Search results for: apache benchmark andreverse proxy

Authors: Deeman Yousif Mahmood, Mohammed Abdullah Hussein

Abstract:

The goal of a network-based intrusion detection system is to classify activities of network traffics into two major categories: normal and attack (intrusive) activities. Nowadays, data mining and machine learning plays an important role in many sciences; including intrusion detection system (IDS) using both supervised and unsupervised techniques. However, one of the essential steps of data mining is feature selection that helps in improving the efficiency, performance and prediction rate of proposed approach. This paper applies unsupervised K-means clustering algorithm with information gain (IG) for feature selection and reduction to build a network intrusion detection system. For our experimental analysis, we have used the new NSL-KDD dataset, which is a modified dataset for KDDCup 1999 intrusion detection benchmark dataset. With a split of 60.0% for the training set and the remainder for the testing set, a 2 class classifications have been implemented (Normal, Attack). Weka framework which is a java based open source software consists of a collection of machine learning algorithms for data mining tasks has been used in the testing process. The experimental results show that the proposed approach is very accurate with low false positive rate and high true positive rate and it takes less learning time in comparison with using the full features of the dataset with the same algorithm.

Keywords: Information Gain (IG), Intrusion Detection System (IDS), K-means Clustering, Weka.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2716

Authors: Chongya Song, Kang Yen, Alexander Pons, Jin Liu

Abstract:

In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.

Keywords: Consensus, curse of correlation, imbalanced classification, rank-based chain-mode ensemble.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 670

Authors: Jack R. McKenzie, Peter A. Appleby, Thomas House, Neil Walton

Abstract:

Cold-start is a notoriously difficult problem which can occur in recommendation systems, and arises when there is insufficient information to draw inferences for users or items. To address this challenge, a contextual bandit algorithm – the Fast Approximate Bayesian Contextual Cold Start Learning algorithm (FAB-COST) – is proposed, which is designed to provide improved accuracy compared to the traditionally used Laplace approximation in the logistic contextual bandit, while controlling both algorithmic complexity and computational cost. To this end, FAB-COST uses a combination of two moment projection variational methods: Expectation Propagation (EP), which performs well at the cold start, but becomes slow as the amount of data increases; and Assumed Density Filtering (ADF), which has slower growth of computational cost with data size but requires more data to obtain an acceptable level of accuracy. By switching from EP to ADF when the dataset becomes large, it is able to exploit their complementary strengths. The empirical justification for FAB-COST is presented, and systematically compared to other approaches on simulated data. In a benchmark against the Laplace approximation on real data consisting of over 670, 000 impressions from autotrader.co.uk, FAB-COST demonstrates at one point increase of over 16% in user clicks. On the basis of these results, it is argued that FAB-COST is likely to be an attractive approach to cold-start recommendation systems in a variety of contexts.

Keywords: Cold-start, expectation propagation, multi-armed bandits, Thompson sampling, variational inference.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 489

Authors: Huihai Wu, Xiaohui Liu

Abstract:

Using Dynamic Bayesian Networks (DBN) to model genetic regulatory networks from gene expression data is one of the major paradigms for inferring the interactions among genes. Averaging a collection of models for predicting network is desired, rather than relying on a single high scoring model. In this paper, two kinds of model searching approaches are compared, which are Greedy hill-climbing Search with Restarts (GSR) and Markov Chain Monte Carlo (MCMC) methods. The GSR is preferred in many papers, but there is no such comparison study about which one is better for DBN models. Different types of experiments have been carried out to try to give a benchmark test to these approaches. Our experimental results demonstrated that on average the MCMC methods outperform the GSR in accuracy of predicted network, and having the comparable performance in time efficiency. By proposing the different variations of MCMC and employing simulated annealing strategy, the MCMC methods become more efficient and stable. Apart from comparisons between these approaches, another objective of this study is to investigate the feasibility of using DBN modeling approaches for inferring gene networks from few snapshots of high dimensional gene profiles. Through synthetic data experiments as well as systematic data experiments, the experimental results revealed how the performances of these approaches can be influenced as the target gene network varies in the network size, data size, as well as system complexity.

Keywords: Genetic regulatory network, Dynamic Bayesian network, GSR, MCMC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1844

Authors: Haitao Yang, Jianming Lv, Fei Xu, Xintong Wang, Yilin Huang, Lanting Xia, Xuewu Zhu

Abstract:

Given a fixed fund, purchasing fewer hosts of higher capability or inversely more of lower capability is a must-be-made trade-off in practices for building a Hadoop big data platform. An exploratory study is presented for a Housing Big Data Platform project (HBDP), where typical big data computing is with SQL queries of aggregate, join, and space-time condition selections executed upon massive data from more than 10 million housing units. In HBDP, an empirical formula was introduced to predict the performance of host clusters potential for the intended typical big data computing, and it was shaped via a regression approach. With this empirical formula, it is easy to suggest an optimal cluster configuration. The investigation was based on a typical Hadoop computing ecosystem HDFS+Hive+Spark. A proper metric was raised to measure the performance of Hadoop clusters in HBDP, which was tested and compared with its predicted counterpart, on executing three kinds of typical SQL query tasks. Tests were conducted with respect to factors of CPU benchmark, memory size, virtual host division, and the number of element physical host in cluster. The research has been applied to practical cluster procurement for housing big data computing.

