(Middle Technical University, ICT Department, Iraq)(2) Laith AL-Frady
(IT Department, Technical College of Management, Middle Technical University, Baghdad, Iraq)(3) Ruaa Ali Khamees
(ICT Department
Middle Technical University
Baghdad, Iraq)*corresponding author
AbstractIn this paper, we developed an effective wrapper-based model to optimize the recognition of physical human daily life activities recorded by smartphone built-in sensors. The proposed model employs Sequential Forward Selection (SFS) method in combination with K-Nearest Neighbor (KNN) classifier based on a group of five commonly used distance measures: (Manhattan, Euclidean, Chebyshev, Canberra, and Correlation) each having a specific geometric neighborhood interpretation. The proposed SFS-KNN multi-distance approach enables each distance metric to guide the feature selection process. It examines how the resulting feature subsets, determined by each distance, impact the overall recognition performance. The goal is to identify the best feature subset that achieves the highest accuracy with the lowest dimensionality. . Our proposed distance-based wrapper model was validated on two publicly available WISDM and UCI-HAR datasets under 10-fold cross-validation. The experimental results obtained on both datasets showed that the performance of the proposed model is significantly affected by the distance measure used due to generating different feature subsets for each distance. For the WISDM dataset, our model achieves an overall accuracy of 93.39% based on Euclidean distance, with a reduction ratio of 71.42%. It also offers a substantial reduction of 95.9% in the feature dimensions of the UCI-HAR dataset using Correlation distance, with a recognition rate of 99.33%. These outcomes confirm the superiority of our wrapper model over other feature selection-based approaches proposed for the same datasets.
KeywordsHuman activity recognition; Smartphone inertial sensors; Feature selection; Classification
|
DOIhttps://doi.org/10.26555/ijain.v12i2.2363 |
Article metricsAbstract views : 454 | PDF views : 1 |
Cite |
Full Text Download
|
References
[1] 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,” Sensors, vol. 23, no. 13, p. 6040, Jun. 2023, doi: 10.3390/s23136040.
[2] D.-Q. Vu, T. P. Thi Thu, N. Le, and J.-C. Wang, “Deep Learning for Human Action Recognition: A Comprehensive Review,” APSIPA Trans. Signal Inf. Process., vol. 12, no. 2, pp. 1–40, Apr. 2022, doi: 10.1561/116.00000068.
[3] H. Haresamudram, I. Essa, and T. Plötz, “Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition,” Sensors, vol. 24, no. 4, p. 1238, Feb. 2024, doi: 10.3390/s24041238.
[4] L. Boborzi, J. Decker, R. Rezaei, R. Schniepp, and M. Wuehr, “Human Activity Recognition in a Free-Living Environment Using an Ear-Worn Motion Sensor,” Sensors, vol. 24, no. 9, p. 2665, Apr. 2024, doi: 10.3390/s24092665.
[5] V. Mahalakshmi, P. Kumar, M. Bhende, I. Keshta, S. Y. Rathod, and J. V. N. Ramesh, “IOT based wearable sensor system architecture for classifying human activity,” Meas. Sensors, vol. 39, no. June, p. 101871, Jun. 2025, doi: 10.1016/j.measen.2025.101871.
[6] S. Javadi, D. Riboni, L. Borzì, and S. Zolfaghari, “Graph-Based Methods for Multimodal Indoor Activity Recognition: A Comprehensive Survey,” IEEE Trans. Comput. Soc. Syst., vol. 12, no. 5, pp. 3728–3746, Oct. 2025, doi: 10.1109/TCSS.2024.3523240.
[7] K. Takenaka, K. Kondo, and T. Hasegawa, “Segment-Based Unsupervised Learning Method in Sensor-Based Human Activity Recognition,” Sensors, vol. 23, no. 20, p. 8449, Oct. 2023, doi: 10.3390/s23208449.
[8] A. Roy, H. Dutta, A. K. Bhuyan, and S. Biswas, “On-Device Semi-Supervised Activity Detection: A New Privacy-Aware Personalized Health Monitoring Approach,” Sensors, vol. 24, no. 14, p. 4444, Jul. 2024, doi: 10.3390/s24144444.
[9] M. Koch, T. Pfitzinger, F. Schlenke, F. Kohlmorgen, R. Groll, and H. Wöhrle, “Recognition of Human Activities Based on Ambient Audio and Vibration Data,” IEEE Access, vol. 12, pp. 174399–174412, 2024, doi: 10.1109/ACCESS.2024.3457912.
[10] A. Grenier et al., “Evaluation of Sensors Measurements in Consumer-Grade Android Wearables for Robust Positioning Applications,” in Proceedings of the International Technical Meeting of the Satellite Division of The Institute of Navigation, ION GNSS+, Institute of Navigation, Oct. 2024, pp. 1094–1108. doi: 10.33012/2024.19675.
