Search results for: fast prediction model

Authors: A. Pedram, M. R. Jamali, T. Pedram, S. M. Fakhraie, C. Lucas

Abstract:

Local Linear Neuro-Fuzzy Models (LLNFM) like other neuro- fuzzy systems are adaptive networks and provide robust learning capabilities and are widely utilized in various applications such as pattern recognition, system identification, image processing and prediction. Local linear model tree (LOLIMOT) is a type of Takagi-Sugeno-Kang neuro fuzzy algorithm which has proven its efficiency compared with other neuro fuzzy networks in learning the nonlinear systems and pattern recognition. In this paper, a dedicated reconfigurable and parallel processing hardware for LOLIMOT algorithm and its applications are presented. This hardware realizes on-chip learning which gives it the capability to work as a standalone device in a system. The synthesis results on FPGA platforms show its potential to improve the speed at least 250 of times faster than software implemented algorithms.

Keywords: LOLIMOT, hardware, neurofuzzy systems, reconfigurable, parallel.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3888

Authors: Hesham Abd Elkhalek, Sherif M. Hafez, Yasser M. El Fahham

Abstract:

Allocating limited budget to maintain bridge networks and selecting effective maintenance strategies for each bridge represent challenging tasks for maintenance managers and decision makers. In Egypt, bridges are continuously deteriorating. In many cases, maintenance works are performed due to user complaints. The objective of this paper is to develop a practical and reliable framework to manage the maintenance, repair, and rehabilitation (MR&R) activities of Bridges network considering performance and budget limits. The model solves an optimization problem that maximizes the average condition of the entire network given the limited available budget using Genetic Algorithm (GA). The framework contains bridge inventory, condition assessment, repair cost calculation, deterioration prediction, and maintenance optimization. The developed model takes into account multiple parameters including serviceability requirements, budget allocation, element importance on structural safety and serviceability, bridge impact on network, and traffic. A questionnaire is conducted to complete the research scope. The proposed model is implemented in software, which provides a friendly user interface. The framework provides a multi-year maintenance plan for the entire network for up to five years. A case study of ten bridges is presented to validate and test the proposed model with data collected from Transportation Authorities in Egypt. Different scenarios are presented. The results are reasonable, feasible and within acceptable domain.

Keywords: Bridge Management Systems (BMS), cost optimization condition assessment, fund allocation, Markov chain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1958

Authors: Çiğdem Bakır, Mecit Yüzkat

Abstract:

With the increasing emphasis on water quality worldwide, the search for and expanding the market for new and intelligent monitoring systems has increased. The current method is the laboratory process, where samples are taken from bodies of water, and tests are carried out in laboratories. This method is time-consuming, a waste of manpower and uneconomical. To solve this problem, we used machine learning methods to detect water pollution in our study. We created decision trees with the Orange3 software used in the study and tried to determine all the factors that cause water pollution. An automatic prediction model based on water quality was developed by taking many model inputs such as water temperature, pH, transparency, conductivity, dissolved oxygen, and ammonia nitrogen with machine learning methods. The proposed approach consists of three stages: Preprocessing of the data used, feature detection and classification. We tried to determine the success of our study with different accuracy metrics and the results were presented comparatively. In addition, we achieved approximately 98% success with the decision tree.

Keywords: Decision tree, water quality, water pollution, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 260

Authors: X. Z. Gao, S. J. Ovaska, X. Wang

Abstract:

Prediction of sinusoidal signals with time-varying frequencies has been an important research topic in power electronics systems. To solve this problem, we propose a new fuzzy predictive filtering scheme, which is based on a Finite Impulse Response (FIR) filter bank. Fuzzy logic is introduced here to provide appropriate interpolation of individual filter outputs. Therefore, instead of regular 'hard' switching, our method has the advantageous 'soft' switching among different filters. Simulation comparisons between the fuzzy predictive filtering and conventional filter bank-based approach are made to demonstrate that the new scheme can achieve an enhanced prediction performance for slowly changing sinusoidal input signals.

