Table 4 - uploaded by Iqra Qasim
Content may be subject to copyright.
Source publication
One of the most valuable asset in any software industry is the correct estimation of effort and hence cost estimation (CE) of the software to be developed by them. Although several CE techniques and models have been proposed by the researches, no research study is available yet to the best of our knowledge that analyze and summarize the latest CE d...
Contexts in source publication
Context 1
... 5 shows 10 most important factors required to estimate the cost of a project accurately. Table 4 shows 9 different tools discussed in the selected studies are identified and listed. ...
Similar publications
In this paper we discuss the use of COCOMO II (Constructive Cost Model) to estimate the cost of software engineering. The COCOMO II which allow us estimate the cost, effort and scheduling when planning new software development. We use the effort equation guidance to find the number of person / months which is needed to complete the project and dura...
Software projects encompass many challenges and difficulties with high risks of such projects end in failure. Really, Software projects have high failure rates, they appear to linger around 65% for major projects. Concurrently, project cost estimation is considering one of the main development activities which occurs the failure of software project...
Citations
... Inaccurate estimation can result in project failure and escalation in project costs. Some of the reasons for inaccurate estimation of software projects include the following: inaccurate project goal setting, project scheduling, required development effort (capability, estimation, and availability), project budgeting, project risk management, stakeholder politics, and market pressures [5]. Effective estimates are critical in the decision-making process. ...
E ective software cost estimation signi cantly contributes to decision-making. e rising trend of using nature-inspired meta-heuristic algorithms has been seen in software cost estimation problems. e constructive cost model (COCOMO) method is a well-known regression-based algorithmic technique for estimating software costs. e limitation of the COCOMO models is that the values of these coe cients are constant for similar kinds of projects whereas, in reality, these parameters vary from one organization to another organization. erefore, for accurate estimation, it is necessary to ne-tune the coe cients. e research community is now examining deep learning (DL) as a forward-looking solution to improve cost estimation. Although deep learning architectures provide some improvements over existing at technologies, they also have some shortcomings, such as large training delays, over-tting, and under-tting. Deep learning models usually require ne-tuning to a large number of parameters. e meta-heuristic algorithm supports nding a good optimal solution at a reasonable computational cost. Additionally, heuristic approaches allow for the location of an optimum solution. So, it can be used with deep neural networks to minimize training delays. e hybrid of ant colony optimization with BAT (HACO-BA) algorithm is a hybrid optimization technique that combines the most common global optimum search technique for ant colonies (ACO) in association with one of the newest search techniques called the BATalgorithm (BA). is technology supports the solution of multivariable problems and has been applied to the optimization of a large number of engineering problems. is work will perform a twofold assessment of algorithms: (i) comparing the e cacy of ACO, BA, and HACO-BA in optimizing COCOMO II coe cients; and (ii) using HACO-BA algorithms to optimize and improve the deep learning training process. e experimental results show that the hybrid HACO-BA performs better as compared to ACO and BA for tuning COCOMO II. HACO-BA also performs better in the optimization of DNN in terms of execution time and accuracy. e process is executed upto 100 epochs, and the accuracy achieved by the proposed DNN approach is almost 98% while NN achieved accuracy of up to 85% on the same datasets.
... Berdasarkan penelitian Systematic Literature Review yang telah dilakukan oleh (El Bajta et al., 2015), berhasil meringkas sembilan pertanyaan penelitian tentang estimasi biaya pada perangkat lunak yang mana didalamnya juga membahas tentang performa estimasi biaya, namun dalam penelitian tersebut belum menjelaskan lebih tentang faktor apa saja yang berpengaruh terhadap teknik estimasi biaya. Selanjutnya, penelitian yang dilakukan oleh (Qasim et al., 2018) berhasil menganalisis perkembangan estimasi biaya dengan menjawab dua pertanyaan penelitian berdasarkan 32 studi penelitian dalam kurun waktu 2009-2017, namun dalam penelitian tersebut juga belum membahas lebih tentang faktor yang berpengaruh terhadap estimasi biaya. Oleh karena itu, penelitian ini bertujuan untuk melakukan Systematic Literature Review (SLR) tentang analisis dan evaluasi beberapa studi primer pilihan, yang dapat membantu merekomendasikan metode estimasi biaya atau kombinasi metode estimasi biaya terbaik berdasarkan ketepatan akurasi teknik tersebut beserta faktor-faktor yang paling banyak digunakan oleh penelitian-penelitian terkini dalam melakukan estimasi biaya. ...
... Pada Gambar 2, jenis metode yang banyak digunakan adalah jenis metode nonparametrik. Jenis metode nonparametrik adalah metode yang dihitung berdasarkan pada teknik artificial intelligence dan machine learning (Qasim et al., 2018 Jenis metode estimasi biaya perangkat lunak parametrik adalah metode perhitungan matematis yang didasarkan pada data historis (Qasim et al., 2018). Ada empat metode usulan yang termasuk dalam jenis metode parametrik yaitu COCOMO II, Bailey-Basili, Homeostasis Mutation Based Differential Evolution (HMBDE), dan Use Case Point (UCP). ...
