INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET) EFFORT ESTIMATION USING A SOFT COMPUTING TECHNIQUE

Size: px
Start display at page:

Download "INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET) EFFORT ESTIMATION USING A SOFT COMPUTING TECHNIQUE"

Transcription

1 INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET) International Journal of Computer Engineering and Technology (IJCET), ISSN (Print), ISSN (Print) ISSN (Online) Volume 4, Issue 6, November - December (203), pp IAEME: Journal Impact Factor (203): (Calculated by GISI) IJCET I A E M E EFFORT ESTIMATION USING A SOFT COMPUTING TECHNIQUE Sheenu Rizvi, Prof. Dr. S. Q. Abbas 2, Prof. Dr. Rizwan Beg 3 Deptt. of CS, Amity University, Luck now, India 2 Director, AIMT, Luck now, India 3 Controller of Examination, Integral University, Lucknow, India ABSTRACT Accurately estimating software effort is probably the biggest challenge facing software developers. Estimates done at the proposal stage has high degree of inaccuracy, where requirements for the scope are not defined to the lowest details, but as the project progresses and requirements are elaborated, accuracy and confidence on estimate increases. It is important to choose the right software effort estimation techniques for the prediction of software effort. In the present work Artificial Neural Network (ANN) model has been developed using Multi Layered Feed Forward Neural Network using Back Propagation learning algorithm by iteratively processing a set of training samples and comparing the network s prediction with the actual effort. COCOMO dataset has been used to test and train the network using nine different types of training algorithms. It was observed that the proposed model improves the estimation accuracy of the model. The performance indices Mean-Square-Error (MSE), Magnitude of Relative-Error (MRE), and Regression analysis (R) have been used to compare the results obtained from this method. The preliminary results suggest that the proposed model can be replicated for accurately forecasting the software development effort. Keywords: Software Effort Estimation, Artificial Neural Network, Back Propagation, COCOMO. I. INTRODUCTION Software effort estimation is one of the most critical and complex, but an inevitable activity in the software development processes. Although a great amount of research time, and money have been devoted to improving accuracy of the various estimation models, due to the inherent uncertainty in software development projects as like complex and dynamic interaction factors, intrinsic software complexity, pressure on standardization and lack of software data, it is unrealistic to expect very accurate effort estimation of software development processes []. 290

2 There are many estimation models which have been proposed and can be categorized based on their basic formulation schemes; estimation by expert [8], analogy based estimation schemes [2], algorithmic methods including empirical methods, rule induction methods [7], artificial neural network based approaches [4] [], Bayesian network approaches [3], decision tree based methods and fuzzy logic based estimation schemes [5]. Among the software cost estimation techniques, COCOMO (Constructive Cost Model) is the mostly used algorithmic cost modeling technique because of its simplicity for estimating the effort in person-months for a project at different stages. Many researchers have [4, 6] explored the possibility of using neural networks for estimating the effort. The aim of the present work is to propose an optimal neural network model for software effort estimation. The network architecture is designed accordingly to accommodate the COCOMO model and its parameters. The present work explores a new single layered artificial neural network that was constructed for software effort estimation and is trained with nine different learning algorithms. II. LITERATURE REVIEW Many software cost estimation models have been developed over the last decades. A recent study by Jorgensen [9] provides a detailed review of different studies on the software development effort. Many researchers have applied the neural networks approach to estimate software development effort [6, 0]. Many different models of neural networks have been proposed [4]. They may be grouped in two major categories. First one is feed forward networks where no loops in the network path occur. Another one is feedback networks that have recursive loops. Understanding the adversity in applying neural networks, Nasser Tadayon [] has proposed a dynamic neural network that will initially use COCOMO II Model. COCOMO, however, has some limitations. It cannot effectively deal with imprecise and uncertain information, and calibration of COCOMO is one of the most important tasks that need to be done in order to get accurate estimations. So, there is always scope for developing effort estimation models with better predictive accuracy. III. ANN METHODOLOGY An ANN can be defined as a system or mathematical model consisting of many nonlinear artificial neurons running in parallel which can be generated as one or multiple layered. A Feed Forward Neural Network (FFNN) consists of at least three layers, input, output and hidden layer. The number of hidden layers and neurons in hidden layer are determined by trial and error method. The strength of connection between the two layers is determined by the weights W ij. The schematic diagram of a FFNN is shown in Fig. X X 2 Y X 3 Wij Input Layer Hidden Output Layer Figure : Schematic diagram of a FFNN 29

3 Each neuron in a layer receives weighted inputs from a previous layer and transmits its output to neurons in the next layer. The summation of weighted input signals is calculated by Eq. () and is transferred by a nonlinear activation function given in Eq. (2). The responses of network are compared with the observation results and the network error is calculated with equation (3) Y Y J net out r = = =. 2 N i= f k i= X i. wi + w0 () + e ( ynet ) = (2) ( Y obs Y out Y out is the response of neural network system, f (Y net ) is the nonlinear activation function, Y net is the summation of weighted inputs, X i is the neuron input, w i is weight coefficient of each neuron input, w 0 is bias, J r is the error between observed value and network result, Y obs is the observation output value IV. AVAILABLE DATA, MODEL INPUTS AND MODEL STRUCTURE One of the most important steps in the development of any prediction model is the selection of appropriate input variables that will allow an ANN to successfully produce the desired results. Good understanding of the process under consideration is an important prerequisite for successful application of data driven approaches. The main reason for this is that ANN belong to the class of data-driven approaches. Predicting Effort is a complicated problem that involves multiple interacting factors. In order to build a reasonably accurate model for prediction, proper parameters must be selected. Some practical considerations in parameter selections are firstly, the selected parameters must affect the target problem, i.e., strong relationships must exist among the parameters and target (or output) variables, and secondly, the selected parameters must be well-populated, and corresponding data must be as clean as possible. Since the soft computing methods model problems based on available data, the availability and quality of data are both essential V. DATA DESCRIPTION In the present work COCOMO8 dataset has been used for Effort Estimation ANN model development. In algorithmic cost estimation, costs and efforts are predicted using mathematical formula. The formula are derived based on some historical data. The best known algorithmic cost model called COCOMO (Constructive Cost Model) was published by Barry Boehm in 98. It was developed from the analysis of sixty three (63) software projects. The data used as input and output variables for optimum model development are given in the Table: below. In all sixteen input variables have been used which include fifteen effort multipliers and the SIZE measured in thousand delivered source instructions. The output of the model is the Development Effort (DE), which is measured in man-months. The data were collected from the analysis of sixty three (63) software projects, as published by Barry Boehm in 98. ) 2 Y net (3) 292