Keywords: Predictive filtering, fuzzy logic, sinusoidal signals, time-varying frequencies.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1493

Authors: Suzan Wedyan

Abstract:

Associative classification (AC) is a data mining approach that combines association rule and classification to build classification models (classifiers). AC has attracted a significant attention from several researchers mainly because it derives accurate classifiers that contain simple yet effective rules. In the last decade, a number of associative classification algorithms have been proposed such as Classification based Association (CBA), Classification based on Multiple Association Rules (CMAR), Class based Associative Classification (CACA), and Classification based on Predicted Association Rule (CPAR). This paper surveys major AC algorithms and compares the steps and methods performed in each algorithm including: rule learning, rule sorting, rule pruning, classifier building, and class prediction.

Keywords: Associative Classification, Classification, Data Mining, Learning, Rule Ranking, Rule Pruning, Prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6633

Authors: Farhad Alizadeh, Alireza Faregh Gharamaleki, Mojtaba Jalilzadeh, Houshang Gholami, Ali Akhoundzadeh

Abstract:

This study presented hybrid pre-processing approach along with a conceptual model to enhance the accuracy of river discharge prediction. In order to achieve this goal, Ensemble Empirical Mode Decomposition algorithm (EEMD), Discrete Wavelet Transform (DWT) and Mutual Information (MI) were employed as a hybrid pre-processing approach conjugated to Least Square Support Vector Machine (LSSVM). A conceptual strategy namely multi-station model was developed to forecast the Souris River discharge more accurately. The strategy used herein was capable of covering uncertainties and complexities of river discharge modeling. DWT and EEMD was coupled, and the feature selection was performed for decomposed sub-series using MI to be employed in multi-station model. In the proposed feature selection method, some useless sub-series were omitted to achieve better performance. Results approved efficiency of the proposed DWT-EEMD-MI approach to improve accuracy of multi-station modeling strategies.

Keywords: River stage-discharge process, LSSVM, discrete wavelet transform (DWT), ensemble empirical decomposition mode (EEMD), multi-station modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 664

Authors: Mohammed Abdalla Osman Mukhtar, Azween Abdullah, Alan Giffin Downe

Abstract:

Model mapping and transformation are important processes in high level system abstractions, and form the cornerstone of model-driven architecture (MDA) techniques. Considerable research in this field has devoted attention to static system abstraction, despite the fact that most systems are dynamic with high frequency changes in behavior. In this paper we provide an overview of work that has been done with regard to behavior model mapping and transformation, based on: (1) the completeness of the platform independent model (PIM); (2) semantics of behavioral models; (3) languages supporting behavior model transformation processes; and (4) an evaluation of model composition to effect the best approach to describing large systems with high complexity.

Keywords: MDA; PIM, PSM, QVT, Model Transformation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1761

Authors: Mohammad Shoyaib, M. Abdullah-Al-Wadud, Oksam Chae

Abstract:

Proteomics is one of the largest areas of research for bioinformatics and medical science. An ambitious goal of proteomics is to elucidate the structure, interactions and functions of all proteins within cells and organisms. Predicting Protein-Protein Interaction (PPI) is one of the crucial and decisive problems in current research. Genomic data offer a great opportunity and at the same time a lot of challenges for the identification of these interactions. Many methods have already been proposed in this regard. In case of in-silico identification, most of the methods require both positive and negative examples of protein interaction and the perfection of these examples are very much crucial for the final prediction accuracy. Positive examples are relatively easy to obtain from well known databases. But the generation of negative examples is not a trivial task. Current PPI identification methods generate negative examples based on some assumptions, which are likely to affect their prediction accuracy. Hence, if more reliable negative examples are used, the PPI prediction methods may achieve even more accuracy. Focusing on this issue, a graph based negative example generation method is proposed, which is simple and more accurate than the existing approaches. An interaction graph of the protein sequences is created. The basic assumption is that the longer the shortest path between two protein-sequences in the interaction graph, the less is the possibility of their interaction. A well established PPI detection algorithm is employed with our negative examples and in most cases it increases the accuracy more than 10% in comparison with the negative pair selection method in that paper.