Keywords: Hadoop platform planning, optimal cluster scheme at fixed-fund, performance empirical formula, typical SQL query tasks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 789

Authors: Balimu Mwiya, Mundia Muya, Chabota Kaliba, Peter Mukalula

Abstract:

Factors affecting construction unit cost vary depending on a country’s political, economic, social and technological inclinations. Factors affecting construction costs have been studied from various perspectives. Analysis of cost factors requires an appreciation of a country’s practices. Identified cost factors provide an indication of a country’s construction economic strata. The purpose of this paper is to identify the essential factors that affect unit cost estimation and their breakdown using artificial neural networks. Twenty five (25) identified cost factors in road construction were subjected to a questionnaire survey and employing SPSS factor analysis the factors were reduced to eight. The 8 factors were analysed using neural network (NN) to determine the proportionate breakdown of the cost factors in a given construction unit rate. NN predicted that political environment accounted 44% of the unit rate followed by contractor capacity at 22% and financial delays, project feasibility and overhead & profit each at 11%. Project location, material availability and corruption perception index had minimal impact on the unit cost from the training data provided. Quantified cost factors can be incorporated in unit cost estimation models (UCEM) to produce more accurate estimates. This can create improvements in the cost estimation of infrastructure projects and establish a benchmark standard to assist the process of alignment of work practises and training of new staff, permitting the on-going development of best practises in cost estimation to become more effective.

Keywords: Construction cost factors, neural networks, roadworks, Zambian Construction Industry.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3785

Authors: Ambalika Ekka

Abstract:

In today’s world, the growing demand for urban built forms has resulted in the production and consumption of building materials i.e. embodied energy in building construction, leading to pollution and greenhouse gas (GHG) emissions. Therefore, new buildings will offer a unique opportunity to implement more energy efficient building without compromising on building performance of the building. Embodied energy of building materials forms major contribution to embodied energy in buildings. The paper results in an approach towards designing an energy efficient apartment building through embodied energy assessment. This paper discusses the trend of residential development in Rourkela, which includes three case studies of the contemporary houses, followed by architectural elements, number of storeys, predominant material use and plot sizes using primary data. It results in identification of predominant material used and other characteristics in urban area. Further, the embodied energy coefficients of various dominant building materials and alternative materials manufactured in Indian Industry is taken in consideration from secondary source i.e. literature study. The paper analyses the embodied energy by estimating materials and operational energy of proposed building followed by altering the specifications of the materials based on the building components i.e. walls, flooring, windows, insulation and roof through res build India software and comparison of different options is assessed with consideration of sustainable parameters. This paper results that autoclaved aerated concrete block only reaches the energy performance Index benchmark i.e. 69.35 kWh/m² yr i.e. by saving 4% of operational energy and as embodied energy has no particular index, out of all materials it has the highest EE 23206202.43  MJ.

Keywords: Energy efficient, embodied energy, energy performance index, building materials.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 936

Authors: Pankaj Gupta, Amit Kumar Srivastava, Nitesh Pandey

Abstract:

This article explores the domain of generative design in order to enhance the development of robot designs for innovative and efficient maintenance approaches for tall buildings. This study aims to optimize the design of robotic hands by focusing on minimizing mass and volume while ensuring they can withstand the specified pressure with equal strength. The research procedure is structured and systematic. The purpose of optimization is to enhance the efficiency of the robot and reduce the manufacturing expenses. The project seeks to investigate the application of generative design in order to optimize products. Autodesk Fusion 360 offers the capability to immediately apply the generative design functionality to the solid model. The effort involved creating a solid model of the Smart Glass Cleaning Robot and optimizing one of its components, the Hand, using generative techniques. The article has thoroughly examined the designs, outcomes, and procedure. These loads serve as a benchmark for creating designs that can endure the necessary level of pressure and preserve their structural integrity. The efficacy of the generative design process is contingent upon the selection of materials, as different materials possess distinct physical attributes. The study utilizes five different materials, namely Steel, Stainless Steel, Titanium, Aluminum, and CFRP (Carbon Fiber Reinforced Polymer), in order to investigate a range of design possibilities.

Keywords: Generative design, mass and volume optimization, material strength analysis, generative design, smart glass cleaning robot.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 102

Authors: Yu-Cheng Chou, Po Ting Lin

Abstract:

The network of delivering commodities has been an important design problem in our daily lives and many transportation applications. The delivery performance is evaluated based on the system reliability of delivering commodities from a source node to a sink node in the network. The system reliability is thus maximized to find the optimal routing. However, the design problem is not simple because (1) each path segment has randomly distributed attributes; (2) there are multiple commodities that consume various path capacities; (3) the optimal routing must successfully complete the delivery process within the allowable time constraints. In this paper, we want to focus on the design optimization of the Multi-State Flow Network (MSFN) for multiple commodities. We propose an efficient approach to evaluate the system reliability in the MSFN with respect to randomly distributed path attributes and find the optimal routing subject to the allowable time constraints. The delivery rates, also known as delivery currents, of the path segments are evaluated and the minimal-current arcs are eliminated to reduce the complexity of the MSFN. Accordingly, the correct optimal routing is found and the worst-case reliability is evaluated. It has been shown that the reliability of the optimal routing is at least higher than worst-case measure. Two benchmark examples are utilized to demonstrate the proposed method. The comparisons between the original and the reduced networks show that the proposed method is very efficient.

