Search results for: analytical network design model

Authors: Hyun-Woo Jun, Tae-Chul Jeong, Huai-Cong Liu, Ju Lee

Abstract:

The paper presents the electromagnetic-thermal flow coupled analysis of permanent magnet synchronous motor (PMSM) which has cooling channel in stator core for forced air cooling. Unlike the general PMSM design, to achieve ohmic loss reduction for high efficiency, cooling channel actively used in the stator core. Equivalent thermal network model was made to analyze the effect of the formation of the additional flow path in the core. According to the shape and position changing of the channel design, electromagnetic-thermal coupled analysis results were reviewed.

Keywords: coupled problems, electric motors, equivalent circuits, fluid flow, thermal analysis

Procedia PDF Downloads 620

Authors: Elias K. Maragos, Petros E. Maravelakis

Abstract:

In Dynamic Data Envelopment Analysis (DDEA), which is a subfield of Data Envelopment Analysis (DEA), the productivity of Decision Making Units (DMUs) is considered in relation to time. In this case, as it is accepted by the most of the researchers, there are outputs, which are produced by a DMU to be used as inputs in a future time. Those outputs are known as intermediates. The common models, in DDEA, do not take into account the shape of the distribution of those inputs, outputs or intermediates data, assuming that the distribution of the virtual value of them does not deviate from linearity. This weakness causes the limitation of the accuracy of the analytical power of the traditional DDEA models. In this paper, the authors, using the concept of piecewise linear inputs and outputs, propose an extended DDEA model. The proposed model increases the flexibility of the traditional DDEA models and improves the measurement of the dynamic performance of DMUs.

Keywords: Dynamic Data Envelopment Analysis, DDEA, piecewise linear inputs, piecewise linear outputs

Procedia PDF Downloads 161

Authors: Ashwini Shripatwar, Mayur Biyani, Nikhil Rao, Rajendra Bodake, Sachin Sane

Abstract:

This paper documents the correlation of valve cover sealing, cracking, and warpage Finite Element Modelling with observations on engine test development. The valve cover is a component mounted on engine head with a gasket which provides sealing against oil which flows around camshaft, valves, rockers, and other overhead components. Material nonlinearity and contact nonlinearity characteristics are taken into consideration because the valve cover is made of a composite material having temperature dependent elastic-plastic properties and because the gasket load-deformation curve is also nonlinear. The leakage is observed between the valve cover and the engine head due to the insufficient contact pressure. The crack is observed on the valve cover due to force application at a region with insufficient stiffness and with elevated temperature. The valve cover shrinkage is observed during the disassembly process on hot exhaust side bolt holes after the engine has been running. In this paper, an analytical approach is developed to correlate a Finite Element Model with the observed failures and to address the design issues associated with the failure modes in question by making design changes in the model.

Keywords: cracking issue, gasket sealing analysis, nonlinearity of contact and material, valve cover

Procedia PDF Downloads 142

Authors: Maor Farid, Oleg Gendelman

Abstract:

Equivalent mechanical model of liquid sloshing in partially-filled cylindrical vessel is treated in the cases of free oscillations and of horizontal base excitation. The model is designed to cover both the linear and essentially nonlinear sloshing regimes. The latter fluid behaviour might involve hydraulic impacts interacting with the inner walls of the tank. These impulsive interactions are often modeled by high-power potential and dissipation functions. For the sake of analytical description, we use the traditional approach by modeling the impacts with velocity-dependent restitution coefficient. This modelling is similar to vibro-impact nonlinear energy sink (VI NES) which was recently explored for its vibration mitigation performances and nonlinear response regimes. Steady-state periodic regimes and chaotic strongly modulated responses (CSMR) are detected. Those dynamical regimes were described by the system's slow motion on the slow invariant manifold (SIM). There is a good agreement between the analytical results and numerical simulations. Subsequently, Finite-Element (FE) method is used to determine and verify the model parameters and to identify dominant dynamical regimes, natural modes and frequencies. The tank failure modes are identified and critical locations are identified. Mathematical relation is found between degrees-of-freedom (DOFs) motion and the mechanical stress applied in the tank critical section. This is the prior attempt to take under consideration large-amplitude nonlinear sloshing and tank structure elasticity effects for design, regulation definition and resistance analysis purposes. Both linear (tuned mass damper, TMD) and nonlinear (nonlinear energy sink, NES) passive energy absorbers contribution to the overall system mitigation is firstly examined, in terms of both stress reduction and time for vibration decay.