Keywords: Interaction graph, Negative training data, Protein-Protein interaction, Support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1702

Authors: N. Mahendran, S. Vishwaja

Abstract:

The Carry Select Adder (CSLA) is a fast adder which improves the speed of addition. From the structure of the CSLA, it is clear that there is opportunity for reducing the area. The logic operations involved in conventional CSLA and binary to excess-1 converter (BEC) based CSLA are analyzed to make a study on the data dependence and to identify redundant logic operations. In the existing adder design, the carry select (CS) operation is scheduled before the final-sum, which is different from the conventional CSLA design. In the presented scheme, Kogge stone parallel adder approach is used instead of existing adder design it will generate fast carry for intermediate stages and also improves the speed of addition. When compared to existing adder design the delay is less in the proposed adder design.

Keywords: Binary to excess-1 converter, delay, carry select adder, Kogge stone adder, speed.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1465

Authors: Caihong Sun, Xizi Zhang

Abstract:

Rating prediction is an important problem for recommender systems. The task is to predict the rating for an item that a user would give. Most of the existing algorithms for the task ignore the effect of negative ratings rated by users on items, but the negative ratings have a significant impact on users’ purchasing decisions in practice. In this paper, we present a rating prediction algorithm based on factorization machines that consider the effect of negative ratings inspired by Loss Aversion theory. The aim of this paper is to develop a concave and a convex negative disgust function to evaluate the negative ratings respectively. Experiments are conducted on MovieLens dataset. The experimental results demonstrate the effectiveness of the proposed methods by comparing with other four the state-of-the-art approaches. The negative ratings showed much importance in the accuracy of ratings predictions.

Keywords: Factorization machines, feature engineering, negative ratings, recommendation systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 941

Authors: Geng Xiangren, Liu Lei, Gui Ye-Wei, Tang Wei, Wang An-ling

Abstract:

The malfunction of thermal protection system (TPS) caused by aerodynamic heating is a latent trouble to aircraft structure safety. Accurately predicting the structure temperature field is quite important for the TPS design of hypersonic vehicle. Since Thornton’s work in 1988, the coupled method of aerodynamic heating and heat transfer has developed rapidly. However, little attention has been paid to the influence of structural deformation on aerodynamic heating and structural temperature field. In the flight, especially the long-endurance flight, the structural deformation, caused by the aerodynamic heating and temperature rise, has a direct impact on the aerodynamic heating and structural temperature field. Thus, the coupled interaction cannot be neglected. In this paper, based on the method of static aero-thermo-elasticity, considering the influence of aero-thermo-elasticity deformation, the aerodynamic heating and heat transfer coupled results of hypersonic vehicle wing model were calculated. The results show that, for the low-curvature region, such as fuselage or center-section wing, structure deformation has little effect on temperature field. However, for the stagnation region with high curvature, the coupled effect is not negligible. Thus, it is quite important for the structure temperature prediction to take into account the effect of elastic deformation. This work has laid a solid foundation for improving the prediction accuracy of the temperature distribution of aircraft structures and the evaluation capacity of structural performance.

Keywords: Aero-thermo-elasticity, elastic deformation, structural temperature, multi-field coupling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 894

Authors: J. McCullagh, T. Whitfort

Abstract:

Artificial Neural Networks (ANNs) have been used successfully in many scientific, industrial and business domains as a method for extracting knowledge from vast amounts of data. However the use of ANN techniques in the sporting domain has been limited. In professional sport, data is stored on many aspects of teams, games, training and players. Sporting organisations have begun to realise that there is a wealth of untapped knowledge contained in the data and there is great interest in techniques to utilise this data. This study will use player data from the elite Australian Football League (AFL) competition to train and test ANNs with the aim to predict the onset of injuries. The results demonstrate that an accuracy of 82.9% was achieved by the ANNs’ predictions across all examples with 94.5% of all injuries correctly predicted. These initial findings suggest that ANNs may have the potential to assist sporting clubs in the prediction of injuries.

