Abstract
Feature selection (FS) plays vital role in reducing computing complexity of the models due to irrelevant features in the data with the intention to develop better predictive models. This process involves selecting significant features to apply in machine learning for model building, where redundant features are removed and new features developed. This approach involves selecting suitable features for use, removing redundant features and create new feature in the process of building models. The study focused on developing a predictive model that performs best for daily living activities (ADLs) using Activity Recognition with Ambient Sensing (ARAS). In this regard, we used feature importance, univariate, and correlation matrix to prepare ARAS dataset before modeling the data. The following algorithms were used to assess the accuracy of selected features, this includes; Logistic Regression (LR), SVM and KNN to learn and analyze the data. The results show that SVM outperformed in both House A and B, compared to other algorithms. Support Vector Machine (SVM) performed best on univariate feature selection with 10 features compared to 5 features with the accuracy of 100% from both House A and House B, while on feature importance selection SVM performed best with 5 features compared to 10 features with the accuracy of 99% from House A and 100% accuracy from House B. The feature selection has improved the prediction accuracy in ARAS dataset compared to the previous results, which achieved the accuracy of 61.5% in average score in House A and 76.2% accuracy for House B.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Brownlee J (2016) Machine learning mastery with Python: understand your data, create accurate models, and work projects end-to-end. Machine Learning Mastery
Raschka S, Mirjalili V (2017) Python machine learning. Packt Publishing Ltd
Kwon M-C, Choi S (2018) Recognition of daily human activity using an artificial neural network and smartwatch. Wirel Commun Mobile Comput 2018
Oukrich N, Maach A et al (2019) Human daily activity recognition using neural networks and ontology-based activity representation. In: Proceedings of the Mediterranean symposium on smart city applications. Springer, pp 622–633
Wang J, Chen Y, Hao S, Peng X, Lisha Hu (2019) Deep learning for sensor-based activity recognition: a survey. Pattern Recogn Lett 119:3–11
Igwe OM, Wang Y, Giakos GC (2018) “Activity learning and recognition using margin setting algorithm in smart homes. In: 2018 9th IEEE annual ubiquitous computing, electronics & mobile communication conference (UEMCON). IEEE
Fang H, Srinivasan R, Cook DJ (2012) Feature selections for human activity recognition in smart home environments. Int J Innov Comput Inf Control 8:3525–3535
Alemdar H, Ersoy C (2017) Multi-resident activity tracking and recognition in smart environments. J Ambient Intell Humaniz Comput 8(4):513–529
Alberdi A et al (2018) Smart home-based prediction of multidomain symptoms related to Alzheimer's disease. IEEE J Biomed Health Inf 22(6):1720–1731
Chen S, Fang H, Liu Z (2020) Human activity recognition based on extreme learning machine in smart home. J Phys Conf Ser 1437(1)
Fahad LG, Tahir FT (2020) Activity recognition in a smart home using local feature weighting and variants of nearest-neighbors classifiers. J Ambient Intell Humanized Comput, 1–10
Hameed J et al (2020) Enhanced classification with logistic regression for short term price and load forecasting in smart homes. In: 2020 3rd international conference on computing, mathematics and engineering technologies (iCoMET). IEEE
Manoj RJ, Anto Praveena MD, Vijayakumar K (2019) An ACO–ANN based feature selection algorithm for big data. Cluster Comput 22(2):3953–3960
Liu Y et al (2020) Daily activity feature selection in smart homes based on Pearson correlation coefficient. Neur Process Lett, 1–17
Tanaka K, Kurita T, Kawabe T (2007) Selection of import vectors via binary particle swarm optimization and cross-validation for kernel logistic regression. In: 2007 international joint conference on neural networks. IEEE
Fang H et al (2014) Human activity recognition based on feature selection in smart home using back-propagation algorithm. ISA Trans 53(5):1629–1638
Abudalfa S, Qusa H (2019) Evaluation of semi-supervised clustering and feature selection for human activity recognition. Int J Comput Digital Syst 8(6)
Rodriguez-Mier P, Mucientes M, BugarÃn A (2019) Feature selection and evolutionary rule learning for Big Data in smart building energy management. Cogn Comput 11(3):418–433
Oukrich N (2019) Daily human activity recognition in smart home based on feature selection, neural network and load signature of appliances. PhD thesis
Minor B, Cook DJ (2017) Forecasting occurrences of activities. Pervasive Mobile Comput 38:77–91
Zainab A, Refaat SS, Bouhali O (2020) Ensemble-based spam detection in smart home IoT devices time series data using machine learning techniques. Information 11(7):344
Alemdar H et al (2013) ARAS human activity datasets in multiple homes with multiple residents. In: 2013 7th international conference on pervasive computing technologies for healthcare and workshops. IEEE
Tang S et al (2019) Smart home IoT anomaly detection based on ensemble model learning from heterogeneous data. In: 2019 IEEE international conference on big data (big data). IEEE
Mohammadi M et al (2018) Deep learning for IoT big data and streaming analytics: a survey. IEEE Commun Surv Tutor 20(4):2923–2960
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kasubi, J.W., Manjaiah, D.H. (2022). Feature Selection Strategy for Multi-residents Behavior Analysis in Smart Home Environment. In: Sharma, N., Chakrabarti, A., Balas, V.E., Bruckstein, A.M. (eds) Data Management, Analytics and Innovation. Lecture Notes on Data Engineering and Communications Technologies, vol 71. Springer, Singapore. https://doi.org/10.1007/978-981-16-2937-2_2
Download citation
DOI: https://doi.org/10.1007/978-981-16-2937-2_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2936-5
Online ISBN: 978-981-16-2937-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)