[11] N. A. Almujally et al., “Biosensor-Driven IoT Wearables for Accurate Body Motion Tracking and Localization,” Sensors, vol. 24, no. 10, p. 3032, May 2024, doi: 10.3390/s24103032.
[12] Y. Yin, L. Xie, Z. Jiang, F. Xiao, J. Cao, and S. Lu, “A Systematic Review of Human Activity Recognition Based on Mobile Devices: Overview, Progress and Trends,” IEEE Commun. Surv. Tutorials, vol. 26, no. 2, pp. 890–929, 2024, doi: 10.1109/COMST.2024.3357591.
[13] V. Dentamaro, V. Gattulli, D. Impedovo, and F. Manca, “Human activity recognition with smartphone-integrated sensors: A survey,” Expert Syst. Appl., vol. 246, no. July, p. 123143, Jul. 2024, doi: 10.1016/j.eswa.2024.123143.
[14] X. Wang, Y. Wang, and J. Wu, “Position-Aware Indoor Human Activity Recognition Using Multisensors Embedded in Smartphones,” Sensors, vol. 24, no. 11, p. 3367, May 2024, doi: 10.3390/s24113367.
[15] H. Jamil, M. A. Khan, and F. Jamil, “A novel hybrid strategy based on Swarm and Heterogeneous Federated Learning using model credibility awareness for activity recognition in cross-silo multistorey building,” Eng. Appl. Artif. Intell., vol. 138, no. December, p. 109126, Dec. 2024, doi: 10.1016/j.engappai.2024.109126.
[16] J. R. Kwapisz, G. M. Weiss, and S. A. Moore, “Activity recognition using cell phone accelerometers,” ACM SIGKDD Explor. Newsl., vol. 12, no. 2, pp. 74–82, Mar. 2011, doi: 10.1145/1964897.1964918.
[17] D. Anguita, A. Ghio, L. Oneto, X. Parra, and J. L. Reyes-Ortiz, “A Public Domain Dataset for Human Activity Recognition using Smartphones,” Eur. Symp. Artif. Neural Networks, pp. 437–442, 2013, Accessed: Aug. 05, 2026. [Online]. Available: https://www.esann.org/sites/default/files/proceedings/legacy/es2013-84.pdf.
[18] A. Logacjov, K. Bach, A. Kongsvold, H. B. Bårdstu, and P. J. Mork, “HARTH: A Human Activity Recognition Dataset for Machine Learning,” Sensors, vol. 21, no. 23, p. 7853, Nov. 2021, doi: 10.3390/s21237853.
[19] W. Gomaa and M. A. Khamis, “A perspective on human activity recognition from inertial motion data,” Neural Comput. Appl., vol. 35, no. 28, pp. 20463–20568, Oct. 2023, doi: 10.1007/s00521-023-08863-9.
[20] N. sedaghati, S. Ardebili, and A. Ghaffari, “Application of human activity/action recognition: a review,” Multimed. Tools Appl., vol. 84, no. 28, pp. 33475–33504, Jan. 2025, doi: 10.1007/s11042-024-20576-2.
[21] E. Zaitseva, V. Levashenko, S. Stankevich, and A. Bekenova, “Importance Analysis Method Application for Feature Selection in a Classification,” in 2023 7th International Conference on System Reliability and Safety (ICSRS), IEEE, Nov. 2023, pp. 144–148. doi: 10.1109/ICSRS59833.2023.10381366.
[22] W. Zhang, G. Yu, and S. Deng, “Research on TCN Model Based on SSARF Feature Selection in the Field of Human Behavior Recognition,” IET Biometrics, vol. 2024, no. 1, p. 4982277, Jan. 2024, doi: 10.1049/2024/4982277.
[23] L. Al-Frady and A. Al-Taei, “Wrapper Filter Approach for Accelerometer-Based Human Activity Recognition,” Pattern Recognit. Image Anal., vol. 30, no. 4, pp. 757–764, Oct. 2020, doi: 10.1134/S1054661820040033.
[24] A. M. Helmi, M. A. A. Al-qaness, A. Dahou, R. Damaševičius, T. Krilavičius, and M. A. Elaziz, “A Novel Hybrid Gradient-Based Optimizer and Grey Wolf Optimizer Feature Selection Method for Human Activity Recognition Using Smartphone Sensors,” Entropy, vol. 23, no. 8, p. 1065, Aug. 2021, doi: 10.3390/e23081065.
[25] M. A. A. Al-qaness, A. M. Helmi, A. Dahou, and M. A. Elaziz, “The Applications of Metaheuristics for Human Activity Recognition and Fall Detection Using Wearable Sensors: A Comprehensive Analysis,” Biosensors, vol. 12, no. 10, p. 821, Oct. 2022, doi: 10.3390/bios12100821.