4 Table : Input and Output variables Input RELY - Required software reliability Variables DATA - Data base size CPLX - Product complexity TIME - Execution time STOR main storage constraint VIRT virtual machine volatility TURN computer turnaround time ACAP analyst capability AEXP applications experience PCAP programmer capability VEXP virtual machine experience LEXP language experience MODP modern programming TOOL use of software tools SCED required development schedule SIZE Output Development Effort (DE) Variable VI. NETWORK BUILDING AND TRAINING NN Model is created using Matlab Neural Network toolbox. Matlab tool facilitates ease of simulation and modeling. As discussed earlier, size of input and output vector is decided. Trials are first conducted by randomly selecting number of processing elements. NN models are created with one hidden layer and varying number of processing elements or neurons. As per White s theorem, one layer with non-linear activation function is enough to map non-linear functional relationship in a fairly accurate way. In the present work optimal network geometry was investigated, using trial and error approach, in an attempt to create more optimum model. Thus to minimise the number of networks that required training and testing, ANN s containing 2 to 20 nodes were considered in order to narrow down the search. Once this range was determined, the trial and error approach was repeated, with the number of hidden nodes increasing in increment of two from minimum nodes onwards. The learning rate was also initially kept to minimum and slowly increased. Thus various permutation and combinations of both these factors were used during the training process. The fixed period stops of 000 cycles was used for training the network and the target error was set to stop during training when the average error reaches below Finally the optimum nodes were found for the best developed network and the networks on either side of the best developed network were also tested. Further training of the network is carried out. Training is the process by which the weights of an ANN are estimated, by using an iterative procedure to minimise a predetermined error, or objective function, such as the MSE. Therefore, ANN training is essentially a nonlinear least squares problem, which can be solved using standard nonlinear least squares methods. As mentioned earlier, nine different types of training algoritms are investigated for developing the MLP network. The algorithms include: LM=Levenberg-Marquardt; GD=Gradient Descent; GDA= Gradient Descent with adaptive learning rate; GDX= Gradient Descent with adaptive learning rate and momentum; GDM= Gradient descent with momentum; SCG= Scaled Conjugate Gradient; RP= Resilient Backpropagation; BFG= BFGS quasi-newton backpropagation; BR= Bayesian Regularization. 293

5 MATLAB provides the built in transfer function which is used in the present work, i.e tangent sigmoid transfer in the hidden layer and linear one in the outer layer. Here in this work Back- Propagation algorithm has been used for training the Feed Forward Neural Network architecture. Table 2: Model parameter values Parameters used for Network Training Network Type Feed Forward Neural Network with Back Propagation Training Functions LM=Levenberg-Marquardt; Used GD=Gradient Descent; GDA= Gradient Descent with adaptive learning rate; GDX= Gradient Descent with adaptive learning rate and momentum; GDM= Gradient descent with momentum; SCG= Scaled Conjugate Gradient; RP= Resilient Baxkpropagation; BFG= BFGS quasi-newton backpropagation BR = Bayesian Regularization Adaption Learning learngdm and learngd Function Performance Function Mean Square Error (MSE); Regression (R) Transfer Function For Hidden layer tansigmoid For output layer - linear No. Of neurons used 2 to 0; in some cases upto 20 for hidden layer Once the training is complete, the weights are frozen, network structure is finalized and data to be used for functional requirements of the NN model is converted into useful format, training, testing, and validation of the NN model can be started. Matlab NN toolbox has characteristic of dividing the available data into 70 percent for training, 5 percent for testing and another 5 percent for validation of the NN model. Training is the only time data is back propagated through the network. During recall, the network is strictly feed forward. The various parameters used for training the network are given in the Table: 2. VII. PERFORMANCE MEASURING CRITERIA Performance criteria which measure prediction accuracy generally measure the fit (or lack there of) between the model outputs and the observed data by some error measure E. () Mean Squared Error (MSE) MSE evaluates the residual between measured and forecasted values. MSE is a frequently-used measure of the difference between values predicted by a model or an estimator and the values actually observed from the thing being modelled or estimated. Theoretically, if this criterion equals zero then model represents the perfect fit, which is not possible at all. (2) Regression (R) It provides information on the strength of linear relationship between the observed and the computed values. The value r close to.0 indicates good model performance and can be calculated using the following formula, (3) Magnitude of Relative Error (MRE) It is defined as MRE ={ [Mod (Actual Effort Predicted Effort)] / Actual Effort}*00 y 294

6 A high score means worse prediction accuracy. Here it is assumed that the error is proportional to the size of the project. VIII. RESULTS AND DISCUSSIONS The model performance in terms of training, testing and validating results corresponding to each neurons added to the hidden layer were calculated and plotted as shown in figures 2 to 7. Table: 3 shows the comparative chart of estimated and predicted effort values for randomly selected 0 project values using COCOMO and ANN methodologies. Further Table: 4 tabulate the Magnitude of Relative Error (MRE) values for both the COCOMO and ANN models. The same results have been plotted graphically in figure 7. This figure shows the effort prediction accuracy of the neural network. The chart clearly shows that there is a decrement in the relative error, so that the proposed model is more suitable for effort estimation. The preliminary results obtained suggest that the proposed architecture can be replicated for accurately forecasting the software development effort. The aim of this study is to improve the estimation accuracy of COCOMO model, so that the estimated effort is more close to the actual effort. Once the network has been trained to the level where the predicted results are fairly accurate, testing is carried out to assure that predicted results are in close proximity to actual values. For the best developed NN model i.e. 6-8-, with eight neurons in the hidden layer using Levenberg training algorithm, the MSE plot is shown in figure:2(b) for the best validation performance and correspondingly the regression plot of training, testing and validation is shown in figure:2(a). MSE is used to judge the accuracy of the prediction during training, testing and validation. It was also noticed from figure 2 that the performance did not improve even when the network error was low. It was noticed that roughly after 5 epochs the training error continued to decrease even when the performance of testing and validation were somewhat stagnant. This can be referred to the effect as overfitting. Since from the study conducted on network topology, the performance of NN model which is most accurate is 6-8-, hence it is our best choice of network topology. With this selection of network topology, number of layers, processing elements, generalization characteristics are preserved. It was also noticed that training time is also significantly reduced as there are lesser iterations every time. Figure 6 depicts comparison of actual values and values predicted by best selected NN model for effort estimation using LM training algorithm and GDM training function for N=8. It is noticed that except for rare occasions, simulated effort values for the designated parameters are in acceptable proximity with actual values. This representation therefore agrees with the conclusion that, high accuracy of prediction is attained by Neural Network model after successful completion of training criteria i.e. with the value of MSE being within acceptable range as well as agreeable performance measure. Hence from the results it is inferred that the performance of NN model is acceptable. Further, from the perusal of the data and the analysis of the graphical plot of R values for training, testing and validation data sets from Figure 3, 4 and 5, it is clear that the best NN model that has been created uses Levenberg-Marquardt training algorithm, followed in descending order of performance by BR, RP and finally SCG. Thus, L-M algorithm seems to be better suited for training the NN model for better prediction accuracy. 295

7 Figure 2(a): Regression analysis graph for N=4 Figure 2(b): Depicts the acceptable training performance R Value for different Training Algorithms R Valus for Testing Data R (Training Data) No. of neurons LM-GDM LM-GD SCG-GDM SCG-GD BR-GDM BR-GD RP-GDM Figure 3: Shows regression values for training data R 0.8 LM-GDM 0.6 LM-GD SCG-GDM 0.4 SCG-GD 0.2 BR-GDM 0 BR-GD RP-GDM No. of Neurons Figure 4: Shows regression values for testing data R Value for Validation Data R No. of Neurons LM-GDM LM-GD SCG-GDM SCG-GD BR-GDM BR-GD RP-GDM Figure 5: Shows regression values for validating data Figure 6: Comparative Plot of Actual, COCOMO and Predicted ANN Efforts Table 3: Comparison of Effort Estimation Sl. No MRE using COCOMO ANN