Keywords: Artificial Neural Networks, data, injuries, sport

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2889

Authors: M. Bohlouli, M. Analoui

Abstract:

For complete support of Quality of Service, it is better that environment itself predicts resource requirements of a job by using special methods in the Grid computing. The exact and correct prediction causes exact matching of required resources with available resources. After the execution of each job, the used resources will be saved in the active database named "History". At first some of the attributes will be exploit from the main job and according to a defined similarity algorithm the most similar executed job will be exploited from "History" using statistic terms such as linear regression or average, resource requirements will be predicted. The new idea in this research is based on active database and centralized history maintenance. Implementation and testing of the proposed architecture results in accuracy percentage of 96.68% to predict CPU usage of jobs and 91.29% of memory usage and 89.80% of the band width usage.

Keywords: Active Database, Grid Computing, ResourceRequirement Prediction, Scheduling,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1432

Authors: Nhu Van NGUYEN, Jean-Marc OGIER, Salvatore TABBONE, Alain BOUCHER

Abstract:

The state-of-the-art Bag of Words model in Content- Based Image Retrieval has been used for years but the relevance feedback strategies for this model are not fully investigated. Inspired from text retrieval, the Bag of Words model has the ability to use the wealth of knowledge and practices available in text retrieval. We study and experiment the relevance feedback model in text retrieval for adapting it to image retrieval. The experiments show that the techniques from text retrieval give good results for image retrieval and that further improvements is possible.

Keywords: Relevance feedback, bag of words model, probabilistic model, vector space model, image retrieval

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2117

Authors: Mara Gubaidullina, Aigerim Yelibayeva

Abstract:

The Shanghai Cooperation Organization is one of the successful outcomes of China's foreign policy since the end of the Cold war. The expansion of multilateral ties all over the world by dint of pursuing institutional strategies as SCO, identify China as a more constructive power. SCO became a new model of cooperation that was formed on remains of collapsed Soviet system, and predetermined China's geopolitical role in the region. As the fast developing effective regional mechanism, SCO today has more of external impact on the international system and forms a new type of interaction for promoting China's grand strategy of 'peaceful rise'.

Keywords: Central Asia, China's grand strategy, Shanghai Cooperation Organization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2005

Authors: W. Triampo, D. Baowan, I.M. Tang, N. Nuttavut, J. Wong-Ekkabut, G. Doungchawee

Abstract:

In this work, we consider a deterministic model for the transmission of leptospirosis which is currently spreading in the Thai population. The SIR model which incorporates the features of this disease is applied to the epidemiological data in Thailand. It is seen that the numerical solutions of the SIR equations are in good agreement with real empirical data. Further improvements are discussed.

Keywords: Leptospirosis, SIR Model, Deterministic model, Thailand.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1987

Authors: Mehdi Ghommem, Daniel Garcia, Nathan Collier, Victor Calo

Abstract:

We develop a fast, user-friendly implementation of a potential flow solver based on the unsteady vortex lattice method (UVLM). The computational framework uses the Python programming language which has easy integration with the scripts requiring computationally-expensive operations written in Fortran. The mixed-language approach enables high performance in terms of solution time and high flexibility in terms of easiness of code adaptation to different system configurations and applications. This computational tool is intended to predict the unsteady aerodynamic behavior of multiple moving bodies (e.g., flapping wings, rotating blades, suspension bridges...) subject to an incoming air. We simulate different aerodynamic problems to validate and illustrate the usefulness and effectiveness of the developed computational tool.

Keywords: Unsteady aerodynamics, numerical simulations, mixed-language approach, potential flow.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1211

Authors: R.Marsalek

Abstract:

This paper present a new way to find the aerodynamic characteristic equation of missile for the numerical trajectories prediction more accurate. The goal is to obtain the polynomial equation based on two missile characteristic parameters, angle of attack (α ) and flight speed (ν ). First, the understudied missile is modeled and used for flow computational model to compute aerodynamic force and moment. Assume that performance range of understudied missile where range -10< α <10 and 0< ν <200. After completely obtained results of all cases, the data are fit by polynomial interpolation to create equation of each case and then combine all equations to form aerodynamic characteristic equation, which will be used for trajectories simulation.