Keywords: nonlinear energy sink (NES), reduced-order modelling, liquid sloshing, vibration mitigation, vibro-impact dynamics

Procedia PDF Downloads 145

Authors: Magdi M. Nabi, Ding-Li Yu

Abstract:

This paper presents a neural network based model predictive control (MPC) strategy to control a strongly exothermic reaction with complicated nonlinear kinetics given by Chylla-Haase polymerization reactor that requires a very precise temperature control to maintain product uniformity. In the benchmark scenario, the operation of the reactor must be guaranteed under various disturbing influences, e.g., changing ambient temperatures or impurity of the monomer. Such a process usually controlled by conventional cascade control, it provides a robust operation, but often lacks accuracy concerning the required strict temperature tolerances. The predictive control strategy based on the RBF neural model is applied to solve this problem to achieve set-point tracking of the reactor temperature against disturbances. The result shows that the RBF based model predictive control gives reliable result in the presence of some disturbances and keeps the reactor temperature within a tight tolerance range around the desired reaction temperature.

Keywords: Chylla-Haase reactor, RBF neural network modelling, model predictive control, semi-batch reactors

Procedia PDF Downloads 468

Authors: Sanaz Kavianpour, Zuraini Ismail, Bharanidharan Shanmugam

Abstract:

Social Network Sites (SNSs) can be served as an invaluable platform to transfer the information across a large number of individuals. A substantial component of communicating and managing information is to identify which individual will influence others in propagating information and also whether dissemination of information in the absence of social signals about that information will be occurred or not. Classifying the final audience of social data is difficult as controlling the social contexts which transfers among individuals are not completely possible. Hence, undesirable information diffusion to an unauthorized individual on SNSs can threaten individuals’ privacy. This paper highlights the information diffusion in SNSs and moreover it emphasizes the most significant privacy issues to individuals of SNSs. The goal of this paper is to propose a privacy-preserving model that has urgent regards with individuals’ data in order to control availability of data and improve privacy by providing access to the data for an appropriate third parties without compromising the advantages of information sharing through SNSs.

Keywords: anonymization algorithm, classification algorithm, information diffusion, privacy, social network sites

Procedia PDF Downloads 321

Authors: Santhosh Srinivasan, Vipul Garhiya, Shahul Hamid Khan

Abstract:

Environmental performance along with social performance is becoming vital factors for industries to achieve global standards. With a good environmental policy global industries are differentiating them from their competitors. This paper concentrates on multi stage, multi product and multi period manufacturing network. Single objective mathematical models for a total cost for the entire forward supply chain and reverse chain are considered. Here five different problems are considered by varying the number of facilities for illustration. M-MOGA, Shuffle Frog Leaping algorithm (SFLA) and CPLEX are used for finding the optimal solution for the mathematical model.

Keywords: closed loop supply chain, genetic algorithm, random search, multi period, green supply chain

Procedia PDF Downloads 391

Authors: Susmita Panda, Arnab Banerjee, Ajinkya Baxy, Bappaditya Manna

Abstract:

The design of short to medium-span high-speed bridges in critical locations is an essential aspect of vehicle-bridge interaction. Due to dynamic interaction between moving load and bridge, mathematical models or finite element modeling computations become time-consuming. Thus, to reduce the computational effort, a universal approximator using an artificial neural network (ANN) has been used to evaluate the dynamic response of the bridge. The data set generation and training of surrogate models have been conducted over the results obtained from mathematical modeling. Further, the robustness of the surrogate model has been investigated, which showed an error percentage of less than 10% with conventional methods. Additionally, the dependency of the dynamic response of the bridge on various load and bridge parameters has been highlighted through a parametric study.

