Hybrid Deep Learning Models Using LSTM with Random Forest for Radio Frequency-Based Human Activity Recognition in Line-of-Sight and Non-Line-of-Sight Environments

Niko Andriano, Feddy Setio Pribadi

Abstract


Human Activity Recognition (HAR) has become an important field of study because of its wide range of applications in healthcare, security, and smart living systems. Radio Frequency (RF)-based HAR offers a non-invasive and privacy-preserving alternative to traditional vision-based systems. This study proposes a hybrid deep learning model combining Long Short-Term Memory (LSTM) networks with Random Forest classifiers for RF-based HAR, aiming to improve recognition accuracy across diverse environments. The model was evaluated using Channel State Information (CSI) and Received Signal Strength Indicator (RSSI) features under Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) conditions. Synthetic Minority Over-sampling Technique (SMOTE) was integrated to balance the dataset, and K-fold Cross-Validation was employed to assess robustness. The dataset included data from 8 subjects performing 10 different activities. The model achieved high classification accuracy, with 99.40% in Environment 1 (LOS), 97.58% in Environment 2 (LOS), and 98.30% in Environment 3 (NLOS), demonstrating the model’s adaptability and effectiveness. The results highlight the potential of the hybrid LSTM with Random Forest approach for scalable and reliable RF-based HAR systems that can be integrated into real-world Internet of Things (IoT) applications.

Keywords


human activity recognition; radio frequency-based; hybrid deep learning; long short-term memory; random forest

Full Text:

PDF

References


L. Bibbò and M. M. B. R. Vellasco, “Human Activity Recognition (HAR) in Healthcare,” Dec. 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/app132413009.

S. Sakka, V. Liagkou, and C. Stylios, “Exploiting Security Issues in Human Activity Recognition Systems (HARSs),” Information (Switzerland), vol. 14, no. 6, 2023, doi: 10.3390/info14060315.

G. Diraco, G. Rescio, A. Caroppo, A. Manni, and A. Leone, “Human Action Recognition in Smart Living Services and Applications: Context Awareness, Data Availability, Personalization, and Privacy,” 2023. doi: 10.3390/s23136040.

M. Karim, S. Khalid, A. Aleryani, J. Khan, I. Ullah, and Z. Ali, “Human Action Recognition Systems: A Review of the Trends and State-of-the-Art,” IEEE Access, vol. 12, pp. 36372–36390, 2024, doi: 10.1109/ACCESS.2024.3373199.

J. Liu, L. Wang, L. Guo, J. Fang, B. Lu, and W. Zhou, “A research on CSI-based human motion detection in complex scenarios,” in 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom 2017, Institute of Electrical and Electronics Engineers Inc., Dec. 2017, pp. 1–6. doi: 10.1109/HealthCom.2017.8210800.

M. G. Moghaddam, A. A. N. Shirehjini, and S. Shirmohammadi, “A WiFi-Based Method for Recognizing Fine-Grained Multiple-Subject Human Activities,” IEEE Trans Instrum Meas, vol. 72, 2023, doi: 10.1109/TIM.2023.3289547.

M. Waqas et al., “Advanced Line-of-Sight (LOS) model for communicating devices in modern indoor environment,” PLoS One, vol. 19, Jul. 2024, doi: 10.1371/journal.pone.0305039.

J. S. Choi, W. H. Lee, J. H. Lee, J. H. Lee, and S. C. Kim, “Deep Learning Based NLOS Identification with Commodity WLAN Devices,” IEEE Trans Veh Technol, vol. 67, pp. 3295–3303, Apr. 2018, doi: 10.1109/TVT.2017.2780121.

C. Huang et al., “Machine Learning-Enabled LOS/NLOS Identification for MIMO Systems in Dynamic Environments,” IEEE Trans Wirel Commun, vol. 19, pp. 3643–3657, Jun. 2020, doi: 10.1109/TWC.2020.2967726.

M. S. Islam, M. K. A. Jannat, M. N. Hossain, W. S. Kim, S. W. Lee, and S. H. Yang, “STC-NLSTMNet: An Improved Human Activity Recognition Method Using Convolutional Neural Network with NLSTM from WiFi CSI,” Sensors, vol. 23, no. 1, Jan. 2023, doi: 10.3390/s23010356.

