Abstract
The biometrical characteristics of the human being such as fingerprints, eye (iris and retina), DNA, palm veins, and face recognition are competent to distinguish uniquely. Similarly, human activity recognition also carries research challenges to furnish an alternative way to identify and authenticate the human beings. The activity recognition contains a two-step process: sensing the raw data and extracting the features and classification. The experimental data used with this paper contains a single accelerometer embedded smartphone for sensing the walking patterns of users. We have intentionally excluded handicraft feature extracting techniques. The deep learning approach is used rather than classical machine learning algorithms. The automatic effective feature learning characteristics of deep learning reduce the barrier to be a domain expert. We have proposed a novel CNN model for user identification based on their activity patterns. The publically available user identification from the walking activity dataset on UCI repository has been used as the experimental dataset. Our model achieved 99.88% accuracy while user recognition based on walking patterns. This paper also includes a comparison study on our proposed model with classical machine learning algorithms listed as AdaBoost, decision tree, GaussianNB, linear discriminant, logistic regression, quadratic discriminant, and random forest. The recognition performance of random forest with 95.78% accuracy became close to our model. But, our model is more efficient than the random forest in case of recognition time consumption and accuracy.
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
Similar content being viewed by others
References
Mukhopadhyay SC (2015) Wearable sensors for human activity monitoring: a review. IEEE Sens J 15:1321–1330. https://doi.org/10.1109/JSEN.2014.2370945
Cook D, Feuz KD, Krishnan NC (2013) Transfer learning for activity recognition: a survey. Knowl Inf Syst 36:537–556. https://doi.org/10.1007/s10115-013-0665-3
Khan AM, Lee YK, Lee SY, Kim TS (2010) A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer. IEEE Trans Inf Technol Biomed 14:1166–1172. https://doi.org/10.1109/TITB.2010.2051955
Yin J, Yang Q, Member S, Pan JJ (2008) Sensor-based abnormal human-activity detection. 20:1082–1090
Ignatov A (2018) Real-time human activity recognition from accelerometer data using convolutional neural networks. Appl Soft Comput J 62:915–922. https://doi.org/10.1016/j.asoc.2017.09.027
Dehghani A, Sarbishei O, Glatard T, Shihab E (2019) A quantitative comparison of overlapping and non-overlapping sliding windows for human activity recognition using inertial sensors. Sensors (Switzerland) 19:10–12. https://doi.org/10.3390/s19225026
Rosati S, Balestra G, Knaflitz M (2018) Comparison of different sets of features for human activity recognition by wearable sensors. https://doi.org/10.3390/s18124189
Alsheikh MA, Selim A, Niyato D, Doyle L, Lin S, Tan HP (2016) Deep activity recognition models with triaxial accelerometers. AAAI Work Tech Rep WS-16-01:8–13
Kwapisz JR, Weiss GM, Moore SA (2010) Activity recognition using cell phone accelerometers. 12:74–82
Lara D, Labrador MA (2012) A mobile platform for real-time human activity recognition. 667–671
Anguita D, Ghio A, Oneto L, Parra X, Reyes-ortiz JL (2013) A public domain dataset for human activity recognition using smartphones. 24–26
Banos O, Galvez JM, Damas M, Pomares H, Rojas I (2014) Window size impact in human activity recognition. Sensors (Switzerland) 14:6474–6499. https://doi.org/10.3390/s140406474
Wang G, Li Q, Wang L, Wang W, Wu M, Liu T (2018) Impact of sliding window length in indoor human motion modes and pose pattern recognition based on smartphone sensors. Sensors (Switzerland) 18. https://doi.org/10.3390/s18061965
Zhu J, San-Segundo R, Pardo JM (2017) Feature extraction for robust physical activity recognition. Human-centric Comput Inf Sci 7:1–16. https://doi.org/10.1186/s13673-017-0097-2
Jansi R, Amutha R (2019) Sparse representation based classification scheme for human activity recognition using smartphones. Multimed Tools Appl 78:11027–11045. https://doi.org/10.1007/s11042-018-6662-5
Wang J, Chen Y, Hao S, Peng X, Hu L (2019) Deep learning for sensor-based activity recognition: a survey. Pattern Recognit Lett. https://doi.org/10.1016/j.patrec.2018.02.010
Bojan Kolosnjaji CE (2015) Neural network-based user-independent physical activity recognition for mobile devices. 378–386. https://doi.org/10.1007/978-3-319-24834-9