8 Table 4: MRE Values for different Models Sl. No MRE using COCOMO ANN Figure 7: Plot of MRE values for COCOMO and ANN models IX. CONCLUSION AND FUTURE WORK A reliable and accurate estimate of software development effort has always been a challenge for both the software industrial and academic communities. There are several software effort forecasting models that can be used in forecasting future software development effort. Hence an effort estimation model based on artificial neural networks has been constructed. The idea consists in the use of a model that maps COCOMO model to a neural network with minimal number of layers and nodes to increase the performance of the network. The neural network that has been used to predict the software development effort is the multi layer feed forward neural network with back propagation training algorithm. The COCOMO8 dataset has been used to train and to test the network and it was observed that neural network model provided significantly better effort estimations than the estimation done using COCOMO model. Accordingly, it is inferred that the rationalization and interpretation of the knowledge stored in the architecture and synapse weights of the neural nets is very important to gain practitioners acceptance. Another great advantage of this work is that one can put together expert knowledge, project data and the traditional algorithmic model into one general framework that can have a wide range of applicability in software cost estimation. This work can be extended by integrating this approach with fuzzy logic to effectively deal with imprecise and uncertain information associated with COCOMO. Therefore, a promising line of future work is to extend to the neuro-fuzzy approach. 297

9 REFERENCES. Boehm, B.W., Software Engineering Economics, Prentice-Hall, Englewood Cliffs, NJ, USA, 994. [22] Tadayon, N., Neural network approach for software cost estimation, International Conference on Information Technology: Coding and Computing (ITCC 2005), Volume: 2, on page(s): 85-88, Chiu NH, Huang SJ, The Adjusted Analogy-Based Software Effort Estimation Based on Similarity Distances, Journal of Systems and Software, Volume 80, Issue 4, pp , G. H. Subramanian, P. C. Pendharkar, and M. Wallace, "An Empirical Study of the Effect of Complexity, Platform, and Program Type on Software Development Effort of Business Applications," Empirical Software Engineering, vol., pp , Heiat A, Comparison of Artificial Neural Network and Regression Models for Estimating Software Development Effort, Journal of Information and Software Technology, Volume 44, Issue 5, pp 9-922, Huang SJ, Lin CY, Chiu NH, Fuzzy Decision Tree Approach for Embedding Risk Assessment Information into Software Cost Estimation Model, Journal of Information Science and Engineering, Volume 22, Number 2, pp , Hughes, R.T., An evaluation of machine learning techniques for software effort estimation, University of Brighton, Jeffery R, Ruhe M,Wieczorek I, Using Public Domain Metrics to Estimate Software Development Effort, In Proceedings of the 7 th International Symposium on Software Metrics, IEEE Computer Society, Washington, DC, pp 6 27, Jorgen M, Sjoberg D.I.K, The Impact of Customer Expectation on Software Development Effort Estimates International Journal of Project Management, Elsevier, pp , Jørgensen. M., A Review of Studies on Expert Estimation of Software Development Effort, Journal of Systems and Software, Volume 70, pp , Jorgerson, M., Experience with accuracy of software maintenance task effort prediction models, IEEE Transactions on Software Engineering, Volume 2 (8), , K. Srinivasan and D. Fisher, "Machine learning approaches to estimating software development effort," IEEE Transactions on Software Engineering, vol. 2, pp , P.V.G.D. Prasad Redd, CH.V.M.K. Hari, T. Srinivasa Rao, Multi Objective Particle Swarm Optimization for Software Cost Estimation, International Journal of Computer Applications ( ) Volume 32 No.3, October, P.V.G.D. Prasad Reddy and CH.V.M.K. Hari, A Fine parameter tuning for COCOMO 8 software effort estimation using Particle swarm optimization, A. Iman and H.O. Siew, Soft Computing Approach for Software Cost Estimation, Int.J. of Software Engineering, IJSE Vol.3 No., pp.-0, January Srinivasa Rao et al, Predictive and Stochastic Approach for Software Effort Estimation, Int. J. of Software Engineering, IJSE Vol. 6 No. January Peram Subba Rao, Dr.K.Venkata Rao and Dr.P.Suresh Varma, A Novel Software Interval Type - 2 Fuzzy Effort Estimation Model using S-Fuzzy Controller With Mean and Standard Deviation, International Journal of Computer Engineering & Technology (IJCET), Volume 4, Issue 3, 203, pp , ISSN Print: , ISSN Online: S.HemaChandra and Dr.R.V.S.Satyanarayana, Temperature Control of Transformers using Soft Computing Techniques, International Journal of Computer Engineering & Technology (IJCET), Volume 3, Issue 2, 202, pp , ISSN Print: , ISSN Online:

Software Effort Estimation using Radial Basis and Generalized Regression Neural Networks

Software Effort Estimation using Radial Basis and Generalized Regression Neural Networks WWW.JOURNALOFCOMPUTING.ORG 87 Software Effort Estimation using Radial Basis and Generalized Regression Neural Networks Prasad Reddy P.V.G.D, Sudha K.R, Rama Sree P and Ramesh S.N.S.V.S.C Abstract -Software

More information

Proposing a New Software Cost Estimation Model Based on Artificial Neural Networks

Proposing a New Software Cost Estimation Model Based on Artificial Neural Networks Proposing a New Software Cost Estimation Model Based on Artificial Neural Networks Iman Attarzadeh, Siew Hock Ow Department of Software Engineering Faculty of Computer Science & Information Technology

More information

Project Plan. CivicPlus Activity Metrics Tool. Version 1.0. Keith Wyss CIS 895 MSE Project Kansas State University

Project Plan. CivicPlus Activity Metrics Tool. Version 1.0. Keith Wyss CIS 895 MSE Project Kansas State University Project Plan CivicPlus Activity Metrics Tool Version 1.0 Keith Wyss CIS 895 MSE Project Kansas State University Table of Contents 1. INTRODUCTION... 5 1.1. REFERENCES... 5 2. WORK BREAKDOWN STRUCTURE...

More information

Project Plan. KSU Student Portal. Version 1.0. Submitted in partial fulfillment of the requirements of the degree of MSE

Project Plan. KSU Student Portal. Version 1.0. Submitted in partial fulfillment of the requirements of the degree of MSE Project Plan KSU Student Portal Version 1.0 Submitted in partial fulfillment of the requirements of the degree of MSE Javier Ramos Rodríguez CIS 895 MSE Project Kansas State University 1 Table of contents

More information

Application of Intelligent Methods for Improving the Performance of COCOMO in Software Projects

Application of Intelligent Methods for Improving the Performance of COCOMO in Software Projects Application of Intelligent Methods for Improving the Performance of COCOMO in Software Projects Mahboobeh Dorosti,. Vahid Khatibi Bardsiri Department of Computer Engineering, Kerman Branch, Islamic Azad

More information

Keywords Effort Estimation, Neural Networks, PNN, GRNN, Data Mining Techniques

Keywords Effort Estimation, Neural Networks, PNN, GRNN, Data Mining Techniques Volume 5, Issue 7, July 2015 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Estimating Software

More information

International Journal of Industrial Engineering Computations

International Journal of Industrial Engineering Computations International Journal of Industrial Engineering Computations 2 (2011) 431 438 Contents lists available at GrowingScience International Journal of Industrial Engineering Computations homepage: www.growingscience.com/ijiec

More information

NEURAL NETWORK SIMULATION OF KARSTIC SPRING DISCHARGE

NEURAL NETWORK SIMULATION OF KARSTIC SPRING DISCHARGE NEURAL NETWORK SIMULATION OF KARSTIC SPRING DISCHARGE 1 I. Skitzi, 1 E. Paleologos and 2 K. Katsifarakis 1 Technical University of Crete 2 Aristotle University of Thessaloniki ABSTRACT A multi-layer perceptron