Keywords: artificial neural network, mode superposition method, moving load analysis, surrogate models

Procedia PDF Downloads 100

Authors: G. V. Siva Krishna Rao, B. Srinivasa Rao

Abstract:

The main aim of the paper is to implement a technique using distributed generation in distribution systems to reduce the distribution system losses and to improve voltage profiles. The fuzzy logic technique is used to select the proper location of DG and an analytical method is proposed to calculate the size of DG unit at any power factor. The optimal sizes of DG units are compared with optimal sizes obtained using the genetic algorithm. The suggested method is programmed under Matlab software and is tested on IEEE 33 bus system and the results are presented.

Keywords: DG Units, sizing of DG units, analytical methods, optimum size

Procedia PDF Downloads 474

Authors: Sadia Arshad, Yifa Tang, Dumitru Baleanu

Abstract:

A fractional order mathematical model is proposed that incorporate CD8+ cells, natural killer cells, cytokines and tumor cells. The tumor cells growth in the absence of an immune response is modeled by logistic law as it was the simplest form for which predictions also agreed with the experimental data. Natural Killer Cells are our first line of defense. NK cells directly kill tumor cells through several mechanisms, including the release of cytoplasmic granules containing perforin and granzyme, expression of tumor necrosis factor (TNF) family members. The effect of the NK cells on the tumor cell population is expressed with the product term. Rational form is used to describe interaction between CD8+ cells and tumor cells. A number of cytokines are produced by NKs, including tumor necrosis factor TNF, IFN, and interleukin (IL-10). Source term for cytokines is modeled by Michaelis-Menten form to indicate the saturated effects of the immune response. Stability of the equilibrium points is discussed for biologically significant values of bifurcation parameters. We studied the treatment of fractional order system by investigating analytical conditions of tumor eradication. Numerical simulations are presented to illustrate the analytical results.

Keywords: cancer model, fractional calculus, numerical simulations, stability analysis

Procedia PDF Downloads 315

Authors: Nicole Pearcy, Jonathan J. Crofts, Nadia Chuzhanova

Abstract:

In this paper, we employ a directed hypergraph model to investigate the extent to which environmental variability influences the set of available biochemical reactions within a living cell. Such an approach avoids the limitations of the usual complex network formalism by allowing for the multilateral relationships (i.e. connections involving more than two nodes) that naturally occur within many biological processes. More specifically, we extend the concept of network reciprocity to complex hyper-networks, thus enabling us to characterize a network in terms of the existence of mutual hyper-connections, which may be considered a proxy for metabolic network complexity. To demonstrate these ideas, we study 115 metabolic hyper-networks of bacteria, each of which can be classified into one of 6 increasingly varied habitats. In particular, we found that reciprocity increases significantly with increased environmental variability, supporting the view that organism adaptability leads to increased complexities in the resultant biochemical networks.

Keywords: complexity, hypergraphs, reciprocity, metabolism

Procedia PDF Downloads 297

Authors: A. Belayadi, A. Mougari, L. Ait-Gougam, F. Mekideche-Chafa

Abstract:

The artificial neural network is one of the interesting techniques that have been advantageously used to deal with modeling problems. In this study, the computing with artificial neural network (CANN) is proposed. The model is applied to modulate the information processing of one-dimensional task. We aim to integrate a new method which is based on a new coding approach of generating the input-output mapping. The latter is based on increasing the neuron unit in the last layer. Accordingly, to show the efficiency of the approach under study, a comparison is made between the proposed method of generating the input-output set and the conventional method. The results illustrated that the increasing of the neuron units, in the last layer, allows to find the optimal network’s parameters that fit with the mapping data. Moreover, it permits to decrease the training time, during the computation process, which avoids the use of computers with high memory usage.