Keywords: ferro-precipitate, adsorption, SDS, zeta potential

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1909

Authors: Amin Esmaeilzadeh, Mohammad Sadeghi, Farhad Kolahan

Abstract:

Arc welding is an important joining process widely used in many industrial applications including production of automobile, ships structures and metal tanks. In welding process, the moving electrode causes highly non-uniform temperature distribution that leads to residual stresses and different deviations, especially buckling distortions in thin plates. In order to control the deviations and increase the quality of welded plates, a fixture can be used as a practical and low cost method with high efficiency. In this study, a coupled thermo-mechanical finite element model is coded in the software ANSYS to simulate the behavior of thin plates located by a 3-2-1 positioning system during the welding process. Computational results are compared with recent similar works to validate the finite element models. The agreement between the result of proposed model and other reported data proves that finite element modeling can accurately predict the behavior of welded thin plates.

Keywords: Welding, thin plate, buckling distortion, fixture locators, finite element modelling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2410

Authors: Amin Almasi

Abstract:

Design and evaluation of reciprocating compressors should include a pulsation study. The object is to ensure that predicted pulsation levels meet guidelines to limit vibration, shaking forces, noise, associated pressure drops, horsepower losses and fabrication cost and time to acceptable levels. This paper explains procedures and recommendations to select and size pulsation suppression devices to obtain optimum arrangement in terms of pulsation, vibration, shaking forces, performance, reliability, safety, operation, maintenance and commercial conditions. Model and advanced formulations for pulsation study are presented. The effect of the full fluid dynamic model on the prediction of pulsation waves and resulting frequency spectrum distributions are discussed. Advanced and optimum methods of controlling pulsations are highlighted. Useful recommendations and guidelines for pulsation control, piping pulsation analysis, pulsation vessel design, shaking forces, low pressure drop orifices, pulsation study report and devices to mitigate pulsation and shaking problems are discussed.

Keywords: Pulsation, Reciprocating Compressor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 8835

Authors: Chia-Ling Chang, Chung-Sheng Liao

Abstract:

The present study focuses on the discussion over the parameter of Artificial Neural Network (ANN). Sensitivity analysis is applied to assess the effect of the parameters of ANN on the prediction of turbidity of raw water in the water treatment plant. The result shows that transfer function of hidden layer is a critical parameter of ANN. When the transfer function changes, the reliability of prediction of water turbidity is greatly different. Moreover, the estimated water turbidity is less sensitive to training times and learning velocity than the number of neurons in the hidden layer. Therefore, it is important to select an appropriate transfer function and suitable number of neurons in the hidden layer in the process of parameter training and validation.

Keywords: Artificial Neural Network (ANN), sensitivity analysis, turbidity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2813

Authors: Ammar Mahjoubi, Ridha Fethi Mechlouch, Belgacem Mahdhaoui, Ammar Ben Brahim

Abstract:

This purpose of this paper is to develop and validate a model to accurately predict the cell temperature of a PV module that adapts to various mounting configurations, mounting locations, and climates while only requiring readily available data from the module manufacturer. Results from this model are also compared to results from published cell temperature models. The models were used to predict real-time performance from a PV water pumping systems in the desert of Medenine, south of Tunisia using 60-min intervals of measured performance data during one complete year. Statistical analysis of the predicted results and measured data highlight possible sources of errors and the limitations and/or adequacy of existing models, to describe the temperature and efficiency of PV-cells and consequently, the accuracy of performance of PV water pumping systems prediction models.

Keywords: Temperature of a photovoltaic module, Predicted models, PV water pumping systems efficiency, Simulation, Desert of southern Tunisia.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1851

Authors: Sujoy Das, M. M. Ghosh

Abstract:

The thermal conductivity of a fluid can be significantly enhanced by dispersing nano-sized particles in it, and the resultant fluid is termed as "nanofluid". A theoretical model for estimating the thermal conductivity of a nanofluid has been proposed here. It is based on the mechanism that evenly dispersed nanoparticles within a nanofluid undergo Brownian motion in course of which the nanoparticles repeatedly collide with the heat source. During each collision a rapid heat transfer occurs owing to the solidsolid contact. Molecular dynamics (MD) simulation of the collision of nanoparticles with the heat source has shown that there is a pulselike pick up of heat by the nanoparticles within 20-100 ps, the extent of which depends not only on thermal conductivity of the nanoparticles, but also on the elastic and other physical properties of the nanoparticle. After the collision the nanoparticles undergo Brownian motion in the base fluid and release the excess heat to the surrounding base fluid within 2-10 ms. The Brownian motion and associated temperature variation of the nanoparticles have been modeled by stochastic analysis. Repeated occurrence of these events by the suspended nanoparticles significantly contributes to the characteristic thermal conductivity of the nanofluids, which has been estimated by the present model for a ethylene glycol based nanofluid containing Cu-nanoparticles of size ranging from 8 to 20 nm, with Gaussian size distribution. The prediction of the present model has shown a reasonable agreement with the experimental data available in literature.

Keywords: Brownian dynamics, Molecular dynamics, Nanofluid, Thermal conductivity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2263

Authors: J. K. Alhassan, B. Attah, S. Misra

Abstract:

Human beings have the ability to make logical decisions. Although human decision - making is often optimal, it is insufficient when huge amount of data is to be classified. Medical dataset is a vital ingredient used in predicting patient’s health condition. In other to have the best prediction, there calls for most suitable machine learning algorithms. This work compared the performance of Artificial Neural Network (ANN) and Decision Tree Algorithms (DTA) as regards to some performance metrics using diabetes data. WEKA software was used for the implementation of the algorithms. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were the two algorithms used for ANN, while RegTree and LADTree algorithms were the DTA models used. From the results obtained, DTA performed better than ANN. The Root Mean Squared Error (RMSE) of MLP is 0.3913 that of RBF is 0.3625, that of RepTree is 0.3174 and that of LADTree is 0.3206 respectively.

Keywords: Artificial neural network, classification, decision tree, diabetes mellitus.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2417

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 910

Authors: Nurul Bahiyah Ahmad Khairudin, Habibah A Wahab

Abstract:

A new approach to predict the 3D structures of proteins by combining the knowledge-based method and Molecular Dynamics Simulation is presented on the chicken villin headpiece subdomain (HP-36). Comparative modeling is employed as the knowledge-based method to predict the core region (Ala9-Asn28) of the protein while the remaining residues are built as extended regions (Met1-Lys8; Leu29-Phe36) which then further refined using Molecular Dynamics Simulation for 120 ns. Since the core region is built based on a high sequence identity to the template (65%) resulting in RMSD of 1.39 Å from the native, it is believed that this well-developed core region can act as a 'nucleation center' for subsequent rapid downhill folding. Results also demonstrate that the formation of the non-native contact which tends to hamper folding rate can be avoided. The best 3D model that exhibits most of the native characteristics is identified using clustering method which then further ranked based on the conformational free energies. It is found that the backbone RMSD of the best model compared to the NMR-MDavg is 1.01 Å and 3.53 Å, for the core region and the complete protein, respectively. In addition to this, the conformational free energy of the best model is lower by 5.85 kcal/mol as compared to the NMR-MDavg. This structure prediction protocol is shown to be effective in predicting the 3D structure of small globular protein with a considerable accuracy in much shorter time compared to the conventional Molecular Dynamics simulation alone.

Keywords: 3D model, Chicken villin headpiece subdomain, Molecular dynamic simulation NMR-MDavg, RMSD.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1549

Authors: Habibi Said Mustafa, Hiroko Ono

Abstract:

Since 2006, Afghanistan is dealing with one of the most dramatic trend of urban movement in its history, cities and towns are expanding in size and number. Kabul is the capital of Afghanistan and as well as the fast-growing city in the Asia. The influx of the returnees from neighbor countries and other provinces of Afghanistan caused high rate of artificial growth which slums increased. As an unwanted consequence of this growth, today informal settlements have covered a vast portion of the city. Land Readjustment (LR) has proved to be an important tool for developing informal settlements and reorganizing urban areas but its implementation always varies from country to country and region to region within the countries. Consequently, to successfully develop the informal settlements in Kabul, we need to define an Afghan model of LR specifically for Afghanistan which needs to incorporate all those factors related to the socio-economic condition of the country. For this purpose, a part of the old city of Kabul has selected as a study area which is located near the Central Business District (CBD). After the further analysis and incorporating all needed factors, the result shows a positive potential for the implementation of an adaptable Land Readjustment model for Kabul city which is more sustainable and socio-economically friendly. It will enhance quality of life and provide better urban services for the residents. Moreover, it will set a vision and criteria by which sustainable developments shall proceed in other similar informal settlements of Kabul.