More information

CONCRETE MIX DESIGN USING ARTIFICIAL NEURAL NETWORK

CONCRETE MIX DESIGN USING ARTIFICIAL NEURAL NETWORK CONCRETE MIX DESIGN USING ARTIFICIAL NEURAL NETWORK Asst. Prof. S. V. Shah 1, Ms. Deepika A. Pawar 2, Ms. Aishwarya S. Patil 3, Mr. Prathamesh S. Bhosale 4, Mr. Abhishek S. Subhedar 5, Mr. Gaurav D. Bhosale

More information

Software Effort Estimation: A Survey of Well-known Approaches

Software Effort Estimation: A Survey of Well-known Approaches Software Effort Estimation: A Survey of Well-known Approaches Amid Khatibi Bardsiri Computer Engineering Department, Bardsir Branch, Islamic Azad University, Kerman, Iran E-mail: a.khatibi@srbiau.ac.ir

More information

Project Plan. For KDD- Service based Numerical Entity Searcher (KSNES) Version 1.1

Project Plan. For KDD- Service based Numerical Entity Searcher (KSNES) Version 1.1 Project Plan For KDD- Service based Numerical Entity Searcher (KSNES) Version 1.1 Submitted in partial fulfillment of the Masters of Software Engineering degree. Naga Sowjanya Karumuri CIS 895 MSE Project

More information

Transactions on Information and Communications Technologies vol 19, 1997 WIT Press, ISSN

Transactions on Information and Communications Technologies vol 19, 1997 WIT Press,   ISSN The neural networks and their application to optimize energy production of hydropower plants system K Nachazel, M Toman Department of Hydrotechnology, Czech Technical University, Thakurova 7, 66 9 Prague

More information

WATER QUALITY PREDICTION IN DISTRIBUTION SYSTEM USING CASCADE FEED FORWARD NEURAL NETWORK

WATER QUALITY PREDICTION IN DISTRIBUTION SYSTEM USING CASCADE FEED FORWARD NEURAL NETWORK WATER QUALITY PREDICTION IN DISTRIBUTION SYSTEM USING CASCADE FEED FORWARD NEURAL NETWORK VINAYAK K PATKI, S. SHRIHARI, B. MANU Research scholar, National Institute of Technology Karnataka (NITK), Surathkal,

More information

Experimental Analysis of Effort Estimation Using Artificial Neural Network

Experimental Analysis of Effort Estimation Using Artificial Neural Network International Journal of Electronics and Computer Science Engineering 1817 Available Online at www.ijecse.org ISSN- 2277-1956 Experimental Analysis of Effort Estimation Using Artificial Neural Network

More information

Determining How Much Software Assurance Is Enough?

Determining How Much Software Assurance Is Enough? Determining How Much Software Assurance Is Enough? Tanvir Khan Concordia Institute of Information Systems Engineering Ta_k@encs.concordia.ca Abstract It has always been an interesting problem for the software

More information

Resource Model Studies

Resource Model Studies Resource Model Studies MODELING AND MEASURING RESOURCES Model Validation Study Walston and Felix build a model of resource estimation for the set of projects at the IBM Federal Systems Division. They did

More information

MODELLING STUDIES BY APPLICATION OF ARTIFICIAL NEURAL NETWORK USING MATLAB

MODELLING STUDIES BY APPLICATION OF ARTIFICIAL NEURAL NETWORK USING MATLAB Journal of Engineering Science and Technology Vol. 10, No.11 (2015) 1477-1486 School of Engineering, Taylor s University MODELLING STUDIES BY APPLICATION OF ARTIFICIAL NEURAL NETWORK USING MATLAB K. S.

More information

Wastewater Effluent Flow Control Using Multilayer Neural Networks

Wastewater Effluent Flow Control Using Multilayer Neural Networks Wastewater Effluent Flow Control Using Multilayer Neural Networks Heidar A. Malki University of Houston 304 Technology Building Houston, TX 77204-4022 malki@uh.edu Shayan Mirabi University of Houston 304

More information

Prediction of Axial and Radial Creep in CANDU 6 Pressure Tubes

Prediction of Axial and Radial Creep in CANDU 6 Pressure Tubes Prediction of Axial and Radial Creep in CANDU 6 Pressure Tubes Vasile S. Radu Institute for Nuclear Research Piteşti vasile.radu@nuclear.ro 1 st Research Coordination Meeting for the CRP Prediction of

More information

CHAPTER 3 FUZZY LOGIC BASED FRAMEWORK FOR SOFTWARE COST ESTIMATION

CHAPTER 3 FUZZY LOGIC BASED FRAMEWORK FOR SOFTWARE COST ESTIMATION CHAPTER 3 FUZZY LOGIC BASED FRAMEWORK FOR SOFTWARE COST ESTIMATION The Fuzzy Logic System is one of the main components of soft computing, the field in computer science that deals with imprecision, uncertainty,

More information

Prediction of Dissolved Oxygen Using Artificial Neural Network

Prediction of Dissolved Oxygen Using Artificial Neural Network 2011 International Conference on Computer Communication and Management Proc.of CSIT vol.5 (2011) (2011) IACSIT Press, Singapore Prediction of Dissolved Oxygen Using Artificial Neural Network Sirilak Areerachakul

More information

An Application of Neural Networks in Market Segmentation

An Application of Neural Networks in Market Segmentation 1 & Marketing An Application of Neural Networks in Market Segmentation Nikolaos Petroulakis 1, Andreas Miaoudakis 2 1 Foundation of research and technology (FORTH), Iraklio Crete, 2 Applied Informatics

More information

Artificial Neural Network Modeling of an Inverse Fluidized Bed Bioreactor *RAJASIMMAN, M, GOVINDARAJAN, L, KARTHIKEYAN, C

Artificial Neural Network Modeling of an Inverse Fluidized Bed Bioreactor *RAJASIMMAN, M, GOVINDARAJAN, L, KARTHIKEYAN, C JASEM ISSN 1119-8362 All rights reserved Full-text Available Online at www.bioline.org.br/ja J. Appl. Sci. Environ. Manage. June, 27 Vol. 11 (2) 65-69 Artificial Neural Network Modeling of an Inverse Fluidized

More information

Day-Ahead Price Forecasting of Electricity Market Using Neural Networks and Wavelet Transform

Day-Ahead Price Forecasting of Electricity Market Using Neural Networks and Wavelet Transform Electrical and Electronic Engineering 2018, 8(2): 37-52 DOI: 10.5923/j.eee.20180802.02 Day-Ahead Price Forecasting of Electricity Market Using Neural Networks and Wavelet Transform Kamran Rahimimoghadam

More information

Genetic Algorithm for Optimizing Neural Network based Software Cost Estimation

Genetic Algorithm for Optimizing Neural Network based Software Cost Estimation Genetic Algorithm for Optimizing Neural Network based Software Cost Estimation Tirimula Rao Benala 1, S Dehuri 2, S.C.Satapathy 1 and Ch Sudha Raghavi 1, 1 Anil Neerukonda Institute of Technology and Sciences

More information

Australian Journal of Basic and Applied Sciences. Vision based Automation for Flame image Analysis in Power Station Boilers

Australian Journal of Basic and Applied Sciences. Vision based Automation for Flame image Analysis in Power Station Boilers Australian Journal of Basic and Applied Sciences, 9(2) February 201, Pages: 40-4 AENSI Journals Australian Journal of Basic and Applied Sciences ISSN:1991-8178 Journal home page: www.ajbasweb.com Vision