Keywords: neural network computing, continuous functions generating the input-output mapping, decreasing the training time, machines with big memories

Procedia PDF Downloads 283

Authors: Abdelkader Merah, Kada Hartani

Abstract:

A reference model based control approach for improving behavior following car is proposed in this paper. The reference model is nonlinear and provides dynamic solutions consistent with safety constraints and comfort specifications. a robust fuzzy logic based control strategy is further proposed in this paper. A set of simulation results showing the suitability of the proposed technique for various demanding cenarios is also included in this paper.

Keywords: reference model, longitudinal control, fuzzy logic, design of car

Procedia PDF Downloads 430

Authors: Yijun Shao, Yan Cheng, Rashmee U. Shah, Charlene R. Weir, Bruce E. Bray, Qing Zeng-Treitler

Abstract:

Deep neural network (DNN) models are being explored in the clinical domain, following the recent success in other domains such as image recognition. For clinical adoption, outcome prediction models require explanation, but due to the multiple non-linear inner transformations, DNN models are viewed by many as a black box. In this study, we developed a deep neural network model for predicting 1-year mortality of patients who underwent major cardio vascular procedures (MCVPs), using temporal image representation of past medical history as input. The dataset was obtained from the electronic medical data warehouse administered by Veteran Affairs Information and Computing Infrastructure (VINCI). We identified 21,355 veterans who had their first MCVP in 2014. Features for prediction included demographics, diagnoses, procedures, medication orders, hospitalizations, and frailty measures extracted from clinical notes. Temporal variables were created based on the patient history data in the 2-year window prior to the index MCVP. A temporal image was created based on these variables for each individual patient. To generate the explanation for the DNN model, we defined a new concept called impact score, based on the presence/value of clinical conditions’ impact on the predicted outcome. Like (log) odds ratio reported by the logistic regression (LR) model, impact scores are continuous variables intended to shed light on the black box model. For comparison, a logistic regression model was fitted on the same dataset. In our cohort, about 6.8% of patients died within one year. The prediction of the DNN model achieved an area under the curve (AUC) of 78.5% while the LR model achieved an AUC of 74.6%. A strong but not perfect correlation was found between the aggregated impact scores and the log odds ratios (Spearman’s rho = 0.74), which helped validate our explanation.

Keywords: deep neural network, temporal data, prediction, frailty, logistic regression model

Procedia PDF Downloads 153

Authors: R. Poonkuzhali, M. Y. Sanavullah, M. R. Gurupriya

Abstract:

Opportunistic routing is used, where the network has the features like dynamic topology changes and intermittent network connectivity. In Delay Tolerant network or Disruption tolerant network opportunistic forwarding technique is widely used. The key idea of opportunistic routing is selecting forwarding nodes to forward data and coordination among these nodes to avoid duplicate transmissions. This paper gives the analysis of pros and cons of various opportunistic routing techniques used in MANET.

Keywords: ETX, opportunistic routing, PSR, throughput

Procedia PDF Downloads 494

Authors: Nicanor Garcia Alvarez, Belarmino Adenso-Diaz, Laura Calzada Infante

Abstract:

In recent years, researchers have shown an interest in modelling maritime traffic as a complex network. In this paper, we propose a bipartite weighted network to model maritime traffic and detect port maritime communities. The bipartite weighted network considers two different types of nodes. The first one represents Spanish ports, while the second one represents the countries with which there is major import/export activity. The flow among both types of nodes is modeled by weighting the volume of product transported. To illustrate the model, the data is segmented by each type of traffic. This will allow fine tuning and the creation of communities for each type of traffic and therefore finding similar ports for a specific type of traffic, which will provide decision-makers with tools to search for alliances or identify their competitors. The traffic with the greatest impact on the Spanish gross domestic product is selected, and the evolution of the communities formed by the most important ports and their differences between 2019 and 2009 will be analyzed. Finally, the set of communities formed by the ports of the Spanish port system will be inspected to determine global similarities between them, analyzing the sum of the membership of the different ports in communities formed for each type of traffic in particular.

