Software Cost Estimation using Single Layer Artificial Neural Network

The most challenging task of software project management is the cost estimation. Cost estimation is to accurately assess required assets and schedules for software improvement ventures and it includes a number of things under its wide umbrella, for example, estimation of the size of the software product to be produced, estimation of the effort required, and last but not the least estimating the cost of the project. The overall project life cycle is impacted by the accurate prediction of the software development cost. The COCOMO model makes employments of single layer feed forward neural system while being actualized and prepared to utilize the perceptron learning algorithm. To test and prepare the system the COCOMO dataset is actualized. This paper has the goal of creating the quantitative measure in not only the current model but also in our proposed model.


I. INTRODUCTION
Estimation of required assets and calendar should be possible through precise cost estimation. Talking about the parameters, the exactness of the product advancement and the precision of the administration choices both are interrelated. The exactness of the previous is dependent on the precision of the last mentioned in terms of relying that is the former will rely on the latter. There are number of parameters for example improvement time, effort estimation and group, and for the calculation of each one of the models is required. For estimation of software cost effort estimation technique used most popular COCOMO model. What is unique about COCOMO model is that it makes use of mathematical formula to analyze project cost effort estimation. The paper based on COCOMO model is making use of single layer neural network technique using perception algorithm.

II. COCOMO
The Constructive Cost Model or better known as the COCOMO model, first presented by Dr. Barry Boehm in 1981 surpassed all the software development practices that took place in those days. Software development techniques have been undergoing many changes and evolving since those days. The COCOMO model can be sub-divided in following models based on the type of application [ 12]. 3. Personnel attributes  Analyst capability or better known as ACAP  Application experience or better known as AEXP  Programmer capability or better known as PCAP  Virtual machine experience or better known as VEXP  Programming language experience or better known as LEXP 4. Project attributes  Modern programming practices or better known as MODP  Use of software tools or better known as TOOLS  Required development schedule or better known as SCED [12].

A. Basic COCOMO
III. ARTIFICIAL NEURAL NETWORK An Artificial Neural Network (ANN) is nonlinear information (signal) processing devices, which are built from interconnected elementary processing devices called neurons. An Artificial Neural Network (ANN) is an information-processing model that is stimulated by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons) working in unification to resolve specific tribulations [15].  Figure 1 shows a simple artificial neural network with two inputs neurons (1, 2) and one output neuron (O). The interconnected weights are given by w1 and w2. There always exists a common bias of '1'. The input neurons are connected to the output neurons through weighted interconnections. This is a single layer network because it has only one layer of interconnections between the input and the output neurons. This network perceives the input signal received and performs the classification [15].

IV. RELATED WORK
Researchers in effort estimation models have developed multiple software's. Artificial neural network is capable for generating good information and modeling complex non-linear relationships. For the calculation of software effort estimation researchers all across the world have used the artificial neural network approach. Moreover, Boehm's COCOMO dataset is also used. N.Tadayon [9] reports the use of neural network with a back propagation. Anupma Kaushik [12] also research on multilayer neural network using perceptron learning algorithm. COCOMO [8] is the most effective and widely used software for effort estimation model, which arranges beneficial expert knowledge. For getting appropriate calculations COCOMO model is one of the most imperative tools, that produces capacity for developing effort estimation models with better analytical accuracy. In this paper, single layer feed forward neural network using perceptron learning algorithm and COCOMO data set have been used. Using this approach, an effort estimation model for software cost evaluation has been proposed.

V. PROPOSED NEURAL NETWORK MODEL
In proposed system Single Layer ANN used to calculate the software cost estimation. For this 16 input parameters are taken which includes 15 Effort Multiplier (EM) and one bias weight (b). First we calculate the net input output (sum of the product of each input neuron to their corresponding weight) after this applies identity activation function get estimated output.
A. Estimated Effort The System is implemented with the help of single layer artificial neural network and trained using the perceptron leaning algorithm. The COCOMO dataset is used to train to test the network. Sum = sum+ EMi * Wi Oest =b+ Sum; MRE = ((oact -oest) / oact) * 100; Here Oest is the estimated effort, Wi effort multiplier weight, MRE is magnitude relative error, Oact actual effort It describes about experimenting networks and calculating new set of weight.

VI. EVALUATION CRITERIA AND RESULTS
In this area, we depict the procedure utilized for figuring endeavors and the outcomes get when actualizing proposed neural system model to the COCOMO information set [14].     VII. CONCULSION Having a dependable and precise estimate of software development has never been an easy task and this is where has always lied the problem for many scholarly and industrial conglomerates since ages. Talking about anticipating the future programming shows how a cost estimation model is built based on single layer artificial neural network. The neural network that is used to estimate the software improvement effort is single layer feed forward network with identity activation function. Accurate value is attained through neural network. In future, for software cost estimation we will put our focus on neuro fuzzy approach.