[26] A. Al-Taei, M. F. Ibrahim, and N. J. Habeeb, “Optimizing the Performance of KNN Classifier for Human Activity Recognition,” in Communications in Computer and Information Science, vol. 1440 CCIS, Springer Science and Business Media Deutschland GmbH, 2021, pp. 373–385. doi: 10.1007/978-3-030-81462-5_34.
[27] D. Thakur and S. Biswas, “Guided regularized random forest feature selection for smartphone based human activity recognition,” J. Ambient Intell. Humaniz. Comput., vol. 14, no. 7, pp. 9767–9779, Jul. 2023, doi: 10.1007/s12652-022-03862-5.
[28] P. Khatiwada, M. Subedi, A. Chatterjee, and M. Wulf Gerdes, “Automated Human Activity Recognition by Colliding Bodies Optimization-based Optimal Feature Selection with Recurrent Neural Network (RNN),” pre prints, vol. 1, pp. 1–17, Oct. 2020, doi: 10.20944/preprints202010.0367.v1.
[29] C. Fan and F. Gao, “Enhanced Human Activity Recognition Using Wearable Sensors via a Hybrid Feature Selection Method,” Sensors, vol. 21, no. 19, p. 6434, Sep. 2021, doi: 10.3390/s21196434.
[30] B. A. Mohammed Hashim and R. Amutha, “Human activity recognition based on smartphone using fast feature dimensionality reduction technique,” J. Ambient Intell. Humaniz. Comput., vol. 12, no. 2, pp. 2365–2374, Feb. 2021, doi: 10.1007/s12652-020-02351-x.
[31] R. Guha, A. H. Khan, P. K. Singh, R. Sarkar, and D. Bhattacharjee, “CGA: a new feature selection model for visual human action recognition,” Neural Comput. Appl., vol. 33, no. 10, pp. 5267–5286, May 2021, doi: 10.1007/s00521-020-05297-5.
[32] V. B. Semwal, P. Lalwani, M. K. Mishra, V. Bijalwan, and J. S. Chadha, “An optimized feature selection using bio-geography optimization technique for human walking activities recognition,” Computing, vol. 103, no. 12, pp. 2893–2914, Dec. 2021, doi: 10.1007/s00607-021-01008-7.
[33] WISDM Lab, “WISDM Activity Prediction Dataset.” [Online]. Available: https://www.cis.fordham.edu/wisdm/dataset.php.
[34] J. L. Reyes-Ortiz, D. Anguita, A. Ghio, L. Oneto, and X. Parra, “Human Activity Recognition Using Smartphones.” [Online]. Available: https://archive.ics.uci.edu/dataset/240/human+activity+recognition+using+smartphones.
[35] B. de la Iglesia, “Evolutionary computation for feature selection in classification problems,” WIREs Data Min. Knowl. Discov., vol. 3, no. 6, pp. 381–407, Nov. 2013, doi: 10.1002/widm.1106.
[36] E. A. K. Zaman, A. Ahmad, and A. Mohamed, “Adaptive threshold optimisation for online feature selection using dynamic particle swarm optimisation in determining feature relevancy and redundancy,” Appl. Soft Comput., vol. 156, no. May, p. 111477, May 2024, doi: 10.1016/j.asoc.2024.111477.
[37] A. Hassan, J. H. Paik, S. R. Khare, and S. A. Hassan, “A wrapper feature selection approach using Markov blankets,” Pattern Recognit., vol. 158, no. February, p. 111069, Feb. 2025, doi: 10.1016/j.patcog.2024.111069.
[38] N. Kumar, A. Narang, and B. Lall, “KL Regularized Normalization Framework for Low Resource Tasks,” in Lecture Notes in Computer Science, vol. 14172 LNAI, Springer Science and Business Media Deutschland GmbH, 2023, pp. 71–89. doi: 10.1007/978-3-031-43421-1_5.
[39] S. Ramadhani et al., “Feature Selection Optimisation for Cancer Classification Based on Evolutionary Algorithms: An Extensive Review,” Comput. Model. Eng. Sci., vol. 143, no. 3, pp. 2711–2765, Jun. 2025, doi: 10.32604/cmes.2025.062709.
[40] F. Kamalov, H. Sulieman, A. Alzaatreh, M. Emarly, H. Chamlal, and M. Safaraliev, “Mathematical Methods in Feature Selection: A Review,” Mathematics, vol. 13, no. 6, p. 996, Mar. 2025, doi: 10.3390/math13060996.
[41] Q. D. Nam Nguyen, A.-B. Liu, and C.-W. Lin, “Development of a Neurodegenerative Disease Gait Classification Algorithm Using Multiscale Sample Entropy and Machine Learning Classifiers,” Entropy, vol. 22, no. 12, p. 1340, Nov. 2020, doi: 10.3390/e22121340.