Keywords: bipartite networks, competition, infomap, maritime traffic, port communities

Procedia PDF Downloads 148

Authors: H. N. Agiza, M. A. Sohaly, M. A. Elfouly

Abstract:

Parkinson's disease (PD) is a heterogeneous disorder with common age of onset, symptoms, and progression levels. In this paper we will solve analytically the PD model as a non-linear delay differential equation using the steps method. The step method transforms a system of delay differential equations (DDEs) into systems of ordinary differential equations (ODEs). On some numerical examples, the analytical solution will be difficult. So we will approximate the analytical solution using Picard method and Taylor method to ODEs.

Keywords: Parkinson's disease, step method, delay differential equation, two delays

Procedia PDF Downloads 205

Authors: Mansour Mohieddin Ghomshei, Reza Shahi

Abstract:

Laminated composite tubes with adhesively bonded joints are widely used in aerospace and automotive industries as well as oil and gas industries. In this research, adhesively tubular single lap joints subjected to torsional and hygrothermal loadings are studied using the differential quadrature method (DQM). The analysis is based on the classical shell theory. At first, an approximate closed form solution is developed by omitting the lateral deflections in the connecting tubes. Using the analytical model, the circumferential displacements in tubes and the shear stresses in the interfacing adhesive layer are determined. Then, a numerical formulation is presented using DQM in which the lateral deflections are taken into account. By using the DQM formulation, the circumferential and radial displacements in tubes as well as shear and peel stresses in the adhesive layer are calculated. Results obtained from the proposed DQM solutions are compared well with those of the approximate analytical model and those of some published references. Finally using the DQM model, parametric studies are carried out to investigate the influence of various parameters such as adhesive layer thickness, torsional loading, overlap length, tubes radii, relative humidity, and temperature.

Keywords: adhesively bonded joint, differential quadrature method (DQM), hygrothermal, laminated composite tube

Procedia PDF Downloads 302

Authors: Yair Bleiberg, Michael Werman

Abstract:

Coordinate-based Multi-Layer Perceptrons (MLPs) are known to have difficulty reconstructing high frequencies of the training data. A common solution to this problem is Positional Encoding (PE), which has become quite popular. However, PE has drawbacks. It has high-frequency artifacts and adds another hyper hyperparameter, just like batch normalization and dropout do. We believe that under certain circumstances, PE is not necessary, and a smarter construction of the network architecture together with a smart training method is sufficient to achieve similar results. In this paper, we show that very simple MLPs can quite easily output a frequency when given input of the half-frequency and quarter-frequency. Using this, we design a network architecture in blocks, where the input to each block is the output of the two previous blocks along with the original input. We call this a Fibonacci Network. By training each block on the corresponding frequencies of the signal, we show that Fibonacci Networks can reconstruct arbitrarily high frequencies.

Keywords: neural networks, positional encoding, high frequency intepolation, fully connected

Procedia PDF Downloads 98

Authors: S. P. Praveen Kumar, Bong-Su Sin, Kwon-Hee Lee

Abstract:

Finned-tube heat exchangers are predominantly used in space conditioning systems, as well as other applications requiring heat exchange between two fluids. The design of finned-tube heat exchangers requires the selection of over a dozen design parameters by the designer such as tube pitch, tube diameter, tube thickness, etc. Finned-tube heat exchangers are common devices; however, their performance characteristics are complicated. In this paper, numerical studies have been carried out to analyze the performances of finned tube heat exchanger (without fins considered for experimental purpose) by predicting the characteristics of temperature difference and pressure drop. In this study, a design considering 5 design variables, maximizing the temperature difference and minimizing the pressure drop was suggested by applying DOE. In this process, L18 orthogonal array was adopted. Parametric analytical studies have been carried out using Analysis of Variance (ANOVA) to determine the relative importance of each variable with respect to the temperature difference and the pressure drop. Following the results, the final design was suggested by predicting the optimum design therefore confirming the optimized condition.

