Open Access Open Access  Restricted Access Subscription Access
Cover Image


Alejandro Humberto Garcia Ruiz, Salvador Ibarra Martínez, José Antonio Castán Rocha, Julio Laria Menchaca, Jesús David Terán Villanueva


Intelligent environments are becoming more integrated into everyday life, making intelligent homes, reality. In this sense, this paper presents the results of a user-based learning model, dedicated to predict the human preferences in an intelligent home. The objective was to assess and determine the average performance of the proposed model for diverse types of users with different preferences each. Our model allows us to endow an intelligent home with the ability to learn from users, for the subsequent prediction of their preferences on the use of household appliances. In specific, the proposed model solves the adequate control of home lights. A methodology based on the artificial intelligence (AI) technique known as case-based reasoning (CBR) was used for the development of this model. Likewise, the Inductive Decision Tree (ID3) technique was implemented in the decision making of the model to provide with a suitable and trustworthy option for the studied problem. Two cases of study were evaluated with four diverse types of users each to assess the learning model. ID3 was able to predict all type of user preferences with an average performance of 98% in a set of 10,000 experiments. Additionally, the model achieved stability after 3,500 experiments. The stabilization capacity of the model was tested with the application of the cases of study, concluding that the model is able to provide solutions to the preferences of users belonging to completely different lifestyles. Finally, some conclusions are presented, emphasizing the advantages of using ID3 in the intelligent home decision making.


Case-Based Reasoning; Inductive Decision Tree; Intelligent Home; Intelligent Environments; Ubiquitous Computing

Full Text:



Aamodt, A. and Plaza, E. (1994). Case-Based Reasoning: Foundational Issues, Methodological Variations, and System.

Ahlawat, A. and Suri, B. (2016). Improving classification in data mining using hybrid algorithm. Delhi: 2016 1st India International Conference on Information Processing (IICIP).

Ahmed, M., Mohamed, A., Shareef, H., Homod, R. and Ali, A. (2016). Artificial neural network based controller for home energy management considering demand response events. Putrajaya: 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering (ICAEES).

Álvarez, C. R. (1994). Estadística multivariante y no paramétrica con SPSS: aplicación a las ciencias de la salud. España: Ediciones Díaz de Santos.

De Paz, J., Bajo, J., Rodríguez, S., Villarrubia, G. and Corchado, J. (2016). Intelligent system for lighting control in smart cities. Elsevier: In Information Sciences, Volume 372.

Duzen, Z. and Aktas, M. S. (2016). An approach to hybrid personalized recommender systems. Sinaia: 2016 International Symposium on INnovations in Intelligent SysTems and Applications (INISTA).

Fernandes, F. et al. (2016). Intelligent energy management using CBR: Brazilian residential consumption scenario. Athens: 2016 IEEE Symposium Series on Computational Intelligence (SSCI).

Fernández, J. A. (2008). Aplicación de los sistemas neurodifusos a la interpretación automática de imágenes de satélite. España: Universidad Almería.

INEGI. (2015). Panorama sociodemográfico de México. México: Instituto Nacional de Estadística y Geografía.

Joh, D. (1997). CBR in Changing Enviroment. Case Based Reasoning Research And Development. Providence, IR, USA: ICCBR-97.

Kang, Y. C. and Liao, Y. F. (2017). Using decision tree to predict the occupational hazards and the return-to-work labors. Sapporo: 2017 International Conference on Applied System Innovation (ICASI).

Kolodner, J. (1983a). Maintaining Organization in a Dynamic Long-Term Memory. Cognitive Science, Vol. 7. pp 243 - 280.

Kolodner, J. (1983b). Reconstructive memory, a computer model. Cognitive Science, Vol. 7. pp 281 - 328.

Kolodner, J. (1993). Case-Based Reasoning. San Mateo. CA: Morgan Kaufmann.

Laza, R., Fernandez, F. and Corchado, J. (2000). Sistemas de Razonamiento Basado en Casos para el Soporte a la Toma de. España: Universidad de Vigo, Campus As Lagoas 32004.

Rodríguez, M., Álvarez, S. and Bravo, E. (2001). Coeficientes de Asociación. México: Plaza y Valdes.

Somvanshi, M. and Chavan, P. (2016). A review of machine learning techniques using decision tree and support vector machine. Pune: 2016 International Conference on Computing Communication Control and automation (ICCUBEA).

Souza, C. R. (2014). The Accord.NET Framework. São Carlos, Brazil:

Watson, L. and Marir, F. (1994). Case-Based Reasoning: A Review. Cambridge University: The knowledge Engineering Review Vol. 9.

Zaher, R., Chaccour, K. and Badr, G. (2016). Intelligent Software Simulation of Water Consumption in Domestic Homes. Cambridge: 2016 UKSim-AMSS 18th International Conference on Computer Modelling and Simulation (UKSim).

Zaouali, K., Ammari, M. L., Bouallegue, R., Sahloul, I. and Chouaieb, A. (2016). Incoming Data Prediction in Smart Home Environment With HMM-Based Machine Learning. Tunis: 2016 International Symposium on Signal, Image, Video and Communications (ISIVC).


  • There are currently no refbacks.