More information

Study of Pile Cap Lateral Resistance using Artificial Neural Networks

Study of Pile Cap Lateral Resistance using Artificial Neural Networks International Journal of Computer Applications (975 8887) Volume 21 No.1, May 211 Study of Pile Cap Lateral Resistance using Artificial Neural Networks Utpal K. Nath Assistant Professor Civil Engineering

More information

A Comparative evaluation of Software Effort Estimation using REPTree and K* in Handling with Missing Values

A Comparative evaluation of Software Effort Estimation using REPTree and K* in Handling with Missing Values Australian Journal of Basic and Applied Sciences, 6(7): 312-317, 2012 ISSN 1991-8178 A Comparative evaluation of Software Effort Estimation using REPTree and K* in Handling with Missing Values 1 K. Suresh

More information

Amanullah Dept. Computing and Technology Absayn University Peshawar Abdus Salam

Amanullah Dept. Computing and Technology Absayn University Peshawar Abdus Salam A Comparative Study for Software Cost Estimation Using COCOMO-II and Walston-Felix models Amanullah Dept. Computing and Technology Absayn University Peshawar scholar.amankhan@gmail.com Abdus Salam Dept.

More information

Anticipating milk yield using artificial neural network

Anticipating milk yield using artificial neural network Int. Journal of Applied Sciences and Engineering Research, Vol. 3, Issue 3, 2014 www.ijaser.com 2014 by the authors Licensee IJASER- Under Creative Commons License 3.0 editorial@ijaser.com Research article

More information

Application of an Improved Neural Network Algorithm in E- commerce Customer Satisfaction Evaluation

Application of an Improved Neural Network Algorithm in E- commerce Customer Satisfaction Evaluation Application of an Improved Neural Network Algorithm in E- commerce Customer Satisfaction Evaluation Lei Yang 1,2 *, Ying Ma 3 1 Science and Technology Key Laboratory of Hebei Province, Baoding 071051,

More information

This article was originally published in a journal published by Elsevier, and the attached copy is provided by Elsevier for the author s benefit and for the benefit of the author s institution, for non-commercial

More information

Asian Research Consortium

Asian Research Consortium Asian Research Consortium Asian Journal of Research in Social Sciences and Humanities Vol. 6, No. 11, November 2016, pp. 26-40. Asian Journal of Research in Social Sciences and Humanities ISSN 2249-7315

More information

International Association of Scientific Innovation and Research (IASIR) (An Association Unifying the Sciences, Engineering, and Applied Research)

International Association of Scientific Innovation and Research (IASIR) (An Association Unifying the Sciences, Engineering, and Applied Research) International Association of Scientific Innovation and Research (IASIR) (An Association Unifying the Sciences, Engineering, and Applied Research) International Journal of Emerging Technologies in Computational

More information

Software Project Risk Assessment and Effort Contingency Model Based on COCOMO Cost Factors

Software Project Risk Assessment and Effort Contingency Model Based on COCOMO Cost Factors Western University Scholarship@Western Electrical and Computer Engineering Publications Electrical and Computer Engineering Department 3-2013 Software Project Risk Assessment and Effort Contingency Model

More information

Estimation of pesticides usage in the agricultural sector in Turkey using Artificial Neural Network (ANN)

Estimation of pesticides usage in the agricultural sector in Turkey using Artificial Neural Network (ANN) Publication date: 18 October 2009, http://www.biosciences.elewa.org/; ISSN 2071-7024 Estimation of pesticides usage in the agricultural sector in Turkey using Artificial Neural Network (ANN) Özbek F. Ş.

More information

Analysis Of the Techniques for Software Cost Estimation

Analysis Of the Techniques for Software Cost Estimation Analysis Of the Techniques for Software Cost Estimation Poonam Pandey Assistant Professor,GLA University,Mathura Email-poonam.pandey@gla.ac.in Abstract: One of the most valuable asset in any software industry

More information

Software Effort Estimation with Different Artificial Neural Network

Software Effort Estimation with Different Artificial Neural Network Software Effort with Different Artificial Neural Network Jagannath Singh Department of Computer Sc. and Engineering National Institute of Technology Rourkela Rourkela, India E-mail: jagannath.singh@gmail.com

More information

Application of Artificial Neural Networks to Estimate Wastewater Treatment Plant Inlet Biochemical Oxygen Demand

Application of Artificial Neural Networks to Estimate Wastewater Treatment Plant Inlet Biochemical Oxygen Demand Application of Artificial Neural Networks to Estimate Wastewater Treatment Plant Inlet Biochemical Oxygen Demand Emrah Dogan, a Asude Ates, b Ece Ceren Yilmaz, b Beytullah Eren b a Department of Civil

More information

presents the COnstructive COst MOdel (COCOMO): the most advanced, thoroughly calibrated software cost estimation model available today.

presents the COnstructive COst MOdel (COCOMO): the most advanced, thoroughly calibrated software cost estimation model available today. SOFTWARE ENGINEERING ECONOMICS BARRY W. BOEHM SUMMARY The primary learning objectives of Software Engineering Economies by Barry W. Boehm are to: identify the factors most strongly influencing software

More information

Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load

Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load Application and comparison of several artificial neural networks for forecasting the Hellenic daily electricity demand load L. EKONOMOU 1 D.S. OIKONOMOU 2 1 Hellenic American University, 12 Kaplanon Street,

More information

A Comparison of Different Model Selection Criteria for Forecasting EURO/USD Exchange Rates by Feed Forward Neural Network

A Comparison of Different Model Selection Criteria for Forecasting EURO/USD Exchange Rates by Feed Forward Neural Network A Comparison of Different Model Selection Criteria for Forecasting EURO/USD Exchange Rates by Feed Forward Neural Network Cagatay Bal, 1 *, Serdar Demir, 2 and Cagdas Hakan Aladag 3 Abstract Feed Forward

More information

Estimation of the Distance Travelled While Collecting Bales from a Field Using Artificial Neural Networks (ANN)

Estimation of the Distance Travelled While Collecting Bales from a Field Using Artificial Neural Networks (ANN) AENSI Journals Journal of Applied Science and Agriculture ISSN 1816-9112 Journal home page: www.aensiweb.com/jasa/index.html Estimation of the Distance Travelled While Collecting Bales from a Field Using

More information

COCOMO model for software based on Open Source: Application to the adaptation of TRIADE to the university system

COCOMO model for software based on Open Source: Application to the adaptation of TRIADE to the university system COCOMO model for software based on Open Source: Application to the adaptation of TRIADE to the university system Moulla Donatien Koulla / Ph.D Student University of Ngaoundéré Ngaoundéré, Cameroon donafice@yahoo.fr,

More information

Prediction of Cost of Quality Using Artificial Neural Network In Construction Projects

Prediction of Cost of Quality Using Artificial Neural Network In Construction Projects Prediction of Cost of Quality Using Artificial Neural Network In Construction Projects Chinchu Mary Jose 1, Ambili S 2 1 M Tech scholar,department of Civil Engineering,MES College of Engineering, Kuttippuram,

More information

Neural Networks and Applications in Bioinformatics. Yuzhen Ye School of Informatics and Computing, Indiana University

Neural Networks and Applications in Bioinformatics. Yuzhen Ye School of Informatics and Computing, Indiana University Neural Networks and Applications in Bioinformatics Yuzhen Ye School of Informatics and Computing, Indiana University Contents Biological problem: promoter modeling Basics of neural networks Perceptrons