Keywords: heat exchanger, fluid analysis, heat transfer, design of experiment, analysis of variance

Procedia PDF Downloads 446

Authors: Hala Zaghloul, Taymoor Nazmy

Abstract:

One of the great challenges of the 21st century is to build a robot that can perceive and act within its environment and communicate with people, while also exhibiting the cognitive capabilities that lead to performance like that of people. The Pulse Coupled Neural Network, PCNN, is a relative new ANN model that derived from a neural mammal model with a great potential in the area of image processing as well as target recognition, feature extraction, speech recognition, combinatorial optimization, compressed encoding. PCNN has unique feature among other types of neural network, which make it a candid to be an important approach for perceiving in cognitive systems. This work show and emphasis on the potentials of PCNN to perform different tasks related to image processing. The main drawback or the obstacle that prevent the direct implementation of such technique, is the need to find away to control the PCNN parameters toward perform a specific task. This paper will evaluate the performance of PCNN standard model for processing images with different properties, and select the important parameters that give a significant result, also, the approaches towards find a way for the adaptation of the PCNN parameters to perform a specific task.

Keywords: cognitive system, image processing, segmentation, PCNN kernels

Procedia PDF Downloads 280

Authors: Ava Salmanpour, Hanieh Saeedi, Payam Rouhi, Elahe Hamzeil, Shima Alimohammadi, Siamak Hossein Khalaj, Mohammad Asadian

Abstract:

Software-defined network (SDN) is a network architecture designed to control network using software application in a central manner. This ability enables remote control of the whole network regardless of the network technology. In fact, in this architecture network intelligence is separated from physical infrastructure, it means that required network components can be implemented virtually using software applications. Today, power networks are characterized by a high range of complexity with a large number of intelligent devices, processing both huge amounts of data and important information. Therefore, reliable and secure communication networks are required. SDNs are the best choice to meet this issue. In this paper, SDN networks capabilities and characteristics will be reviewed and different basic controllers will be compared. The importance of using SDNs to escalate efficiency and reliability in utility power networks is going to be discussed and the comparison between the SDN-based power networks and traditional networks will be explained.

Keywords: software-defined network, SDNs, utility network, open flow, communication, gas and electricity, controller

Procedia PDF Downloads 113

Authors: Arya Prakash Padhi, Anupam Chakrabarti, Rajib Chowdhury

Abstract:

Topology or layout optimization often gives better performing economic structures and is very helpful in the conceptual design phase. But traditionally it is being done in finite element-based optimization schemes which, although gives a good result, is very time-consuming especially in 3D structures. Among other alternatives machine learning, especially deep learning-based methods, have a very good potential in resolving this computational issue. Here convolutional neural network (3D-CNN) based variational auto encoder (VAE) is trained using a dataset generated from commercially available topology optimization code ABAQUS Tosca using solid isotropic material with penalization (SIMP) method for compliance minimization. The encoded data in latent space is then fed to a 3D generative adversarial network (3D-GAN) to generate the outcome in 64x64x64 size. Here the network consists of 3D volumetric CNN with rectified linear unit (ReLU) activation in between and sigmoid activation in the end. The proposed network is seen to provide almost optimal results with significantly reduced computational time, as there is no iteration involved.

Keywords: 3D generative adversarial network, deep learning, structural topology optimization, variational auto encoder

Procedia PDF Downloads 174

Authors: Jamshaid Ul Rahman, Faiza Makhdoom, Dianchen Lu

Abstract:

Activation functions play a decisive role in determining the capacity of Deep Neural Networks (DNNs) as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions primarily focused on the utility of monotonic or non-oscillatory functions, until Growing Cosine Unit (GCU) broke the taboo for a number of applications. In this paper, a Convolutional Neural Network (CNN) model named as ASU-CNN is proposed which utilizes recently designed activation function ASU across its layers. The effect of this non-monotonic and oscillatory function is inspected through feature map visualizations from different convolutional layers. The optimization of proposed network is offered by Adam with a fine-tuned adjustment of learning rate. The network achieved promising results on both training and testing data for the classification of CIFAR-10. The experimental results affirm the computational feasibility and efficacy of the proposed model for performing tasks related to the field of computer vision.