Keywords: Multiple Commodities, Multi-State Flow Network (MSFN), Time Constraints, Worst-Case Reliability (WCR)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1411

Authors: Esam I. Jassim, Mohamed M. Awad

Abstract:

Natural gas flow contains undesirable solid particles, liquid condensation, and/or oil droplets and requires reliable removing equipment to perform filtration. Recent natural gas processing applications are demanded compactness and reliability of process equipment. Since conventional means are sophisticated in design, poor in efficiency, and continue lacking robust, a supersonic nozzle has been introduced as an alternative means to meet such demands. A 3-D Convergent-Divergent Nozzle is simulated using commercial Code for pressure ratio (NPR) varies from 1.2 to 2. Six different shapes of nozzle are numerically examined to illustrate the position of shock-wave as such spot could be considered as a benchmark of particle separation. Rectangle, triangle, circular, elliptical, pentagon, and hexagon nozzles are simulated using Fluent Code with all have same cross-sectional area. The simple one-dimensional inviscid theory does not describe the actual features of fluid flow precisely as it ignores the impact of nozzle configuration on the flow properties. CFD Simulation results, however, show that nozzle geometry influences the flow structures including location of shock wave. The CFD analysis predicts shock appearance when p01/pa>1.2 for almost all geometry and locates at the lower area ratio (Ae/At). Simulation results showed that shock wave in Elliptical nozzle has the farthest distance from the throat among the others at relatively small NPR. As NPR increases, hexagon would be the farthest. The numerical result is compared with available experimental data and has shown good agreement in terms of shock location and flow structure.

Keywords: CFD, Particle Separation, Shock wave, Supersonic Nozzle.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3201

Authors: Padmanabhan Balasubramanian, Ryuta Arisaka

Abstract:

Factoring Boolean functions is one of the basic operations in algorithmic logic synthesis. A novel algebraic factorization heuristic for single-output combinatorial logic functions is presented in this paper and is developed based on the set theory paradigm. The impact of factoring is analyzed mainly from a low power design perspective for standard cell based digital designs in this paper. The physical implementation of a number of MCNC/IWLS combinational benchmark functions and sub-functions are compared before and after factoring, based on a simple technology mapping procedure utilizing only standard gate primitives (readily available as standard cells in a technology library) and not cells corresponding to optimized complex logic. The power results were obtained at the gate-level by means of an industry-standard power analysis tool from Synopsys, targeting a 130nm (0.13μm) UMC CMOS library, for the typical case. The wire-loads were inserted automatically and the simulations were performed with maximum input activity. The gate-level simulations demonstrate the advantage of the proposed factoring technique in comparison with other existing methods from a low power perspective, for arbitrary examples. Though the benchmarks experimentation reports mixed results, the mean savings in total power and dynamic power for the factored solution over a non-factored solution were 6.11% and 5.85% respectively. In terms of leakage power, the average savings for the factored forms was significant to the tune of 23.48%. The factored solution is expected to better its non-factored counterpart in terms of the power-delay product as it is well-known that factoring, in general, yields a delay-efficient multi-level solution.

Keywords: Factorization, Set theory, Logic function, Standardcell based design, Low power.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1750

Authors: Y. Z. Wu, Z. Dong, S. K. You

Abstract:

Global approximation using metamodel for complex mathematical function or computer model over a large variable domain is often needed in sensibility analysis, computer simulation, optimal control, and global design optimization of complex, multiphysics systems. To overcome the limitations of the existing response surface (RS), surrogate or metamodel modeling methods for complex models over large variable domain, a new adaptive and regressive RS modeling method using quadratic functions and local area model improvement schemes is introduced. The method applies an iterative and Latin hypercube sampling based RS update process, divides the entire domain of design variables into multiple cells, identifies rougher cells with large modeling error, and further divides these cells along the roughest dimension direction. A small number of additional sampling points from the original, expensive model are added over the small and isolated rough cells to improve the RS model locally until the model accuracy criteria are satisfied. The method then combines local RS cells to regenerate the global RS model with satisfactory accuracy. An effective RS cells sorting algorithm is also introduced to improve the efficiency of model evaluation. Benchmark tests are presented and use of the new metamodeling method to replace complex hybrid electrical vehicle powertrain performance model in vehicle design optimization and optimal control are discussed.

Keywords: Global approximation, polynomial response surface, domain decomposition, domain combination, multiphysics modeling, hybrid powertrain optimization

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1869

Authors: Danielle Shackley, Yetunde Folajimi

Abstract:

As more people turn to the internet seeking health related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores of text, ranging from positive, neutral and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing, tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process, and substituting the Naive Bayes for a deep learning neural network model.

Keywords: Sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 380

Authors: Kasra Majbouri Yazdi, Adel Majbouri Yazdi, Saeid Khodayi, Jingyu Hou, Wanlei Zhou, Saeed Saedy

Abstract:

Fake news and false information are big challenges of all types of media, especially social media. There is a lot of false information, fake likes, views and duplicated accounts as big social networks such as Facebook and Twitter admitted. Most information appearing on social media is doubtful and in some cases misleading. They need to be detected as soon as possible to avoid a negative impact on society. The dimensions of the fake news datasets are growing rapidly, so to obtain a better result of detecting false information with less computation time and complexity, the dimensions need to be reduced. One of the best techniques of reducing data size is using feature selection method. The aim of this technique is to choose a feature subset from the original set to improve the classification performance. In this paper, a feature selection method is proposed with the integration of K-means clustering and Support Vector Machine (SVM) approaches which work in four steps. First, the similarities between all features are calculated. Then, features are divided into several clusters. Next, the final feature set is selected from all clusters, and finally, fake news is classified based on the final feature subset using the SVM method. The proposed method was evaluated by comparing its performance with other state-of-the-art methods on several specific benchmark datasets and the outcome showed a better classification of false information for our work. The detection performance was improved in two aspects. On the one hand, the detection runtime process decreased, and on the other hand, the classification accuracy increased because of the elimination of redundant features and the reduction of datasets dimensions.

