A user behavior prediction model based on parallel neural network and k-nearest neighbor algorithms

In the last decade, we have witnessed the dramatic development of the smart home industry. Smart home systems are currently facing an explosive growth of data. Making good use of this vast amount of data has become an attractive research topic in recent years. In order to develop smart home systems’ abilities for learning users’ behaviors autonomously and offering services spontaneously, a user behavior prediction model based on parallel back propagation neural network (BPNN) and k-nearest neighbor (KNN) algorithms is introduced in this paper. Based on MapReduce, a parallel BPNN algorithm is proposed to improve the prediction accuracy and speed, and a parallel KNN algorithm is developed for user decision-making rule selection. The experimental results indicate that the proposed model is significantly better than traditional user behavior prediction models in term of prediction accuracy and speed. A case study on smart home also illustrates the effectiveness of the proposed model.

[1]  Xing Xie,et al.  User-Service Rating Prediction by Exploring Social Users' Rating Behaviors , 2016, IEEE Transactions on Multimedia.

[2]  Wei Wu,et al.  A multi-agent based failure prediction method using neural network algorithm , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[3]  Athanasios V. Vasilakos,et al.  A Survey on Service-Oriented Network Virtualization Toward Convergence of Networking and Cloud Computing , 2012, IEEE Transactions on Network and Service Management.

[4]  D. Camerino,et al.  Estimating the Impact of Workplace Bullying: Humanistic and Economic Burden among Workers with Chronic Medical Conditions , 2015, BioMed research international.

[5]  Maureen Schmitter-Edgecombe,et al.  Automated Cognitive Health Assessment From Smart Home-Based Behavior Data , 2016, IEEE Journal of Biomedical and Health Informatics.

[6]  Lavanya Ramakrishnan,et al.  Processing Cassandra Datasets with Hadoop-Streaming Based Approaches , 2016, IEEE Transactions on Services Computing.

[7]  B. Kalaavathi,et al.  An Optimized User Behavior Prediction Model Using Genetic Algorithm on Mobile Web Structure , 2015, KSII Trans. Internet Inf. Syst..

[8]  Justine Rochas,et al.  K Nearest Neighbour Joins for Big Data on MapReduce: A Theoretical and Experimental Analysis , 2016, IEEE Transactions on Knowledge and Data Engineering.

[9]  Keqin Li,et al.  An Intelligent Economic Approach for Dynamic Resource Allocation in Cloud Services , 2015, IEEE Transactions on Cloud Computing.

[10]  Tushar Rane,et al.  A Survey on Efficient Big Data Clustering using MapReduce , 2015 .

[11]  Fei Chen,et al.  A Parallel Algorithm for Datacleansing in Incomplete Information Systems Using MapReduce , 2014, 2014 Tenth International Conference on Computational Intelligence and Security.

[12]  Yang Liu,et al.  Economical and Balanced Energy Usage in the Smart Home Infrastructure: A Tutorial and New Results , 2015, IEEE Transactions on Emerging Topics in Computing.

[13]  Weishan Zhang,et al.  A Distributed Video Management Cloud Platform Using Hadoop , 2015, IEEE Access.

[14]  Tommi Kramer,et al.  Enrichment of Smart Home Services by Integrating Social Network Services and Big Data Analytics , 2016, 2016 49th Hawaii International Conference on System Sciences (HICSS).

[15]  Mohammad Al Hasan,et al.  An Iterative MapReduce Based Frequent Subgraph Mining Algorithm , 2013, IEEE Transactions on Knowledge and Data Engineering.

[16]  Sajad Ahmadian,et al.  Training back propagation neural networks using asexual reproduction optimization , 2015, 2015 7th Conference on Information and Knowledge Technology (IKT).

[17]  Dmitry Vavilov,et al.  Smart home user's behavior prediction , 2013, 2013 IEEE Third International Conference on Consumer Electronics ¿ Berlin (ICCE-Berlin).

[18]  Jian Ming Cui,et al.  Data Mining with BP Neural Network Algorithm Based MapReduce , 2013 .

[19]  Issa M. Khalil,et al.  Prediction of User's Web-Browsing Behavior: Application of Markov Model , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[20]  Kuang-Chao Fan,et al.  A Long-Stroke Nanopositioning Control System of the Coplanar Stage , 2014, IEEE/ASME Transactions on Mechatronics.

[21]  Gonzalo Hernández,et al.  Detection of abnormal processes of wine fermentation by support vector machines , 2016, Cluster Computing.

[22]  Youngki Kim,et al.  Establishing the importance weight of appropriability mechanism by using AHP: the case of the China’s electronic industry , 2016, Cluster Computing.

[23]  Mingtian Zhou,et al.  Cyber Insider Threats Situation Awareness Using Game Theory and Information Fusion-based User Behavior Predicting Algorithm , 2011 .

[24]  Hartmut Schmeck,et al.  User behavior prediction for energy management in smart homes , 2011, 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).

[25]  Jenq-Muh Hsu,et al.  A Semantic and Environment Models-Based User Behavior Prediction Scheme in Smart Home , 2012 .

[26]  Ke Xu,et al.  Toward software defined smart home , 2016, IEEE Communications Magazine.

[27]  Weisong Shi,et al.  Workload Analysis, Implications, and Optimization on a Production Hadoop Cluster: A Case Study on Taobao , 2014, IEEE Transactions on Services Computing.

[28]  Ahmed Abdulhakim Al-Absi,et al.  Long Read Alignment with Parallel MapReduce Cloud Platform , 2015, BioMed research international.

[29]  Juan C. Yelmo,et al.  A Personal Data Framework for Distributed User Modelling in New Service Ecosystems , 2015, IEEE Latin America Transactions.