Keywords: amplifying sine unit, activation function, convolutional neural networks, oscillatory activation, image classification, CIFAR-10

Procedia PDF Downloads 111

Authors: Okyu Kwon, Dongho Kang, Byungsik Kim, Seungkwon Jung

Abstract:

We propose a technique to measure the impact of loss of traffic function in a particular area to surrounding areas. The proposed method is applied to the city of Seoul, which is the capital of South Korea, with a population of about ten million. Based on the actual road network in Seoul, we construct an abstract road network between 1kmx1km grid cells. The link weight of the abstract road network is re-adjusted considering traffic volume measured at several survey points. On the modified abstract road network, we evaluate the traffic vulnerability by calculating a network measure of betweenness centrality (BC) for every single grid cells. This study analyzes traffic impacts caused by road dysfunction due to heavy rainfall in urban areas. We could see the change of the BC value in all other grid cells by calculating the BC value once again when the specific grid cell lost its traffic function, that is, when the node disappeared on the grid-based road network. The results show that it is appropriate to use the sum of the BC variation of other cells as the influence index of each lattice cell on traffic. This research was supported by a grant (2017-MOIS31-004) from Fundamental Technology Development Program for Extreme Disaster Response funded by Korean Ministry of Interior and Safety (MOIS).

Keywords: vulnerability, road network, beweenness centrality, heavy rainfall, road impact

Procedia PDF Downloads 95

Authors: Yating Yang, Xue Zhang, Chengli Zhao

Abstract:

In the increasingly interconnected global environment brought about by globalization, it is crucial for countries to timely grasp the development motivations in relevant research fields of other countries and seize development opportunities. Motivation, as the intrinsic driving force behind actions, is abstract in nature, making it difficult to directly measure and evaluate. Drawing on the ideas of social influence network theory, the research motivations of a country can be understood as the driving force behind the development of its science and technology sector, which is simultaneously influenced by both the country itself and other countries/regions. In response to this issue, this paper improves upon Friedkin's social influence network theory and applies it to motivation description, constructing a dynamic alliance network and hostile network centered around the United States and China, as well as a sensitivity matrix, to remotely assess the changes in national research motivations under the influence of international relations. Taking artificial intelligence as a case study, the research reveals that the motivations of most countries/regions are declining, gradually shifting from a neutral attitude to a negative one. The motivation of the United States is hardly influenced by other countries/regions and remains at a high level, while the motivation of China has been consistently increasing in recent years. By comparing the results with real data, it is found that this model can reflect, to some extent, the trends in national motivations.

Keywords: influence network theory, remote assessment, relation matrix, dynamic sensitivity matrix

Procedia PDF Downloads 68

Authors: Panagiotis Karadimos, Leonidas Anthopoulos

Abstract:

Predicting the actual cost and duration in construction projects concern a continuous and existing problem for the construction sector. This paper addresses this problem with modern methods and data available from past public construction projects. 39 bridge projects, constructed in Greece, with a similar type of available data were examined. Considering each project’s attributes with the actual cost and the actual duration, correlation analysis is performed and the most appropriate predictive project variables are defined. Additionally, the most efficient subgroup of variables is selected with the use of the WEKA application, through its attribute selection function. The selected variables are used as input neurons for neural network models through correlation analysis. For constructing neural network models, the application FANN Tool is used. The optimum neural network model, for predicting the actual cost, produced a mean squared error with a value of 3.84886e-05 and it was based on the budgeted cost and the quantity of deck concrete. The optimum neural network model, for predicting the actual duration, produced a mean squared error with a value of 5.89463e-05 and it also was based on the budgeted cost and the amount of deck concrete.