More information

Artificial Neural Network Analysis of the Solar-Assisted Heat Pumps Performance for Domestic Hot Water Production

Artificial Neural Network Analysis of the Solar-Assisted Heat Pumps Performance for Domestic Hot Water Production Artificial Neural Network Analysis of the Solar-Assisted Heat Pumps Performance for Domestic Hot Water Production Alireza Zendehboudi, Xianting Li*, Siyuan Ran Department of Building Science, School of

More information

Resource Decisions in Software Development Using Risk Assessment Model

Resource Decisions in Software Development Using Risk Assessment Model Proceedings of the 39th Hawaii International Conference on System Sciences - 6 Resource Decisions in Software Development Using Risk Assessment Model Wiboon Jiamthubthugsin Department of Computer Engineering

More information

Optimizing Effort and Time Parameters of COCOMO II Estimation using Fuzzy Multi-Objective PSO

Optimizing Effort and Time Parameters of COCOMO II Estimation using Fuzzy Multi-Objective PSO Optimizing Effort and Time Parameters of COCOMO II Estimation using Fuzzy Multi-Objective PSO Kholed Langsari 1, Riyanarto Sarno 2 Department of Informatics Engineering Institut Teknologi Sepuluh Nopember

More information

Neural Networks and Applications in Bioinformatics

Neural Networks and Applications in Bioinformatics Contents Neural Networks and Applications in Bioinformatics Yuzhen Ye School of Informatics and Computing, Indiana University Biological problem: promoter modeling Basics of neural networks Perceptrons

More information

COMPRESSIVE STRENGTH MODELING OF SCC USING LINEAR REGRESSION AND ARTIFICIAL NEURAL NETWORK APPROACH

COMPRESSIVE STRENGTH MODELING OF SCC USING LINEAR REGRESSION AND ARTIFICIAL NEURAL NETWORK APPROACH SCC 2009-China, June 5-7 2009, Beijing,China COMPRESSIVE STRENGTH MODELING OF SCC USING LINEAR REGRESSION AND ARTIFICIAL NEURAL NETWORK APPROACH Rafat Siddique(1), Paratibha Aggarwal(2) and Yogesh Aggarwal(2)

More information

Parameter Optimization of SAW in Hardfacing Process Using Hybrid Approach of Adaptive Stimulated Annealing and Neural Networks

Parameter Optimization of SAW in Hardfacing Process Using Hybrid Approach of Adaptive Stimulated Annealing and Neural Networks Asian Journal of Engineering and Applied Technology ISSN 2249-068X Vol. 1. 2, 2012, pp.16-20 The Research Publication, www.trp.org.in Parameter Optimization of SAW in Hardfacing Process Using Hybrid Approach

More information

Research Paper on Software Cost Estimation Using Fuzzy Logic

Research Paper on Software Cost Estimation Using Fuzzy Logic Research Paper on Software Cost Estimation Using Fuzzy Logic Nishi M. Tech Scholar B.P.S.M.V University, Sonepat nishisinghal54@gmail.com Mr. Vikas Malik Assistant Professor B.P.S.M.V University, Sonepat

More information

Research Article Forecasting Bank Deposits Rate: Application of ARIMA and Artificial Neural Networks

Research Article Forecasting Bank Deposits Rate: Application of ARIMA and Artificial Neural Networks Research Journal of Applied Sciences, Engineering and Technology 7(3): 527-532, 2014 DOI:10.19026/rjaset.7.286 ISSN: 2040-7459; e-issn: 2040-7467 2014 Maxwell Scientific Publication Corp. Submitted: February

More information

A hybrid approach artificial bee colony optimization and k-means clustering for software cost estimation

A hybrid approach artificial bee colony optimization and k-means clustering for software cost estimation Journal of Scientific Research and Development 2 (4): 250-255, 2015 Available online at www.jsrad.org ISSN 1115-7569 2015 JSRAD A hybrid approach artificial bee colony optimization and k-means clustering

More information

Keywords COCOMO model, cost estimation, genetic algorithm, ant colony optimization.

Keywords COCOMO model, cost estimation, genetic algorithm, ant colony optimization. Volume 4, Issue 1, January 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com COCOMO model

More information

WATER LEVEL PREDICTION BY ARTIFICIAL NEURAL NETWORK IN THE SURMA-KUSHIYARA RIVER SYSTEM OF BANGLADESH

WATER LEVEL PREDICTION BY ARTIFICIAL NEURAL NETWORK IN THE SURMA-KUSHIYARA RIVER SYSTEM OF BANGLADESH WATER LEVEL PREDICTION BY ARTIFICIAL NEURAL NETWORK IN THE SURMA-KUSHIYARA RIVER SYSTEM OF BANGLADESH Robin Kumar Biswas MEE0877 Supervisor: Prof. A. W. Jayawardena ABSTRACT The nonlinear relationship

More information

Chapter 5 Estimate Influences

Chapter 5 Estimate Influences Dilbert Scott Adams Dilbert Scott Adams Chapter 5 Estimate Influences How much is 68 + 73? ENGINEER: It s 141. Short and sweet. MATHEMATICIAN: 68 + 73 = 73 + 68 by the commutative law of addition. True,

More information

Should Function Point Elements be Used to Build Prediction Models?

Should Function Point Elements be Used to Build Prediction Models? Should Function Point Elements be Used to Build Prediction Models? Kohei Yoshigami, Masateru Tsunoda Department of Informatics Kindai University Osaka, Japan tsunoda@info.kindai.ac.jp Yuto Yamada, Shinji

More information

NEURO-FUZZY CONTROLLER ALGORITHM FOR OBTAINING MAXIMUM POWER POINT TRACKING OF PHOTOVOLTAIC SYSTEM FOR DYNAMIC ENVIRONMENTAL CONDITIONS

NEURO-FUZZY CONTROLLER ALGORITHM FOR OBTAINING MAXIMUM POWER POINT TRACKING OF PHOTOVOLTAIC SYSTEM FOR DYNAMIC ENVIRONMENTAL CONDITIONS International Journal of Electrical and Electronics Engineering Research (IJEEER) ISSN 2250-155X Vol.2, Issue 3 Sep 2012 1-11 TJPRC Pvt. Ltd., NEURO-UZZY CONTROLLER ALGORITHM OR OBTAINING MAXIMUM POWER

More information

Neuro-Genetic Optimization of LDO-fired Rotary Furnace Parameters for the Production of Quality Castings

Neuro-Genetic Optimization of LDO-fired Rotary Furnace Parameters for the Production of Quality Castings International Journal of Engineering Research and Development e-issn: 2278-067X, p-issn: 2278-800X, www.ijerd.com Volume 11, Issue 06 (June 2015), PP.30-37 Neuro-Genetic Optimization of LDO-fired Rotary

More information

Prediction of Properties of Austempered Ductile Iron Assisted by Artificial Neural Network

Prediction of Properties of Austempered Ductile Iron Assisted by Artificial Neural Network ISSN 1392 132 MATERIALS SCIENCE (MEDŽIAGOTYRA). Vol. 12, No. 1. 26 Prediction of Properties of Austempered Ductile Iron Assisted by Artificial Neural Network Robert BIERNACKI, Jacek KOZŁOWSKI, Dawid MYSZKA,

More information

Improving the Accuracy of COCOMO II Using Fuzzy Logic and Local Calibration Method

Improving the Accuracy of COCOMO II Using Fuzzy Logic and Local Calibration Method Improving the Accuracy of COCOMO II Using Fuzzy Logic and Local Calibration Method Muhammad Baiquni, Riyanarto Sarno, Sarwosri Department of Informatics Engineering, Institut Teknologi Sepuluh Nopember