Keywords: Fake news detection, feature selection, support vector machine, K-means clustering, machine learning, social media.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4379

Authors: Gozel Judakova, Markus Bause

Abstract:

We present and analyze reliable numerical techniques for simulating complex flow and transport phenomena related to natural gas transportation in pipelines. Such kind of problems are of high interest in the field of petroleum and environmental engineering. Modeling and understanding natural gas flow and transformation processes during transportation is important for the sake of physical realism and the design and operation of pipeline systems. In our approach a two fluid flow model based on a system of coupled hyperbolic conservation laws is considered for describing natural gas flow undergoing hydratization. The accurate numerical approximation of two-phase gas flow remains subject of strong interest in the scientific community. Such hyperbolic problems are characterized by solutions with steep gradients or discontinuities, and their approximation by standard finite element techniques typically gives rise to spurious oscillations and numerical artefacts. Recently, stabilized and discontinuous Galerkin finite element techniques have attracted researchers’ interest. They are highly adapted to the hyperbolic nature of our two-phase flow model. In the presentation a streamline upwind Petrov-Galerkin approach and a discontinuous Galerkin finite element method for the numerical approximation of our flow model of two coupled systems of Euler equations are presented. Then the efficiency and reliability of stabilized continuous and discontinous finite element methods for the approximation is carefully analyzed and the potential of the either classes of numerical schemes is investigated. In particular, standard benchmark problems of two-phase flow like the shock tube problem are used for the comparative numerical study.

Keywords: Discontinuous Galerkin method, Euler system, inviscid two-fluid model, streamline upwind Petrov-Galerkin method, two-phase flow.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 750

Authors: Yousef Swesi, Asia Elmeshergi, Abdelati Elalem, Walid Alfoghy

Abstract:

This paper involves a study of the heavy metal pollution of the soils around one of cement plants in Libya called Suk-Alkhameas and surrounding urban areas caused by cement kiln dust (CKD) emitted. Samples of soil was collected from sites at four directions around the cement factory at distances 250m, 1000m, and 3000m from the factory and at (0-10)cm deep in the soil. These samples are analyzed for Fe (iii), Zn(ii), and Pb (ii) as major pollutants. These values are compared with soils at 25 Km distances from the factory as a reference or control samples. The results show that the concentration of Fe ions in the surface soil was within the acceptable range of 1000ppm. However, for Zn and Pb ions the concentrations at the east and north sides of the factory were found six fold higher than the benchmark level. This high value was attributed to the wind which blows usually from south to north and from west to east. This work includes an investigation of the adsorption isotherms and adsorption efficiency of CKD as adsorbent of heavy metal ions (Fe (iii), Zn(ii), and Pb(ii)) from the polluted soils of Suk-Alkameas city. The investigation was conducted in batch and fixed bed column flow technique. The adsorption efficiency of the studied heavy metals ions removals onto CKD depends on the pH of the solution. The optimum pH values are found to be in the ranges of 8-10 and decreases at lower pH values. The removal efficiency of these heavy metals ions ranged from 93% for Pb, 94% for Zn, and 98% for Fe ions for 10 g.l^-1 adsorbent concentration. The maximum removal efficiency of these ions was achieved at 50-60 minutes contact times at which equilibrium is reached. Fixed bed column experimental measurements are also made to evaluate CKD as an adsorbent for the heavy metals. Results obtained are with good agreement with Langmuir and Drachsal assumption of multilayer formation on the adsorbent surface.

Keywords: Adsorption, Cement Kiln dust (CKD & CAC), Isotherms, Zn and Pb ions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2345

Authors: Maumita Bhattacharya

Abstract:

Evolutionary Algorithms are population-based, stochastic search techniques, widely used as efficient global optimizers. However, many real life optimization problems often require finding optimal solution to complex high dimensional, multimodal problems involving computationally very expensive fitness function evaluations. Use of evolutionary algorithms in such problem domains is thus practically prohibitive. An attractive alternative is to build meta models or use an approximation of the actual fitness functions to be evaluated. These meta models are order of magnitude cheaper to evaluate compared to the actual function evaluation. Many regression and interpolation tools are available to build such meta models. This paper briefly discusses the architectures and use of such meta-modeling tools in an evolutionary optimization context. We further present two evolutionary algorithm frameworks which involve use of meta models for fitness function evaluation. The first framework, namely the Dynamic Approximate Fitness based Hybrid EA (DAFHEA) model [14] reduces computation time by controlled use of meta-models (in this case approximate model generated by Support Vector Machine regression) to partially replace the actual function evaluation by approximate function evaluation. However, the underlying assumption in DAFHEA is that the training samples for the metamodel are generated from a single uniform model. This does not take into account uncertain scenarios involving noisy fitness functions. The second model, DAFHEA-II, an enhanced version of the original DAFHEA framework, incorporates a multiple-model based learning approach for the support vector machine approximator to handle noisy functions [15]. Empirical results obtained by evaluating the frameworks using several benchmark functions demonstrate their efficiency

Keywords: Meta model, Evolutionary algorithm, Stochastictechnique, Fitness function, Optimization, Support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2012

Authors: Tim Dunne, Weicheng Li, Chris Cheng, Qi Peng

Abstract:

Deeper petroleum reservoirs are more challenging to exploit due to the high hardness and abrasive characteristics of the formations. A cutting structure that consists of particulate diamond impregnated in a supporting matrix is found to be effective. Diamond impregnated bits are favored in these applications due to the higher thermal stability of the matrix material. The diamond particles scour or abrade away concentric grooves while the rock formation adjacent to the grooves is fractured and removed. The matrix material supporting the diamond will wear away, leaving the superficial dull diamonds to fall out. The matrix material wear will expose other embedded intact sharp diamonds to continue the operation. Minimizing the erosion effect on the matrix is an important design consideration, as the life of the bit can be extended by preventing early diamond pull-out. A careful balancing of the key parameters, such as diamond concentration, tungsten carbide and metal binder must be considered during development. Described herein is the design of experiment for developing and lab testing 8 unique samples. ASTM B611 wear testing was performed to benchmark the material performance against baseline products, with further scanning electron microscopy and microhardness evaluations. The recipe S5 with diamond 25/35 mesh size, narrow size distribution, high concentration blended with fine tungsten carbide and Co-Cu-Fe-P metal binder has the best performance, which shows 19% improvement in the ASTM B611 wear test compared with the reference material. In the field trial, the rate of penetration (ROP) is measured as 15 m/h, compared to 9.5, 7.8, and 6.8 m/h of other commercial impregnated bits in the same formation. A second round of optimizing recipe S5 for a higher wear resistance is further reported.

Keywords: Diamond containing material, grit hot press insert, impregnated diamond, insert, rate of penetration, ultrahard formation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 313

Authors: Zhen Cheng, Xinyu Dai, Shujian Huang, Jiajun Chen

Abstract:

Recently, explanatory natural language inference has attracted much attention for the interpretability of logic relationship prediction, which is also known as explanation generation for Natural Language Inference (NLI). Existing explanation generators based on discriminative Encoder-Decoder architecture have achieved noticeable results. However, we find that these discriminative generators usually generate explanations with correct evidence but incorrect logic semantic. It is due to that logic information is implicitly encoded in the premise-hypothesis pairs and difficult to model. Actually, logic information identically exists between premise-hypothesis pair and explanation. And it is easy to extract logic information that is explicitly contained in the target explanation. Hence we assume that there exists a latent space of logic information while generating explanations. Specifically, we propose a generative model called Variational Explanation Generator (VariationalEG) with a latent variable to model this space. Training with the guide of explicit logic information in target explanations, latent variable in VariationalEG could capture the implicit logic information in premise-hypothesis pairs effectively. Additionally, to tackle the problem of posterior collapse while training VariaztionalEG, we propose a simple yet effective approach called Logic Supervision on the latent variable to force it to encode logic information. Experiments on explanation generation benchmark—explanation-Stanford Natural Language Inference (e-SNLI) demonstrate that the proposed VariationalEG achieves significant improvement compared to previous studies and yields a state-of-the-art result. Furthermore, we perform the analysis of generated explanations to demonstrate the effect of the latent variable.

Keywords: Natural Language Inference, explanation generation, variational auto-encoder, generative model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 617

Authors: Xiang Zhang, Daohong Yang, Ziyuan Wu, Lei Li, Wanting Zhou

Abstract:

Visual Simultaneous Localization and Mapping (VSLAM) uses cameras to gather information in unknown environments to achieve simultaneous localization and mapping of the environment. This technology has a wide range of applications in autonomous driving, virtual reality, and other related fields. Currently, the research advancements related to VSLAM can maintain high accuracy in static environments. But in dynamic environments, the presence of moving objects in the scene can reduce the stability of the VSLAM system, leading to inaccurate localization and mapping, or even system failure. In this paper, a robust VSLAM method was proposed to effectively address the challenges in dynamic environments. We proposed a dynamic region removal scheme based on a semantic segmentation neural network and geometric constraints. Firstly, a semantic segmentation neural network is used to extract the prior active motion region, prior static region, and prior passive motion region in the environment. Then, the lightweight frame tracking module initializes the transform pose between the previous frame and the current frame on the prior static region. A motion consistency detection module based on multi-view geometry and scene flow is used to divide the environment into static regions and dynamic regions. Thus, the dynamic object region was successfully eliminated. Finally, only the static region is used for tracking thread. Our research is based on the ORBSLAM3 system, which is one of the most effective VSLAM systems available. We evaluated our method on the TUM RGB-D benchmark and the results demonstrate that the proposed VSLAM method improves the accuracy of the original ORBSLAM3 by 70%˜98.5% under a high dynamic environment.

Keywords: Dynamic scene, dynamic visual SLAM, semantic segmentation, scene flow, VSLAM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 79

Authors: Daniele Losanno, H. A. Hadad, Giorgio Serino

Abstract:

This paper presents a numerical investigation on the seismic performance of a benchmark bridge with different optimal isolation systems under near fault ground motion. Usually, very large displacements make seismic isolation an unfeasible solution due to boundary conditions, especially in case of existing bridges or high risk seismic regions. Hence, near-fault ground motions are most likely to affect either structures with long natural period range like isolated structures or structures sensitive to velocity content such as viscously damped structures. The work is aimed at analyzing the seismic performance of a three-span continuous bridge designed with different isolation systems having different levels of damping. The case study was analyzed in different configurations including: (a) simply supported, (b) isolated with lead rubber bearings (LRBs), (c) isolated with rubber isolators and 10% classical damping (HDLRBs), and (d) isolated with rubber isolators and 70% supplemental damping ratio. Case (d) represents an alternative control strategy that combines the effect of seismic isolation with additional supplemental damping trying to take advantages from both solutions. The bridge is modeled in SAP2000 and solved by time history direct-integration analyses under a set of six recorded near-fault ground motions. In addition to this, a set of analysis under Italian code provided seismic action is also conducted, in order to evaluate the effectiveness of the suggested optimal control strategies under far field seismic action. Results of the analysis demonstrated that an isolated bridge equipped with HDLRBs and a total equivalent damping ratio of 70% represents a very effective design solution for both mitigation of displacement demand at the isolation level and base shear reduction in the piers also in case of near fault ground motion.

