Human Activity Recognition by Using Different Deep Learning Approaches for Wearable Sensors


With the spread of wearable sensors, the solutions to the task of activity recognition by using the data obtained from the sensors have become widespread. Recognition of activities owing to wearable sensors such as accelerometers, gyroscopes, and magnetometers, etc. has been studied in recent years. Although there are several applications in the literature, differently in this study, deep learning algorithms such as Convolutional Neural Networks, Convolutional LSTM, and 3D Convolutional Neural Networks fed by Convolutional LSTM have been used in human activity recognition task by feeding with data obtained from accelerometer sensor. For this purpose, a frame was formed with raw samples of the same activity which were collected consecutively from the accelerometer sensor. Thus, it is aimed to capture the pattern inherent in the activity and due to preserving the continuous structure of the movement.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8


  1. 1.

    Tateno S, Meng F, Qian R, Li T (2020) Human motion detection based on low resolution infrared array sensor. IN: 2020 59th Annual conference of the society of instrument and control engineers of Japan (SICE), Chiang Mai, Thailand, 2020, pp 1016–1021

  2. 2.

    Paydarfar AJ, Prado A, Agrawal SK (2020) Human activity recognition using recurrent neural network classifiers on raw signals from insole piezoresistors. In: 2020 8th IEEE RAS/EMBS international conference for biomedical robotics and biomechatronics (BioRob), New York City, NY, USA, pp 916–921.

  3. 3.

    Ihianle IK, Nwajana AO, Ebenuwa SH, Otuka RI, Owa K, Orisatoki MO (2020) A deep learning approach for human activities recognition from multimodal sensing devices. IEEE Access 8:179028–179038.

    Article  Google Scholar 

  4. 4.

    Krishnaprabha KK, Raju CK (2020) Predicting human activity from mobile sensor data using CNN architecture. In: 2020 Advanced computing and communication technologies for high performance applications (ACCTHPA), Cochin, India, pp 206–210.

  5. 5.

    Masum AKM, Bahadur EH, Shan-A-Alahi A, Uz Zaman Chowdhury MA, Uddin MR, Al Noman A (2019) Human activity recognition using accelerometer, gyroscope and magnetometer sensors: deep neural network approaches. In: 2019 10th International conference on computing, communication and networking technologies (ICCCNT), Kanpur, India, pp 1–6.

  6. 6.

    Erdaş ÇB, Atasoy I, Açıcı K, Oğul H (2016) Integrating features for accelerometer-based activity recognition. ProcediaComputSci 98:522–527

    Google Scholar 

  7. 7.

    Ravi N, Dandekar N, Mysore P, Littman ML (2005) Activity recognition from accelerometer data. American Association for Artificial Intelligence, Menlo Park, pp 1541–1546

    Google Scholar 

  8. 8.

    Lester J, Choudhury T, Borriello G (2006) A practical approach to recognizing physical activities. In: Fishkin KP, Schiele B, Nixon P, Quigley A (eds) PERVASIVE 2006. LNCS, vol 3968. Springer, Heidelberg, pp 1–16

    Google Scholar 

  9. 9.

    Yurtman A, Barshan B (2017) Activity recognition ınvariant to sensor orientation with wearable motion sensors. Sensors 17(8):1838.

    Article  Google Scholar 

  10. 10.

    Qin Z, Zhang Y, Meng S, Qin Z, Choo K-KR (2020) Imaging and fusing time series for wearable sensor-based human activity recognition. Inf Fusion 53:80–87

    Article  Google Scholar 

  11. 11.

    Güney S, Erdaş ÇB (2019) A deep LSTM approach for activity recognition. In: IEEE 42nd ınternational conference on telecommunications and signal processing (TSP), Budapest

  12. 12.

    Eyobu OS, Han D (2018) Feature representation and data augmentation for human activity classification based on wearable IMU sensor data using a deep LSTM neural network. Sensors 18(9):28–92

    Google Scholar 

  13. 13.