More information

Evaluation of Software Hazard and Cost by Commercial Point-of-View

Evaluation of Software Hazard and Cost by Commercial Point-of-View Evaluation of Software Hazard and Cost by Commercial Point-of-View Ankur Srivastava 1 Mahesh Kumar Singh 2, Abhimanyu Mishra 3 1 3 Assistant Professor, Department of CSE, Jahangirabad Group of Institutions,

More information

Advanced analytics at your hands

Advanced analytics at your hands 2.4 Advanced analytics at your hands Today, most organizations are stuck at lower-value descriptive analytics. But more sophisticated analysis can bring great business value. TARGET APPLICATIONS Business

More information

A Generalized Regression Neural Network Based on Soft Sensor for Multicomponent Distillation Column

A Generalized Regression Neural Network Based on Soft Sensor for Multicomponent Distillation Column A Generalized Regression Neural Network Based on Soft Sensor for Multicomponent Distillation Column Sanjay R. Patil 1 *, V. N. Ghate 2 1 Department of Instrumentation Engineering, Government College of

More information

Artificial Neural Network Modeling for Predicting Compaction Parameters based on Index Properties of Soil

Artificial Neural Network Modeling for Predicting Compaction Parameters based on Index Properties of Soil Artificial Neural Network Modeling for Predicting Compaction Parameters based on Index Properties of Soil Ashwini Tenpe 1, Dr. Suneet Kaur 2 1 Mtech Scholar, Civil Department, MANIT, Madhya Pradesh, India

More information

PREDICTING EMPLOYEE ATTRITION THROUGH DATA MINING

PREDICTING EMPLOYEE ATTRITION THROUGH DATA MINING PREDICTING EMPLOYEE ATTRITION THROUGH DATA MINING Abbas Heiat, College of Business, Montana State University, Billings, MT 59102, aheiat@msubillings.edu ABSTRACT The purpose of this study is to investigate

More information

+ Evaluation Technology of Software Reliability by using the BP Neural Network

+ Evaluation Technology of Software Reliability by using the BP Neural Network RESEARCH ARTICLE OPEN ACCESS + Evaluation Technology of Software Reliability by using the BP Neural Network D.Jyothirmai 1, M.Suresh Kumar 2, Dr.Katta Subba Rao 3 1 (CSE, BVRIT, Narsapur), 2 (Scientist-E,DRDO,Hyderabad,Telangana),

More information

Short-term electricity price forecasting in deregulated markets using artificial neural network

Short-term electricity price forecasting in deregulated markets using artificial neural network Proceedings of the 2011 International Conference on Industrial Engineering and Operations Management Kuala Lumpur, Malaysia, January 22 24, 2011 Short-term electricity price forecasting in deregulated

More information

Determining Nitriding Parameters with Neural Networks

Determining Nitriding Parameters with Neural Networks Journal of ASTM International, May 2005, Vol. 2, No. 5 Paper ID JAI12213 Available online at www.astm.org Tomislav Filetin, 1 Irena Žmak, 1 and Davor Novak 1 Determining Nitriding Parameters with Neural

More information

Optimized Fuzzy Logic Based Framework for Effort Estimation in Software Development

Optimized Fuzzy Logic Based Framework for Effort Estimation in Software Development ISSN (Online): 1694-784 ISSN (Print): 1694-814 Optimized Fuzzy Logic Based Framework for Effort Estimation in Software Development 3 Vishal Sharma 1 and Harsh Kumar Verma 2 1 Department of Computer Science

More information

Artificial Neural Network Model for Rainfall-Runoff -A Case Study

Artificial Neural Network Model for Rainfall-Runoff -A Case Study , pp. 263-272 http://dx.doi.org/10.14257/ijhit.2016.9.3.24 Artificial Neural Network Model for Rainfall-Runoff -A Case Study P.Sundara Kumar 1, T.V.Praveen 2 and M. Anjanaya Prasad 3 1 Research scholar,

More information

A Short-Term Bus Load Forecasting System

A Short-Term Bus Load Forecasting System 2 th International Conference on Hybrid Intelligent Systems A Short-Term Bus Load Forecasting System Ricardo Menezes Salgado Institute of Exact Sciences Federal University of Alfenase Alfenas-MG, Brazil

More information

Comparative Study on Prediction of Fuel Cell Performance using Machine Learning Approaches

Comparative Study on Prediction of Fuel Cell Performance using Machine Learning Approaches , March 16-18, 2016, Hong Kong Comparative Study on Prediction of Fuel Cell Performance using Machine Learning Approaches Lei Mao*, Member, IAENG, Lisa Jackson Abstract This paper provides a comparative

More information

Prediction of permeability from reservoir main properties using neural network

Prediction of permeability from reservoir main properties using neural network Scientific Research and Essays Vol. 6(32), pp. 6626-6635, 23 December, 2011 Available online at http://www.academicjournals.org/sre DOI: 10.5897/SRE11.686 ISSN 1992-2248 2011 Academic Journals Full Length

More information

Wind Power Generation Prediction for a 5Kw Wind turbine

Wind Power Generation Prediction for a 5Kw Wind turbine Bulletin of Environment, Pharmacology and Life Sciences Bull. Env. Pharmacol. Life Sci., Vol 3 (1) December 2013: 163-168 2013 Academy for Environment and Life Sciences, India Online ISSN 2277-1808 Journal

More information

arxiv: v1 [cs.lg] 26 Oct 2018

arxiv: v1 [cs.lg] 26 Oct 2018 Comparing Multilayer Perceptron and Multiple Regression Models for Predicting Energy Use in the Balkans arxiv:1810.11333v1 [cs.lg] 26 Oct 2018 Radmila Janković 1, Alessia Amelio 2 1 Mathematical Institute

More information

Stock Market Prediction with Multiple Regression, Fuzzy Type-2 Clustering and Neural Networks

Stock Market Prediction with Multiple Regression, Fuzzy Type-2 Clustering and Neural Networks Available online at www.sciencedirect.com Procedia Computer Science 6 (2011) 201 206 Complex Adaptive Systems, Volume 1 Cihan H. Dagli, Editor in Chief Conference Organized by Missouri University of Science

More information

3. PROPOSED MODEL. International Journal of Computer Applications ( ) Volume 103 No.9, October 2014

3. PROPOSED MODEL. International Journal of Computer Applications ( ) Volume 103 No.9, October 2014 Software Effort Estimation: A Fuzzy Logic Approach Vishal Chandra AI, SGVU Jaipur, Rajasthan, India ABSTRACT There are many equation based effort estimation models like Bailey-Basil Model, Halstead Model,

More information

Applying 2 k Factorial Design to assess the performance of ANN and SVM Methods for Forecasting Stationary and Non-stationary Time Series

Applying 2 k Factorial Design to assess the performance of ANN and SVM Methods for Forecasting Stationary and Non-stationary Time Series Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 22 (2013 ) 60 69 17 th International Conference in Knowledge Based and Intelligent Information and Engineering Systems

More information

A Trust Evaluation Model for Social Commerce Based on BP Neural Network

A Trust Evaluation Model for Social Commerce Based on BP Neural Network Journal of Data Analysis and Information Processing, 2016, 4, 147-158 http://www.scirp.org/journal/jdaip ISSN Online: 2327-7203 ISSN Print: 2327-7211 A Trust Evaluation Model for Social Commerce Based