Keywords: Isolated bridges, optimal design, near-fault motion, supplemental damping.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1215

Authors: Dhananjay C. Joshi, Jung-Hsin Lin

Abstract:

Protein-protein interactions (PPI) play a crucial role in many biological processes such as cell signalling, transcription, translation, replication, signal transduction, and drug targeting, etc. Structural information about protein-protein interaction is essential for understanding the molecular mechanisms of these processes. Structures of protein-protein complexes are still difficult to obtain by biophysical methods such as NMR and X-ray crystallography, and therefore protein-protein docking computation is considered an important approach for understanding protein-protein interactions. However, reliable prediction of the protein-protein complexes is still under way. In the past decades, several grid-based docking algorithms based on the Katchalski-Katzir scoring scheme were developed, e.g., FTDock, ZDOCK, HADDOCK, RosettaDock, HEX, etc. However, the success rate of protein-protein docking prediction is still far from ideal. In this work, we first propose a more practical measure for evaluating the success of protein-protein docking predictions,the rate of first success (RFS), which is similar to the concept of mean first passage time (MFPT). Accordingly, we have assessed the ZDOCK bound and unbound benchmarks 2.0 and 3.0. We also createda new benchmark set for protein-protein docking predictions, in which the complexes have experimentally determined binding affinity data. We performed free energy calculation based on the solution of non-linear Poisson-Boltzmann equation (nlPBE) to improve the binding mode prediction. We used the well-studied thebarnase-barstarsystem to validate the parameters for free energy calculations. Besides,thenlPBE-based free energy calculations were conducted for the badly predicted cases by ZDOCK and ZRANK. We found that direct molecular mechanics energetics cannot be used to discriminate the native binding pose from the decoys.Our results indicate that nlPBE-based calculations appeared to be one of the promising approaches for improving the success rate of binding pose predictions.

Keywords: protein-protein docking, protein-protein interaction, molecular mechanics energetics, Poisson-Boltzmann calculations

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1753

Authors: A. Abdulla Khairi Mohamed, Mohamed Gamal Abdelmonem, Gehan Selim

Abstract:

Walkability in civic and public spaces in Libyan cities is challenging due to the lack of accessibility design, informal merging into car traffic, and the general absence of adequate urban and space planning. The lack of accessible and pedestrian-friendly public spaces in Libyan cities has emerged as a major concern for the government if it is to develop smart and sustainable spaces for the 21st century. A walkable urban space has become a driver for urban development and redistribution of land use to ensure pedestrian and walkable routes between sites of living and workplaces. The characteristics of urban open space in the city centre play a main role in attracting people to walk when attending their daily needs, recreation and daily sports. There is significant gap in the understanding of perceptions, feasibility and capabilities of Libyan urban space to accommodate enhance or support the smart design of a walkable pedestrian-friendly environment that is safe and accessible to everyone. The paper aims to undertake observations of walkability and walkable space in the city of Tripoli as a benchmark for Libyan cities; assess the validity and consistency of the seven principal aspects of smart design, safety, accessibility and 51 factors that affect the walkability in open urban space in Tripoli, through the analysis of 10 local urban spaces experts (town planner, architect, transport engineer and urban designer); and explore user groups’ perceptions of accessibility in walkable spaces in Libyan cities through questionnaires. The study sampled 200 respondents in 2015-16. The results of this study are useful for urban planning, to classify the walkable urban space elements which affect to improve the level of walkability in the Libyan cities and create sustainable and liveable urban spaces.

Keywords: Walkability, sustainability, liveability, accessibility, safety.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1345

Authors: A. Pensiri, K. Nantaporn, P. Parichut

Abstract:

Tourism is very important to the economy of many countries due to the large contribution in the areas of employment and income generation. However, the rapid growth of tourism can also be considered as one of the major uses of water user, and therefore also have a significant and detrimental impact on the environment. Guest behavior in water usage can be used to manage water in hotels for sustainable water resources management. This research presents a study of hotel guest water usage behavior at two hotels, namely Hotel A (located in Kathu district) and Hotel B (located in Muang district) in Phuket Province, Thailand, as case studies. Primary and secondary data were collected from the hotel manager through interview and questionnaires. The water flow rate was measured in-situ from each water supply device in the standard room type at each hotel, including hand washing faucets, bathroom faucets, shower and toilet flush. For the interview, the majority of respondents (n = 204 for Hotel A and n = 244 for Hotel B) were aged between 21 years and 30 years (53% for Hotel A and 65% for Hotel B) and the majority were foreign (78% in Hotel A, and 92% in Hotel B) from American, France and Austria for purposes of tourism (63% in Hotel A, and 55% in Hotel B). The data showed that water consumption ranged from 188 litres to 507 liters, and 383 litres to 415 litres per overnight guest in Hotel A and Hotel B (n = 244), respectively. These figures exceed the water efficiency benchmark set for Tropical regions by the International Tourism Partnership (ITP). It is recommended that guest water saving initiatives should be implemented at hotels. Moreover, the results showed that guests have high satisfaction for the hotels, the front office service reveal the top rates of average score of 4.35 in Hotel A and 4.20 in Hotel B, respectively, while the luxury decoration and room cleanliness exhibited the second satisfaction scored by the guests in Hotel A and B, respectively. On the basis of this information, the findings can be very useful to improve customer service satisfaction and pay attention to this particular aspect for better hotel management.