... Pada Gambar 2, jenis metode yang banyak digunakan adalah jenis metode nonparametrik. Jenis metode nonparametrik adalah metode yang dihitung berdasarkan pada teknik artificial intelligence dan machine learning (Qasim et al., 2018 Jenis metode estimasi biaya perangkat lunak parametrik adalah metode perhitungan matematis yang didasarkan pada data historis (Qasim et al., 2018). Ada empat metode usulan yang termasuk dalam jenis metode parametrik yaitu COCOMO II, Bailey-Basili, Homeostasis Mutation Based Differential Evolution (HMBDE), dan Use Case Point (UCP). ...
p>Estimasi biaya sampai sekarang masih menjadi salah satu permasalahan utama dalam perencanaan proyek perangkat lunak. Estimasi biaya ini memiliki peran yang penting karena berpengaruh pada berjalannya proyek dan menjadi penentu keberhasilan suatu proyek perangkat lunak. Kegagalan estimasi biaya dalam perencanaan proyek perangkat lunak dapat menyebabkan proyek tidak berjalan dengan baik dan menimbulkan kerugian bagi perusahaan. Oleh karena itu, banyak peneliti sampai saat ini masih mencari dan melakukan penelitian untuk mendapatkan estimasi terbaik. Berbagai metode diusulkan untuk mendapatkan ketepatan akurasi dengan memperhatikan faktor-faktor estimasi biaya. Tujuan penelitian ini adalah membuat Systematic Literature Review (SLR) yang berisi rangkuman dan analisis perkembangan penelitian terbaru tentang estimasi biaya pada perangkat lunak, khususnya pada metode yang digunakan serta faktor-faktor yang mempengaruhi. Penelitian ini berhasil mengkaji 21 penelitian lain dalam lima tahun terakhir (2015-2020) dan didapatkan 24 metode usulan yang terbagi menjadi tiga jenis metode yang sering digunakan dalam melakukan estimasi biaya perangkat lunak yaitu nonparametrik, parametrik dan semiparametrik. Selain itu, penelitian ini juga berhasil menemukan metode dan kombinasi metode terbaik berdasarkan ketepatan akurasi beserta lima faktor utama yang mempengaruhi estimasi biaya sehingga dapat digunakan para peneliti atau praktisi lain untuk mengembangkan estimasi biaya pada proyek perangkat lunak.
Abstract
Cost estimation has an important role because it affects the project’s progress and determines the success of a software project. Failure to estimate costs in software project planning can cause the project to not run well and cause losses to the company. Therefore, many researchers are still looking for and researching to get the best estimation by considering the cost estimation factors. The purpose of this study is to create a Systematic Literature Review (SLR) which contains a summary and analysis of the latest research developments on cost estimation in software, especially in the methods used and the factors that affect cost estimation. This study successfully reviewed 21 other studies in the last five years (2015-2020) and obtained 24 planning methods which are divided into three types of methods that are often used in conducting software cost research, namely nonparametric, parametric and semiparametric. Besides, this study also succeeded in finding the best method and combination of methods based on best accuracy, namely COCOMO II and the combination of Genetic Algorithm and Artificial Bee Colony, along with the five main factors that influence cost estimation so that it can be used by researchers or other practitioners to develop cost estimates for software projects.
</p
... Collection of associative memory neural networks (ENNA) is a machine learning algorithm for calculating computer effort estimates that improve accuracy and robustness compared to neural networks. Qasim et al. [1] examined that Fuzzy Emotional COCOMO II System Cost Estimation (FECSCE) does not find other problem areas for validity as well as project features for system cost estimation. ...
Cost estimation has evolved over the years since it came into existence. There have been many recent developments in Software Engineering over the years in this age of Artificial Intelligence and Machine learning, different software engineering metrics are analyzed; the predictions are deciphered and made. Cost estimation is one of these tasks that is of great importance in improving the quality of software that helps software developers and testers to concentrate on modules without worrying about the budget. The most substantial software development activity is the accurate estimation of cost in the project. The ambiguity and complexity of the software system made it the most complicated task to develop a cost-efficient software and contributed to the tendency of systems towards modern streamlined methods. In this paper, we have analyzed multiple cost estimation techniques and drawn comparison among them in order to individually highlight the importance of each technique.
Effort estimation is the most critical activity for the success of overall solution delivery in software engineering projects. In this context, the paper’s main contributions to the literature on software effort estimation are twofold. First, this paper examines the application of meta-heuristic algorithms to have a logical and acceptable parametric model for software effort estimation. Secondly, to unravel the benefits of nature-inspired meta-heuristic algorithms usage in optimizing Deep Learning (DL) architectures for software effort estimation, this paper presents a Deep Neural Network (DNN) model for software effort estimation based on meta-heuristic algorithms. In this paper, Grey Wolf Optimizer (GWO) and StrawBerry (SB) meta-heuristic algorithms are applied for having a logical and acceptable parametric model for software effort estimation. To validate the performances of these two algorithms, a set of nine benchmark functions having wide dimensions is applied. Results from GWO and SB algorithms are compared with five other meta-heuristic algorithms used in literature for software effort estimation. Experimental results showed that the GWO has comprehensive superiority in terms of accuracy in estimation. The proposed DNN model (GWDNNSB) using meta-heuristic algorithms for initial weights and learning rate selection, produced better results compared to existing work on using DNN for software effort estimation.