More information

Optimization of Software Project. Risk Assessment. Using Neuro-Fuzzy Techniques

Optimization of Software Project. Risk Assessment. Using Neuro-Fuzzy Techniques Optimization of Software Project Risk Assessment Using Neuro-Fuzzy Techniques Mukesh Vijay Goyal Department of Computer Science and Engineering National Institute of Technology Rourkela Rourkela-769 008,

More information

Fusion beats extraction from ECG using neural network based soft computing techniques

Fusion beats extraction from ECG using neural network based soft computing techniques Available online at www.pelagiaresearchlibrary.com Advances in Applied Science Research, 2010, 1 (2): 76-83 ISSN: 0976-8610 CODEN (USA): AASRFC Fusion beats extraction from ECG using neural network based

More information

Prediction of coal-bed permeability from well logs using artificial neural network

Prediction of coal-bed permeability from well logs using artificial neural network P-108 Prediction of coal-bed permeability from well logs using Vishal Das* and Rima Chatterjee, Indian School of Mines Summary Prediction of permeability from well logs in heterogeneous formation is a

More information

Optimizing Effort Parameter of COCOMO II Using Particle Swarm Optimization Method

Optimizing Effort Parameter of COCOMO II Using Particle Swarm Optimization Method TELKOMNIKA, Vol.16, No.5, October 2018, pp.2208~2216 ISSN: 1693-6930, accredited First Grade by Kemenristekdikti, Decree No: 21/E/KPT/2018 DOI: 10.12928/TELKOMNIKA.v16i5.9703 2208 Optimizing Effort Parameter

More information

The Rosetta Stone: Making COCOMO 81 Files Work With COCOMO II

The Rosetta Stone: Making COCOMO 81 Files Work With COCOMO II The Rosetta Stone: Making COCOMO 81 Files Work With COCOMO II Donald J. Reifer, Reifer Consultants, Inc. Barry W. Boehm, University of Southern California Sunita Chulani, University of Southern California

More information

The prediction of electric energy consumption using an artificial neural network

The prediction of electric energy consumption using an artificial neural network Energy Production and Management in the 21st Century, Vol. 1 109 The prediction of electric energy consumption using an artificial neural network I. Chernykh 1, D. Chechushkov 1 & T. Panikovskaya 2 1 Department

More information

Prediction of Success or Failure of Software Projects based on Reusability Metrics using Support Vector Machine

Prediction of Success or Failure of Software Projects based on Reusability Metrics using Support Vector Machine Prediction of Success or Failure of Software Projects based on Reusability Metrics using Support Vector Machine R. Sathya Assistant professor, Department of Computer Science & Engineering Annamalai University

More information

SEISMIC ATTRIBUTES SELECTION AND POROSITY PREDICTION USING MODIFIED ARTIFICIAL IMMUNE NETWORK ALGORITHM

SEISMIC ATTRIBUTES SELECTION AND POROSITY PREDICTION USING MODIFIED ARTIFICIAL IMMUNE NETWORK ALGORITHM Journal of Engineering Science and Technology Vol. 13, No. 3 (2018) 755-765 School of Engineering, Taylor s University SEISMIC ATTRIBUTES SELECTION AND POROSITY PREDICTION USING MODIFIED ARTIFICIAL IMMUNE

More information

Benchmarking by an Integrated Data Envelopment Analysis-Artificial Neural Network Algorithm

Benchmarking by an Integrated Data Envelopment Analysis-Artificial Neural Network Algorithm 2013, TextRoad Publication ISSN 2090-4304 Journal of Basic and Applied Scientific Research www.textroad.com Benchmarking by an Integrated Data Envelopment Analysis-Artificial Neural Network Algorithm Leila

More information

ANeuroFuzzyAlgorithmtoComputeSoftwareEffortEstimation

ANeuroFuzzyAlgorithmtoComputeSoftwareEffortEstimation Global Journal of Computer Science and Technology: C Software & Data Engineering Volume 16 Issue 1 Version 1. Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals

More information

CHAPTER: 5 PREDICTION USING ARTIFICIAL NEURAL NETWORK

CHAPTER: 5 PREDICTION USING ARTIFICIAL NEURAL NETWORK CHAPTER: 5 PREDICTION USING ARTIFICIAL NEURAL NETWORK 5.1 LITERATURE SURVEY: Artificial neural networks (ANN) are data-processing systems which are regulated by biological neural system and are widely

More information

SOFTWARE DEVELOPMENT PRODUCTIVITY FACTORS IN PC PLATFORM

SOFTWARE DEVELOPMENT PRODUCTIVITY FACTORS IN PC PLATFORM SOFTWARE DEVELOPMENT PRODUCTIVITY FACTORS IN PC PLATFORM Abbas Heiat, College of Business, Montana State University-Billings, Billings, MT 59101, 406-657-1627, aheiat@msubillings.edu ABSTRACT CRT and ANN

More information

Nonconventional Technologies Review no. 4/2011 MODELING THE PLASMA ARC CUTTING PROCESS USING ANN

Nonconventional Technologies Review no. 4/2011 MODELING THE PLASMA ARC CUTTING PROCESS USING ANN MODELING THE PLASMA ARC CUTTING PROCESS USING ANN Miroslav RADOVANOVIC, Milos MADIC University of Nis, Faculty of Mechanical Engineering in Nis, Serbia Abstract: This paper deals with modeling of plasma

More information

[ED03] Automated low cost house demand forecasting for urban area

[ED03] Automated low cost house demand forecasting for urban area [ED03] Automated low cost house demand forecasting for urban area Noor Yasmin Zainun 1, Muhd Zaimi Abd. Majid 1 Faculty of Environment and Structural Engineering, Department of Building and Construction,

More information

Effort Estimation in Information Systems Projects using Data Mining Techniques

Effort Estimation in Information Systems Projects using Data Mining Techniques Effort Estimation in Information Systems Projects using Data Mining Techniques JOAQUÍN VILLANUEVA-BALSERA FRANCISCO ORTEGA-FERNANDEZ VICENTE RODRÍGUEZ-MONTEQUÍN RAMIRO CONCEPCIÓN-SUÁREZ Project Engineering

More information

Combining Back-Propagation and Genetic Algorithms to Train Neural Networks for Start-Up Time Modeling in Combined Cycle Power Plants

Combining Back-Propagation and Genetic Algorithms to Train Neural Networks for Start-Up Time Modeling in Combined Cycle Power Plants Combining Back-Propagation and Genetic Algorithms to Train Neural Networks for Start-Up Time Modeling in Combined Cycle Power Plants I. Bertini 1, M. De Felice 1,2, S. Pizzuti 1 1- ENEA (Italian Energy

More information

ADCHEM International Symposium on Advanced Control of Chemical Processes Gramado, Brazil April 2-5, 2006

ADCHEM International Symposium on Advanced Control of Chemical Processes Gramado, Brazil April 2-5, 2006 ADCHEM 2006 International Symposium on Advanced Control of Chemical Processes Gramado, Brazil April 2-5, 2006 AN INVERSE ARTIFICIAL NEURAL NETWORK BASED MODELLING APPROACH FOR CONTROLLING HFCS ISOMERIZATION

More information

A Treeboost Model for Software Effort Estimation Based on Use Case Points

A Treeboost Model for Software Effort Estimation Based on Use Case Points Western University Scholarship@Western Electrical and Computer Engineering Publications Electrical and Computer Engineering 12-2012 A Treeboost Model for Software Effort Estimation Based on Use Case Points

More information