate how the grid services could be used to support remote visualization of large datasets and to break the constraint of physical co-location of the resources by applying the grid computing technologies. We show our grid enabled architecture to visualize large medical datasets (circa 5 million polygons) for remote interactive visualization on modest resources clients.

Keywords: Visualization, Grid computing, Medical datasets, visualization techniques, thin clients, Globus toolkit, VTK.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1747

Authors: John M. Ikome, Martha E. Ikome, Therese Van Wyk

Abstract:

Productivity optimization of a company can significantly increase the company’s output and productivity which can be in the form of corrective actions of ineffective activities, process simplification, and reduction of variations, responsiveness, and reduction of set-up-time which are all under the classification of waste within the manufacturing environment. Deriving a means to eliminate a number of these issues has a key importance for manufacturing organization. This paper focused on a number of industrial engineering techniques which include a cause and effect diagram, to identify and optimize the method or systems being used. Based on our results, it shows that there are a number of variations within the production processes that can significantly disrupt the expected output.

Keywords: Optimization, fishbone diagram, productivity.

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

Authors: Vidhu Mitha Goutham, Ruma Mukherjee

Abstract:

The low availability of well-trained, unlimited, dynamic-access models for specific languages makes it hard for corporate users to adopt quick translation techniques and incorporate them into product solutions. As translation tasks increasingly require a dynamic sequence learning curve; stable, cost-free opensource models are scarce. We survey and compare current translation techniques and propose a modified sequence to sequence model repurposed with attention techniques. Sequence learning using an encoder-decoder model is now paving the path for higher precision levels in translation. Using a Convolutional Neural Network (CNN) encoder and a Recurrent Neural Network (RNN) decoder background, we use Fairseq tools to produce an end-to-end bilingually trained Spanish-English machine translation model including source language detection. We acquire competitive results using a duo-lingo-corpus trained model to provide for prospective, ready-made plug-in use for compound sentences and document translations. Our model serves a decent system for large, organizational data translation needs. While acknowledging its shortcomings and future scope, it also identifies itself as a well-optimized deep neural network model and solution.

Keywords: Attention, encoder-decoder, Fairseq, Seq2Seq, Spanish, translation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 469

Authors: May Phyo Thwal, Khin Htay Kyi, Kyaw Swar Soe

Abstract:

According to the density of the chips, designers are trying to put so any facilities of computational and storage on single chips. Along with the complexity of computational and storage circuits, the designing, testing and debugging become more and more complex and expensive. So, hardware design will be built by using very high speed hardware description language, which is more efficient and cost effective. This paper will focus on the implementation of 32-bit ALU design based on Verilog hardware description language. Adder and subtracter operate correctly on both unsigned and positive numbers. In ALU, addition takes most of the time if it uses the ripple-carry adder. The general strategy for designing fast adders is to reduce the time required to form carry signals. Adders that use this principle are called carry look- ahead adder. The carry look-ahead adder is to be designed with combination of 4-bit adders. The syntax of Verilog HDL is similar to the C programming language. This paper proposes a unified approach to ALU design in which both simulation and formal verification can co-exist.

Keywords: Addition, arithmetic logic unit, carry look-ahead adder, Verilog HDL.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 8919

Authors: Faisal Alshuwaier, Ali Areshey

Abstract:

Text mining techniques are generally applied for classifying the text, finding fuzzy relations and structures in data sets. This research provides plenty text mining capabilities. One common application is text classification and event extraction, which encompass deducing specific knowledge concerning incidents referred to in texts. The main contribution of this paper is the clarification of a concept graph generation mechanism, which is based on a text classification and optimal fuzzy relationship extraction. Furthermore, the work presented in this paper explains the application of fuzzy relationship extraction and branch and bound (BB) method to simplify the texts.

Keywords: Extraction, Max-Prod, Fuzzy Relations, Text Mining, Memberships, Classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2176

Authors: Rami N. Khushaba, Adel Al-Jumaily

Abstract:

The myoelectric signal (MES) is one of the Biosignals utilized in helping humans to control equipments. Recent approaches in MES classification to control prosthetic devices employing pattern recognition techniques revealed two problems, first, the classification performance of the system starts degrading when the number of motion classes to be classified increases, second, in order to solve the first problem, additional complicated methods were utilized which increase the computational cost of a multifunction myoelectric control system. In an effort to solve these problems and to achieve a feasible design for real time implementation with high overall accuracy, this paper presents a new method for feature extraction in MES recognition systems. The method works by extracting features using Wavelet Packet Transform (WPT) applied on the MES from multiple channels, and then employs Fuzzy c-means (FCM) algorithm to generate a measure that judges on features suitability for classification. Finally, Principle Component Analysis (PCA) is utilized to reduce the size of the data before computing the classification accuracy with a multilayer perceptron neural network. The proposed system produces powerful classification results (99% accuracy) by using only a small portion of the original feature set.

Keywords: Biomedical Signal Processing, Data mining andInformation Extraction, Machine Learning, Rehabilitation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1734

Authors: Alan Dormer

Abstract:

Business rules are widely used within the services sector. They provide consistency and allow relatively unskilled staff to process complex transactions correctly. But there are many examples where the rules themselves have an impact on the costs and profits of an organisation. Financial services, transport and human services are areas where the rules themselves can impact the bottom line in a predictable way. If this is the case, how can we find that set of rules that maximise profit, performance or customer service, or any other key performance indicators? The manufacturing, energy and process industries have embraced mathematical optimisation techniques to improve efficiency, increase production and so on. This paper explores several real world (but simplified) problems in the services sector and shows how business rules can be optimised. It also examines the similarities and differences between the service and other sectors, and how optimisation techniques could be used to deliver similar benefits.

Keywords: Business rules, services, optimisation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1616

Authors: Carol Anne Hargreaves

Abstract:

A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.

Keywords: Machine learning, stock market trading, logistic principal component analysis, automated stock investment system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1094

Authors: H. Ali, K. Hameed, N. Khan

Abstract:

In DMVC, we have more than one options of sources available for construction of side information. The newer techniques make use of both the techniques simultaneously by constructing a bitmask that determines the source of every block or pixel of the side information. A lot of computation is done to determine each bit in the bitmask. In this paper, we have tried to define areas that can only be well predicted by temporal interpolation and not by multiview interpolation or synthesis. We predict that all such areas that are not covered by two cameras cannot be appropriately predicted by multiview synthesis and if we can identify such areas in the first place, we don-t need to go through the script of computations for all the pixels that lie in those areas. Moreover, this paper also defines a technique based on KLT to mark the above mentioned areas before any other processing is done on the side view.

Keywords: Side Information, Distributed Multiview Video Coding, Fusion, Early Decision.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1327