Keywords: Hotel, tourism, Phuket, water usage.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2245

Authors: Abdulaziz Alsadhan, Naveed Khan

Abstract:

In recent years intrusions on computer network are the major security threat. Hence, it is important to impede such intrusions. The hindrance of such intrusions entirely relies on its detection, which is primary concern of any security tool like Intrusion detection system (IDS). Therefore, it is imperative to accurately detect network attack. Numerous intrusion detection techniques are available but the main issue is their performance. The performance of IDS can be improved by increasing the accurate detection rate and reducing false positive. The existing intrusion detection techniques have the limitation of usage of raw dataset for classification. The classifier may get jumble due to redundancy, which results incorrect classification. To minimize this problem, Principle component analysis (PCA), Linear Discriminant Analysis (LDA) and Local Binary Pattern (LBP) can be applied to transform raw features into principle features space and select the features based on their sensitivity. Eigen values can be used to determine the sensitivity. To further classify, the selected features greedy search, back elimination, and Particle Swarm Optimization (PSO) can be used to obtain a subset of features with optimal sensitivity and highest discriminatory power. This optimal feature subset is used to perform classification. For classification purpose, Support Vector Machine (SVM) and Multilayer Perceptron (MLP) are used due to its proven ability in classification. The Knowledge Discovery and Data mining (KDD’99) cup dataset was considered as a benchmark for evaluating security detection mechanisms. The proposed approach can provide an optimal intrusion detection mechanism that outperforms the existing approaches and has the capability to minimize the number of features and maximize the detection rates.

Keywords: Particle Swarm Optimization (PSO), Principle component analysis (PCA), Linear Discriminant Analysis (LDA), Local Binary Pattern (LBP), Support Vector Machine (SVM), Multilayer Perceptron (MLP).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2707

Authors: Ebipatei Victoria Tunyan, T. A. Cao, Cheol Young Ock

Abstract:

Detecting subjectively biased statements is a vital task. This is because this kind of bias, when present in the text or other forms of information dissemination media such as news, social media, scientific texts, and encyclopedias, can weaken trust in the information and stir conflicts amongst consumers. Subjective bias detection is also critical for many Natural Language Processing (NLP) tasks like sentiment analysis, opinion identification, and bias neutralization. Having a system that can adequately detect subjectivity in text will boost research in the above-mentioned areas significantly. It can also come in handy for platforms like Wikipedia, where the use of neutral language is of importance. The goal of this work is to identify the subjectively biased language in text on a sentence level. With machine learning, we can solve complex AI problems, making it a good fit for the problem of subjective bias detection. A key step in this approach is to train a classifier based on BERT (Bidirectional Encoder Representations from Transformers) as upstream model. BERT by itself can be used as a classifier; however, in this study, we use BERT as data preprocessor as well as an embedding generator for a Bi-LSTM (Bidirectional Long Short-Term Memory) network incorporated with attention mechanism. This approach produces a deeper and better classifier. We evaluate the effectiveness of our model using the Wiki Neutrality Corpus (WNC), which was compiled from Wikipedia edits that removed various biased instances from sentences as a benchmark dataset, with which we also compare our model to existing approaches. Experimental analysis indicates an improved performance, as our model achieved state-of-the-art accuracy in detecting subjective bias. This study focuses on the English language, but the model can be fine-tuned to accommodate other languages.

Keywords: Subjective bias detection, machine learning, BERT–BiLSTM–Attention, text classification, natural language processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 759

Authors: Haj Najafi Leila, Tehranizadeh Mohsen

Abstract:

Dependencies between diverse factors involved in probabilistic seismic loss evaluation are recognized to be an imperative issue in acquiring accurate loss estimates. Dependencies among component damage costs could be taken into account considering two partial distinct states of independent or perfectly-dependent for component damage states; however, in our best knowledge, there is no available procedure to take account of loss dependencies in story level. This paper attempts to present a method called "modal cost superposition method" for decoupling story damage costs subjected to earthquake ground motions dealt with closed form differential equations between damage cost and engineering demand parameters which should be solved in complex system considering all stories' cost equations by the means of the introduced "substituted matrixes of mass and stiffness". Costs are treated as probabilistic variables with definite statistic factors of median and standard deviation amounts and a presumed probability distribution. To supplement the proposed procedure and also to display straightforwardness of its application, one benchmark study has been conducted. Acceptable compatibility has been proven for the estimated damage costs evaluated by the new proposed modal and also frequently used stochastic approaches for entire building; however, in story level, insufficiency of employing modification factor for incorporating occurrence probability dependencies between stories has been revealed due to discrepant amounts of dependency between damage costs of different stories. Also, more dependency contribution in occurrence probability of loss could be concluded regarding more compatibility of loss results in higher stories than the lower ones, whereas reduction in incorporation portion of cost modes provides acceptable level of accuracy and gets away from time consuming calculations including some limited number of cost modes in high mode situation.