Keywords: Adaptation, informal settlements, Kabul, land readjustment, preservation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1331

Authors: Victor Bodell, Lukas Ekstrom, Somayeh Aghanavesi

Abstract:

Fuel consumption (FC) is one of the key factors in determining expenses of operating a heavy-duty vehicle. A customer may therefore request an estimate of the FC of a desired vehicle. The modular design of heavy-duty vehicles allows their construction by specifying the building blocks, such as gear box, engine and chassis type. If the combination of building blocks is unprecedented, it is unfeasible to measure the FC, since this would first r equire the construction of the vehicle. This paper proposes a machine learning approach to predict FC. This study uses around 40,000 vehicles specific and o perational e nvironmental c onditions i nformation, such as road slopes and driver profiles. A ll v ehicles h ave d iesel engines and a mileage of more than 20,000 km. The data is used to investigate the accuracy of machine learning algorithms Linear regression (LR), K-nearest neighbor (KNN) and Artificial n eural n etworks (ANN) in predicting fuel consumption for heavy-duty vehicles. Performance of the algorithms is evaluated by reporting the prediction error on both simulated data and operational measurements. The performance of the algorithms is compared using nested cross-validation and statistical hypothesis testing. The statistical evaluation procedure finds that ANNs have the lowest prediction error compared to LR and KNN in estimating fuel consumption on both simulated and operational data. The models have a mean relative prediction error of 0.3% on simulated data, and 4.2% on operational data.

Keywords: Artificial neural networks, fuel consumption, machine learning, regression, statistical tests.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 830

Authors: S. R. Nikhashemi, L. Haj Paim, Ali Khatibi

Abstract:

Structural Equation Modeling (SEM) was used to test a hypothesized model explaining Malaysian hypermarket customers’ perceptions of brand trust (BT), customer perceived value (CPV) and perceived service quality (PSQ) on building their brand loyalty (CBL) and generating positive word-of-mouth communication (WOM). Self-administered questionnaires were used to collect data from 374 Malaysian hypermarket customers from Mydin, Tesco, Aeon Big and Giant in Kuala Lumpur, a metropolitan city of Malaysia. The data strongly supported the model exhibiting that BT, CPV and PSQ are prerequisite factors in building customer brand loyalty, while PSQ has the strongest effect on prediction of customer brand loyalty compared to other factors. Besides, the present study suggests the effect of the aforementioned factors via customer brand loyalty strongly contributes to generate positive word of mouth communication.

Keywords: Brand trust, perceived value, perceived service quality, brand loyalty, positive word of mouth communication.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3041

Authors: M. Ebrahimi Shohani, S. M. Taheri, S. M. Golgoun

Abstract:

Environmental radiation dosimeter is a kind of detector that measures the dose of the radiation area. Dosimeter registers the radiation and converts it to the dose according to the calibration parameters. The limit of a dose is different at each radiation area and this limit should be notified and reported to the user and health physics department. The stochastic nature of radiation is the reason for the fluctuation of any gamma detector dosimetry. In this research we investigated Geiger-Muller type of dosimeter and tried to improve the dose measurement. Geiger-Muller dosimeter is a counter that converts registered radiation to the dose. Therefore, for better data analysis, it is necessary to apply an algorithm to smooth statistical variations of registered radiation. We proposed a method to smooth these fluctuations much more and also proposed a dynamic way to trace rapid changes of radiations. Results show that our method is fast and reliable method in comparison the traditional method.

Keywords: Geiger-Muller, radiation detection, smoothing algorithms, dosimeter, dose calculation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 466