Casale P, Pujol O, Radeva P (2011) Human activity recognition from accelerometer data using a wearable device. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 6669:289–296. https://doi.org/10.1007/978-3-642-21257-4_36
Kim Y, Kang B, Kim D (2015) Hidden markov model ensemble for activity recognition using tri-axis accelerometer. https://doi.org/10.1109/SMC.2015.528
Anguita D, Ghio A, Oneto L, Parra X, Reyes-Ortiz JL (2012) Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics). 7657:216–223. https://doi.org/10.1007/978-3-642-35395-6_30
Shi D, Li Y, Ding B (2015) Unsupervised feature learning for human activity recognition. Guofang Keji Daxue Xuebao/J Natl Univ Def Technol 37:128–134. https://doi.org/10.11887/j.cn.201505020
Li D, Zhang H, Zhang M (2017) Wavelet de-noising and genetic algorithm-based least squares twin SVM for classification of arrhythmias. Circuits Syst Signal Process 36:2828–2846. https://doi.org/10.1007/s00034-016-0439-8
Song CK, Wang YQ, Song KT (2005) Remote activity monitoring of the elderly using a two-axis accelerometer
Bao L, Intille SS (2004) Activity recognition from user-annotated acceleration data BT—UbiComp 2002: Ubiquitous Computing. UbiComp Ubiquitous Comput 3001:1–17
Gani MO, Fayezeen T, Povinelli RJ, Smith RO, Arif M, Kattan AJ, Ahamed SI (2019) A light weight smartphone based human activity recognition system with high accuracy. J Netw Comput Appl 141:59–72. https://doi.org/10.1016/j.jnca.2019.05.001
Casale P, Pujol O, Radeva P (2012) Personalization and user verification in wearable systems using biometric walking patterns. Pers Ubiquitous Comput 16:563–580. https://doi.org/10.1007/s00779-011-0415-z
Thomas S, Bourobou M, Yoo Y (2015) User activity recognition in smart homes using pattern clustering applied to temporal ANN algorithm. 11953–11971. https://doi.org/10.3390/s150511953
Geng C, Song J (2016) Human action recognition based on convolutional neural networks with a convolutional auto-encoder. pp 933–938. https://doi.org/10.2991/iccsae-15.2016.173
Połap D, Woźniak M, Wei W, Damaševičius R (2018) Multi-threaded learning control mechanism for neural networks. Futur Gener Comput Syst 87:16–34. https://doi.org/10.1016/j.future.2018.04.050
Inoue M, Inoue S, Nishida T (2018) Deep recurrent neural network for mobile human activity recognition with high throughput. Artif Life Robot 23:173–185. https://doi.org/10.1007/s10015-017-0422-x
Chen WH, Baca CAB, Tou CH (2017) LSTM-RNNs combined with scene information for human activity recognition. In: 2017 IEEE 19th international conference e-health networking, application and services (Healthcom), 2017-Decem, pp 1–6. https://doi.org/10.1109/HealthCom.2017.8210846
Yamashita R, Nishio M, Do RKG, Togashi K (2018) Convolutional neural networks: an overview and application in radiology. Insights Imaging. https://doi.org/10.1007/s13244-018-0639-9
Bhandare A, Bhide M, Gokhale P, Chandavarkar R (2016) Applications of convolutional neural networks. Int J Comput Sci Inf Technol 7:2206–2215
Dataset Availability
The dataset has been used to conduct the user identification experiment, download from UCI repository named user identification from walking activity dataSet. The dataset is available at URL: http://archive.ics.uci.edu/ml/machine-learning-databases/00286/.
Code Availability
The python programming language is used to implement the concept of the proposed model. The experimental codes are available on GitHub with dataset and manual: https://github.com/prabhat-parth/User-Identification-Using-Walking-Patterns/.
Author Contributions
Prabhat Kumar designed the architecture, experiments, data analysis, and wrote the paper. S Suresh guided the paper writing and reviewed the paper. All authors review and authenticate the final manuscript.
Funding
This research has not received any external financial assists.
Conflicts of Interest
The authors declare no conflict of interest.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kumar, P., Suresh, S. (2021). Smartphone User Identification and Authentication Based on Raw Accelerometer Walking Activity Data Using Convolutional Neural Networks. In: Agrawal, S., Kumar Gupta, K., H. Chan, J., Agrawal, J., Gupta, M. (eds) Machine Intelligence and Smart Systems . Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-33-4893-6_4
Download citation
DOI: https://doi.org/10.1007/978-981-33-4893-6_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-4892-9
Online ISBN: 978-981-33-4893-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)