Keywords: actual cost and duration, attribute selection, bridge construction, neural networks, predicting models, FANN TOOL, WEKA

Procedia PDF Downloads 134

Authors: Cristian Pauna

Abstract:

Trading the financial markets is a widespread activity today. A large number of investors, companies, public of private funds are buying and selling every day in order to make profit. Algorithmic trading is the prevalent method to make the trade decisions after the electronic trading release. The orders are sent almost instantly by computers using mathematical models. This paper will present a price prediction methodology based on a multi-dimensional neural network. Using the Fisher transform, the neural network will be instructed for a low-latency auto-adaptive process in order to predict the price evolution for the next period of time. The model is designed especially for algorithmic trading and uses the real-time price series. It was found that the characteristics of the Fisher function applied at the nodes scale level can generate reliable trading signals using the neural network methodology. After real time tests it was found that this method can be applied in any timeframe to trade the financial markets. The paper will also include the steps to implement the presented methodology into an automated trading system. Real trading results will be displayed and analyzed in order to qualify the model. As conclusion, the compared results will reveal that the neural network methodology applied together with the Fisher transform at the nodes level can generate a good price prediction and can build reliable trading signals for algorithmic trading.

Keywords: algorithmic trading, automated trading systems, financial markets, high-frequency trading, neural network

Procedia PDF Downloads 160

Authors: Martins Y. Otache, John J. Musa, Abayomi I. Kuti, Mustapha Mohammed

Abstract:

The performance of an artificial neural network (ANN) is contingent on a host of factors, for instance, the network optimisation scheme. In view of this, the study examined the general implications of the ANN training optimisation algorithm on its forecast performance. To this end, the Bayesian regularisation (Br), Levenberg-Marquardt (LM), and the adaptive learning gradient descent: GDM (with momentum) algorithms were employed under different ANN structural configurations: (1) single-hidden layer, and (2) double-hidden layer feedforward back propagation network. Results obtained revealed generally that the gradient descent with momentum (GDM) optimisation algorithm, with its adaptive learning capability, used a relatively shorter time in both training and validation phases as compared to the Levenberg- Marquardt (LM) and Bayesian Regularisation (Br) algorithms though learning may not be consummated; i.e., in all instances considering also the prediction of extreme flow conditions for 1-day and 5-day ahead, respectively especially using the ANN model. In specific statistical terms on the average, model performance efficiency using the coefficient of efficiency (CE) statistic were Br: 98%, 94%; LM: 98 %, 95 %, and GDM: 96 %, 96% respectively for training and validation phases. However, on the basis of relative error distribution statistics (MAE, MAPE, and MSRE), GDM performed better than the others overall. Based on the findings, it is imperative to state that the adoption of ANN for real-time forecasting should employ training algorithms that do not have computational overhead like the case of LM that requires the computation of the Hessian matrix, protracted time, and sensitivity to initial conditions; to this end, Br and other forms of the gradient descent with momentum should be adopted considering overall time expenditure and quality of the forecast as well as mitigation of network overfitting. On the whole, it is recommended that evaluation should consider implications of (i) data quality and quantity and (ii) transfer functions on the overall network forecast performance.

Keywords: streamflow, neural network, optimisation, algorithm

Procedia PDF Downloads 152

Authors: Mikheil Kalmakhelidze

Abstract:

Record linkage (RL) problem has become more and more important in recent years due to the growing interest towards big data analysis. The problem can be formulated in a very simple way: Given two entries a and b of a database, decide whether they represent the same object or not. There are two classical deterministic and probabilistic ways of solving the RL problem. Using simple Bayes classifier in many cases produces useful results but sometimes they show to be poor. In recent years several successful approaches have been made towards solving specific RL problems by neural network algorithms including single layer perception, multilayer back propagation network etc. In our work, we model the RL problem for specific dataset of student applications in fuzzy description logic (FDL) where linkage of specific pair (a,b) depends on the truth value of corresponding formula A(a,b) in a canonical FDL model. As a main result, we build neural network for deciding truth value of FDL formulas in a canonical model and thus link RL problem to machine learning. We apply the approach to dataset with 10000 entries and also compare to classical RL solving approaches. The results show to be more accurate than standard probabilistic approach.

Keywords: description logic, fuzzy logic, neural networks, record linkage

Procedia PDF Downloads 272