    Zebin T, Scully PJ, Ozanyan KB (2016) Human activity recognition with inertial sensors using deep learning approach. In: 2016 IEEE SENSORS

  14. 14.

    Ordóñez F, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1):115

    Article  Google Scholar 

  15. 15.

    Hassan MM, Uddin MdZ, Mohamed A, Almogren A (2018) A robust human activity recognition system using smartphone sensors and deep learning. Future GenerComputSyst 81:307–313

    Google Scholar 

  16. 16.

    Rafegas M, Vanrell LA, Alexandre GA (2019) Understanding trained CNNs by indexing neuron selectivity. Pattern Recognit Lett 136:318–325

    Article  Google Scholar 

  17. 17.

    Konstantinidis D, Argyriou V, Stathaki T, Grammalidis N (2020) A modular CNN-based building detector for remote sensing images. ComputNetw 168:107034

    Google Scholar 

  18. 18.

    Shi X, Chen Z, Wang H, Yeung D-Y, Wong W, Woo W-C (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: NIPS'15: proceedings of the 28th ınternational conference on neural ınformation processing systems, vol 1, pp 802–810

  19. 19.

    Yuan Z, Zhou X, Yang T (2018) Hetero-ConvLSTM: a deep learning approach to traffic accident prediction on heterogeneous spatiotemporal data. In: Proceedings of the 24th ACM SIGKDD ınternational conference on knowledge discovery & data mining, pp 984–992

  20. 20.

    Casale P, Pujol O, Radeva P (2011) Activity recognition from accelerometer data using wearable device. Pers Ubiquitous Comput 289–296

  21. 21.

    Basnet J, Alsadoon A, Prasad PWC et al (2020) A novel solution of using deep learning for white blood cells classification: enhanced loss function with regularization and weighted loss (ELFRWL). Neural Process Lett 52:1517–1553.

    Article  Google Scholar 

  22. 22.

    Anami BS, Bhandage VA (2019) A comparative study of suitability of certain features in classification of Bharatanatyam mudra images using artificial neural network. Neural Process Lett 50:741–769.

    Article  Google Scholar 

  23. 23.

    Sánchez-Monedero J, Gutiérrez PA, Fernández-Navarro F et al (2011) Weighting efficient accuracy and minimum sensitivity for evolving multi-class classifiers. Neural Process Lett 34:101.

    Article  Google Scholar 

  24. 24.

    Thurnhofer-Hemsi K, Domínguez E (2020) A convolutional neural network framework for accurate skin cancer detection. Neural Process Lett.

    Article  Google Scholar 

  25. 25.

    Tran DP, Hoang VD (2019) Adaptive learning based on tracking and reidentifying objects using convolutional neural network. Neural Process Lett 50:263–282.

    Article  Google Scholar 

  26. 26.

    Zhang W, Yan Z, Xiao G et al (2019) Learning distance metric for support vector machine: a multiple kernel learning approach. Neural Process Lett 50:2899–2923.

    Article  Google Scholar 

  27. 27.

    Guo S, Zhang X, Yang X et al (2020) Developer activity motivated bug triaging: via convolutional neural network. Neural Process Lett 51:2589–2606.

    Article  Google Scholar 

  28. 28.

    Seliya N, Khoshgoftaar TM, Van Hulse J (2009) A study on the relationships of classifier performance metrics. In: 2009 21st IEEE ınternational conference on tools with artificial ıntelligence, Newark, NJ, pp 59–66.

  29. 29.

    Jones GP, Hickey MJ, Di Stefano PG et al (2020) Metrics and methods for a systematic comparison of fairness-aware machine learning algorithms. arXiv preprint arXiv:2010.03986

  30. 30.

    Pham BT, Jaafari A, Avand M, Al-Ansari N, Du Dinh T, Yen HPH, Phong TV, Nguyen DH, Le HV, Mafi-Gholami D, Prakash I, ThiThuy H, Tuyen TT (2020) Performance evaluation of machine learning methods for forest fire modeling and prediction. Symmetry 12:1022

    Article  Google Scholar 

  31. 31.