M. Z. Khan et al., “Contactless Human Activity Recognition using Deep Learning with Flexible and Scalable Software Define Radio,” in 2023 International Wireless Communications and Mobile Computing, IWCMC 2023, 2023. doi: 10.1109/IWCMC58020.2023.10182652.

I. Ahmad, A. Ullah, and W. Choi, “WiFi-Based Human Sensing with Deep Learning: Recent Advances, Challenges, and Opportunities,” IEEE Open Journal of the Communications Society, vol. 5, pp. 3595–3623, 2024, doi: 10.1109/OJCOMS.2024.3411529.

M. M. U. Khan, A. Bin Shams, and M. S. Raihan, “A prospective approach for human-to-human interaction recognition from Wi-Fi channel data using attention bidirectional gated recurrent neural network with GUI application implementation,” Multimed Tools Appl, vol. 83, pp. 62379–62422, Jul. 2024, doi: 10.1007/s11042-023-17487-z.

S. M. Bokhari, S. Sohaib, A. R. Khan, M. Shafi, and A. ur R. Khan, “DGRU based human activity recognition using channel state information,” Measurement (Lond), vol. 167, 2021, doi: 10.1016/j.measurement.2020.108245.

M. Mohtadifar, M. Cheffena, and A. Pourafzal, “Acoustic-and Radio-Frequency-Based Human Activity Recognition,” Sensors, vol. 22, no. 9, May 2022, doi: 10.3390/s22093125.

J. Strohmayer and M. Kampel, “Directional Antenna Systems for Long-Range Through-Wall Human Activity Recognition,” Jan. 2024, doi: 10.1109/ICIP51287.2024.10647666.

X. Huang and M. Dai, “Indoor Device-Free Activity Recognition Based on Radio Signal,” IEEE Trans Veh Technol, vol. 66, no. 6, pp. 5316–5329, Jun. 2017, doi: 10.1109/TVT.2016.2616883.

Z. Chen, C. Cai, T. Zheng, J. Luo, J. Xiong, and X. Wang, “RF-Based Human Activity Recognition Using Signal Adapted Convolutional Neural Network,” IEEE Trans Mob Comput, vol. 22, no. 1, pp. 487–499, Jan. 2021, doi: 10.1109/TMC.2021.3073969.

A. Gaikwad, “A Comparative Study of Machine Learning Techniques for Human Activity Recognition,” Journal of Informatics Education and Research, 2024, doi: 10.52783/jier.v4i2.935.

H. A. N. Huimei, Z. H. U. Xingquan, and L. I. Ying, “Generalizing long short-term memory network for deep learning from generic data,” ACM Trans Knowl Discov Data, vol. 14, no. 2, 2020, doi: 10.1145/3366022.

A. Sharma, K. Singh, and R. Bisht, “Human Activity Recognition Using CNN-LSTM,” Computer Science, Engineering and Technology, vol. 2, pp. 31–35, Sep. 2024, doi: 10.46632/cset/2/3/4.

Y. A. Khan, S. Imaduddin, Y. P. Singh, M. Wajid, M. Usman, and M. Abbas, “Artificial Intelligence Based Approach for Classification of Human Activities Using MEMS Sensors Data,” Sensors, vol. 23, Feb. 2023, doi: 10.3390/s23031275.

V. Ghate and C. Sweetlin Hemalatha, “Hybrid deep learning approaches for smartphone sensor-based human activity recognition,” Multimed Tools Appl, vol. 80, pp. 35585–35604, Nov. 2021, doi: 10.1007/s11042-020-10478-4.

Z. Y. Lim, L. Y. Ong, and M. C. Leow, “Radio frequency-based human activity dataset collected using ESP32 microcontroller in line-of-sight and non-line-of-sight indoor experiment setups,” Data Brief, vol. 57, Dec. 2024, doi: 10.1016/j.dib.2024.111101.




DOI: https://doi.org/https://doi.org/10.17529/jre.v21i2.44828

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


View My Stats

 

Creative Commons License

Jurnal Rekayasa Elektrika (JRE) is published under license of Creative Commons Attribution-ShareAlike 4.0 International License.