ESTIMATION OF THE EFFORT REQUIRED TO DEVELOP A SOFTWARE THROUGH THE K-NEAREST NEIGHBORS METHOD

Anca-Elena IORDAN, Florin COVACIU

Abstract


The purpose of the study presented in this article is to improve the efficiency of estimating the effort required to develop a software product by means of k-Nearest Neighbours machine learning method (KNN). The data set used for training KNN method is NASA93. The evaluation is related to the parameter tuning concept, KNN method being characterized by 2 parameters: the distance used to determine which are neighbours with common characteristics and the number of used neighbours for determining the prediction. To determine which version of KNN method provides the most accurate values for effort, three metrics were calculated: mean absolute error, mean squared error, and median absolute error. Implementation was done using Python programming language and Scikit-learn tool.

Full Text:

PDF

References


Panoiu, M., Panoiu, C., Mezinescu, S., Militaru, G., Baciu, I. Machine Learning Techniques Applied to the Harmonic Analysis of Railway Power Supply, Mathematics 2023, Vol. 11(6).

Iordan, A.E., Optimal Solution of the Guarini Puzzle Extension using Tripartite Graphs, IOP Conference Series: Materials Science and Engineering 2019, Vol. 477(1).

Marapelli, B., Software Development Effort Duration and Cost Estimation using Linear Regression and K-Nearest Neighbors, International Journal of Innovative Technology and Exploring Engineering 2019, Vol. 9(2), 1043–1047.

Covaciu, F., Iordan, A.E., Control of a Drone in Virtual Reality using MEMS Sensor Technology and Machine Learning, Micromachines 2022, Vol. 13(4), pp. 1-19.

Rob, R., Panoiu, C, Rusu Anghel, S., Intelligent System for tracking and logging the zigzag pantograph motion, Innovations in Intelligent Systems and Applications 2018.

Goyal, R., Chandra, P., Singh, Y., Suitability of KNN Regression in the Development of Interaction Based Software Fault Prediction Models, IERI Procedia 2014, Vol. 6, 15-21.

Sanchez, E.R., Santacruz, E.FV., Maceda, H.C., Effort and cost estimation using decision tree techniques and story points in agile software development, Mathematics 2023, Vol. 11, 1477.

Iordan, A.E., Supervised learning use to acquire knowledge from 2D analytic geometry problems, Recent Challenges in Intelligent Information and Database Systems 2022,189-200.

Dragicevic, S., Turic, M., Bayesian network model for task effort estimation in agile software development, Journal of Systems and Software 2017, Vol. 127, 109-119.

Iordan, A.E., Usage of Stacked Long Short-Term Memory for Recognition of 3D Analytic Geometry Elements, Proceedings of the 14th International Conference on Agents and Artificial Intelligence 2022, Vol. 3, 745-752.

Panoiu, M., Panoiu, C., Iordan, A., Ghiormez, L., Artificial neural networks in predicting current in electric arc furnaces, IOP Conference Series: Materials Science and Engineering 2014, Vol. 57(1), 012011.

Saif, A., A New Cost-Quality Estimation Model Based on Case-Based Reasoning Technique, International Journal of Computer Science and Mobile Computing 2021, Vol. 10(3), 46-54.

Iordan, A., Savii, G., Panoiu, M., Panoiu, C., Visual interactive environment for doing geometrical constructions, Wseas Transactions on Computers 2009, Vol. 8(2), 258-268.

Iordan, A., Development of an interactive environment used for simulation of shortest paths, Annals of the Faculty of Engineering Hunedoara 2012, Vol. 10(3), 97-102.

Mabayoje, A., Balogun, A., Hajarah, H., Atoyebi, J., Mojeed, H., Adeyemo, V., Parameter tuning in KNN for software defect prediction: an empirical analysis, Jurnal Teknologi dan Sistem Komputer 2019, Vol. 7(4), 121-126.

Lu, B., Charlton, M., Brunsdon, C., Harris, P., The Minkowski approach for choosing the distance metric in geographically weighted regression, International Journal of Geo-graphical Information Science 2015, Vol. 30(2), 1-18.

Iordan, A., Savii, G., Panoiu, M., Panoiu, C., Development of a dynamical software for teaching plane analytical geometry, Mathematic and Computers in Science and Engineering 2008, Vol. 5, 55-60.

Awar, N., Zhu, S., Biros, G., Gligoric, M., A performance portability framework for Python, Proceedings of the ACM International Conference on Supercom-puting, USA 2021, 467-478.

Amin, M.Z., Ali, A., An Intuitive Guide of K-Nearest Neighbor with Practical Implementation in Scikit Learn, International Journal of Engineering Research and Technology 2019.

Handelman, G.S., Kok, H.K., Chandra, R., Razavi, A., Huang, S., Brooks, M., Lee, M., Asadi, H., Peering into the Black Box of Artificial Intelligence: Evaluation Metrics of Machine Learning Methods, American Journal of Roentgenology 2019, 212, 38-43.

Iordan, A.E., Covaciu, F., Improving design of a triangle geometry computer application using a creational pattern, Acta Technica Napocensis: Applied Mathematics, Mecha-nics and Engineering 2020, Vol. 63(1), 73-78.


Refbacks

  • There are currently no refbacks.


JOURNAL INDEXED IN :