    Mattson P et al (2020) MLPerf: an ındustry standard benchmark suite for machine learning performance. In: IEEE Micro, vol 40, no 2, pp 8–16, 1 March–April.

  32. 32.

    Tan HX, Aung NN, Tian J, Chua MCH, Yang YO (2019) Time series classification using a modified LSTM approach from accelerometer-based data: a comparative study for gait cycle detection. Gait Posture 74:128–134

    Article  Google Scholar 

  33. 33.

    Powers DMW (2011) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. Int J Mach Learn Technol 2(1):37–63

    MathSciNet  Article  Google Scholar 

  34. 34.

    Tatbul N, Lee TJ, Zdonik S, Alam M, Gottschlich J (2018) Precision and recall for time series. Adv Neural Inf Process Syst 31:1920–1930

    Google Scholar 

  35. 35.

    Hwang W-S, Yun J-H, Kim J, Kim HC (2019) Time-series aware precision and recall for anomaly detection: considering variety of detection result and addressing ambiguous labeling. In: Proceedings of the 28th ACM ınternational conference on ınformation and knowledge management (CIKM’19). Association for Computing Machinery, pp 2241–2244

  36. 36.

    Li D, Chen D, Jin B, Shi L, Goh J, Ng SK (2019) MAD-GAN: multivariate anomaly detection for time series data with generative adversarial networks. In: Tetko I, Kůrková V, Karpov P, Theis F (eds) Artificial neural networks and machine learning—ICANN 2019: text and time series. ICANN 2019. Lecture Notes in Computer Science, vol 11730. Springer, Cham

  37. 37.

    Zhang C, Song D, Chen Y, Feng X, Lumezanu C, Cheng W, Ni J, Zong B, Chen H, Chawla NV (2019) A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data. Proc AAAI ConfArtifIntell 33(01):1409–1416

    Article  Google Scholar 

  38. 38.

    Ramirez A, Iriarte J (2019) Event recognition on time series frac data using machine learning. Society of Petroleum Engineers

  39. 39.

    Mboga N, Georganos S, Grippa T, Lennert M, Vanhuysse S, Wolff E (2019) Fully convolutional networks and geographic object-based image analysis for the classification of VHR imagery. Remote Sens 11:597

    Article  Google Scholar 

  40. 40.

    Khan AH, Cao X, Li S, Katsikis VN, Liao L (2020) BAS-ADAM: an ADAM based approach to improve the performance of beetle antennae search optimizer. IEEE/CAA J Autom Sin 7(2):461–471.

    Article  Google Scholar 

  41. 41.

    Li Z, Li S (2020) Saturated PI control for nonlinear system with provable convergence: an optimization perspective. In: IEEE transactions on circuits and systems II: express briefs.

  42. 42.

    Khan AH, Cao X, Li S, Luo C (2020) Using social behavior of beetles to establish a computational model for operational management. IEEE Trans ComputSocSyst 7(2):492–502.

    Article  Google Scholar 

  43. 43.

    Khan AH, Li S, Luo X (2020) Obstacle avoidance and tracking control of redundant robotic manipulator: an RNN-based metaheuristic approach. IEEE Trans IndInf 16(7):4670–4680.

    Article  Google Scholar 

  44. 44.

    Li Z, Zuo W, Li S (2020) Zeroing dynamics method for motion control of industrial upper-limb exoskeleton system with minimal potential energy modulation. Measurement 163:107964, ISSN 0263-2241.

  45. 45.

    Li Z, Li C, Li S, Cao X (2020) A fault-tolerant method for motion planning of industrial redundant manipulator. IEEE Trans IndInf 16(12):7469–7478.

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Çağatay Berke Erdaş.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Erdaş, Ç.B., Güney, S. Human Activity Recognition by Using Different Deep Learning Approaches for Wearable Sensors. Neural Process Lett (2021).

Download citation


  • Wearable sensors
  • Human activity recognition
  • Deep learning
  • CNN
  • Convolutional LSTM