Keywords: Dependency, story-cost, cost modes, engineering demand parameter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 977

Authors: Ahmad B. Habieb, Gabriele Milani, Tavio Tavio, Federico Milani

Abstract:

Housings in developing countries have often inadequate seismic protection, particularly for masonry. People choose this type of structure since the cost and application are relatively cheap. Seismic protection of masonry remains an interesting issue among researchers. In this study, we develop a low-cost seismic isolation system for masonry using fiber reinforced elastomeric isolators. The elastomer proposed consists of few layers of rubber pads and fiber lamina, making it lower in cost comparing to the conventional isolators. We present a finite element (FE) analysis to predict the behavior of the low cost rubber isolators undergoing moderate deformations. The FE model of the elastomer involves a hyperelastic material property for the rubber pad. We adopt a Yeoh hyperelasticity model and estimate its coefficients through the available experimental data. Having the shear behavior of the elastomers, we apply that isolation system onto small masonry housing. To attach the isolators on the building, we model the shear behavior of the isolation system by means of a damped nonlinear spring model. By this attempt, the FE analysis becomes computationally inexpensive. Several ground motion data are applied to observe its sensitivity. Roof acceleration and tensile damage of walls become the parameters to evaluate the performance of the isolators. In this study, a concrete damage plasticity model is used to model masonry in the nonlinear range. This tool is available in the standard package of Abaqus FE software. Finally, the results show that the low-cost isolators proposed are capable of reducing roof acceleration and damage level of masonry housing. Through this study, we are also capable of monitoring the shear deformation of isolators during seismic motion. It is useful to determine whether the isolator is applicable. According to the results, the deformations of isolators on the benchmark one story building are relatively small.

Keywords: Masonry, low cost elastomeric isolator, finite element analysis, hyperelasticity, damped non-linear spring, concrete damage plasticity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1137

Authors: Theingi Shwe, Riken Homma, Kazuhisa Iki, Juko Ito

Abstract:

The growing cities of the developing country are characterized by rapid growth and poor infrastructure management inviting and accelerating relative environmental problems. Even though the movements of the sustainability had already been developed around the world, it is still increasing in the developing countries to plant sustainable practices. Aligned with the sustainable development actions, many sustainable assessment tools are also developed to rate and evaluate the sustainability performances through the building to community level. Among them, CASBEE is developed by Japanese organizations and is recognized as one of the international well-known assessment tools. The main purpose of the study is to find out the potential of CASBEE tool reflecting sustainability city level performances in developing countries. The research framework was designed with three major phases: Quantitative Approach, Qualitative Approach and Evaluation Reflection. The first two approaches were based on the investigation of tool’s contents and indicators by means of three sustainable dimensions and sustainability categories. To know the reality and reflection on developing country, Pathein City from Myanmar was selected and evaluated by 2012 version of CASBEE for Cities. The evaluation practices went through assigned indicators and the evaluation outcome presents the performances of Pathein city’s environmental efficiency as a very good in current conditions. The results of this study indicate that the indicators of this tool have balance coverage among three dimensions of sustainability but it has not yet counted enough for some indicators like location, infrastructure and institution which are relative to society dimension. In the developing countries’ cities, the most critical issues on development such as affordable housing and heritage preservation which are already planted in Pathein City but the tool does not account for those issues. Moreover, in some of the indicators, the benchmark and the weighting coefficient are strongly linked to the system birth region. By means of this study, it can be stated that CASBEE for Cities would be potential for delivering sustainable city level development in developing country especially in Myanmar along with further inclusion of the indicators.

Keywords: Assessment tool, CASBEE, developing country, Myanmar, Pathein city, sustainable development.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1036

Authors: Mohammad R. Jalali, Mohammad M. Jalali

Abstract:

The earliest theories of sloshing waves and solitary waves based on potential theory idealisations and irrotational flow have been extended to be applicable to more realistic domains. To this end, the computational fluid dynamics (CFD) methods are widely used. Three-dimensional CFD methods such as Navier-Stokes solvers with volume of fluid treatment of the free surface and Navier-Stokes solvers with mappings of the free surface inherently impose high computational expense; therefore, considerable effort has gone into developing depth-averaged approaches. Examples of such approaches include Green–Naghdi (GN) equations. In Cartesian system, GN velocity profile depends on horizontal directions, x-direction and y-direction. The effect of vertical direction (z-direction) is also taken into consideration by applying weighting function in approximation. GN theory considers the effect of vertical acceleration and the consequent non-hydrostatic pressure. Moreover, in GN theory, the flow is rotational. The present study illustrates the application of GN equations to propagation of sloshing waves and solitary waves. For this purpose, GN equations solver is verified for the benchmark tests of Gaussian hump sloshing and solitary wave propagation in shallow basins. Analysis of the free surface sloshing of even harmonic components of an initial Gaussian hump demonstrates that the GN model gives predictions in satisfactory agreement with the linear analytical solutions. Discrepancies between the GN predictions and the linear analytical solutions arise from the effect of wave nonlinearities arising from the wave amplitude itself and wave-wave interactions. Numerically predicted solitary wave propagation indicates that the GN model produces simulations in good agreement with the analytical solution of the linearised wave theory. Comparison between the GN model numerical prediction and the result from perturbation analysis confirms that nonlinear interaction between solitary wave and a solid wall is satisfactorilly modelled. Moreover, solitary wave propagation at an angle to the x-axis and the interaction of solitary waves with each other are conducted to validate the developed model.

Keywords: Even harmonic components of sloshing waves, Green–Naghdi equations, nonlinearity, solitary waves.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 828