[42] S. Shafiee, L. M. Lied, I. Burud, J. A. Dieseth, M. Alsheikh, and M. Lillemo, “Sequential forward selection and support vector regression in comparison to LASSO regression for spring wheat yield prediction based on UAV imagery,” Comput. Electron. Agric., vol. 183, no. April, p. 106036, Apr. 2021, doi: 10.1016/j.compag.2021.106036.
[43] J. Bemister-Buffington, A. J. Wolf, S. Raschka, and L. A. Kuhn, “Machine Learning to Identify Flexibility Signatures of Class A GPCR Inhibition,” Biomolecules, vol. 10, no. 3, p. 454, Mar. 2020, doi: 10.3390/biom10030454.
[44] R. K. Sachdeva, P. Bathla, P. Rani, R. Lamba, G. S. P. Ghantasala, and I. F. Nassar, “RETRACTED ARTICLE: A novel K-nearest neighbor classifier for lung cancer disease diagnosis,” Neural Comput. Appl., vol. 36, no. 35, pp. 22403–22416, Dec. 2024, doi: 10.1007/s00521-024-10235-w.
[45] B. Yuan, Y. Chen, Z. Tan, W. Jinyan, H. Liu, and Y. Zhang, “Label Distribution Learning-Enhanced Dual-KNN for Text Classification,” in Proceedings of the 2024 SIAM International Conference on Data Mining (SDM), Philadelphia, PA: Society for Industrial and Applied Mathematics, 2024, pp. 400–408. doi: 10.1137/1.9781611978032.47.
[46] M. Sabri et al., “A Novel Classification Algorithm Based on the Synergy Between Dynamic Clustering with Adaptive Distances and K-Nearest Neighbors,” J. Classif., vol. 41, no. 2, pp. 264–288, Jul. 2024, doi: 10.1007/s00357-024-09471-5.
[47] G. P. Kumar, K. Anbazhagan, and N. Ramasenderan, “Object classification based-on patterns using random forest classifier compared with enhanced K-nearest neighbor algorithm,” in AIP Conference Proceedings, American Institute of Physics, Aug. 2024, p. 020200. doi: 10.1063/5.0229218.
[48] M.-N. Wang, X.-J. Xie, Z.-H. You, L. Wong, L.-P. Li, and Z.-H. Chen, “Combining K Nearest Neighbor With Nonnegative Matrix Factorization for Predicting Circrna-Disease Associations,” IEEE/ACM Trans. Comput. Biol. Bioinforma., vol. 20, no. 5, pp. 2610–2618, Sep. 2023, doi: 10.1109/TCBB.2022.3180903.
[49] X. Wu et al., “Top 10 algorithms in data mining,” Knowl. Inf. Syst., vol. 14, no. 1, pp. 1–37, Jan. 2008, doi: 10.1007/s10115-007-0114-2.
[50] A. Cetin and A. Buyuklu, “Revisiting distance metrics in k-nearest neighbors algorithms: Implications for sovereign country credit rating assessments,” Therm. Sci., vol. 28, no. 2 Part C, pp. 1905–1915, 2024, doi: 10.2298/TSCI231111008C.
[51] B.-W. Yuan et al., “A novel density-based adaptive k nearest neighbor method for dealing with overlapping problem in imbalanced datasets,” Neural Comput. Appl., vol. 33, no. 9, pp. 4457–4481, May 2021, doi: 10.1007/s00521-020-05256-0.
[52] L. Gautheron, A. Habrard, E. Morvant, and M. Sebban, “Metric Learning from Imbalanced Data,” in 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), IEEE, Nov. 2019, pp. 923–930. doi: 10.1109/ICTAI.2019.00131.
[53] Z. Wang et al., “Exploring global information for session-based recommendation,” Pattern Recognit., vol. 145, no. January, p. 109911, Jan. 2024, doi: 10.1016/j.patcog.2023.109911.
[54] S. Sun and R. Huang, “An adaptive k-nearest neighbor algorithm,” in 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery, IEEE, Aug. 2010, pp. 91–94. doi: 10.1109/FSKD.2010.5569740.
[55] H. A. Abu Alfeilat et al., “Effects of Distance Measure Choice on K-Nearest Neighbor Classifier Performance: A Review,” Big Data, vol. 7, no. 4, pp. 221–248, Dec. 2019, doi: 10.1089/big.2018.0175.
[56] R. Todeschini, D. Ballabio, and V. Consonni, “Distances and Other Dissimilarity Measures in Chemometrics,” in Encyclopedia of Analytical Chemistry, Wiley, 2015, pp. 1–34. doi: 10.1002/9780470027318.a9438.
[57] M. Grandini, E. Bagli, and G. Visani, “Metrics for Multi-Class Classification: an Overview,” vol. 1, pp. 1–17, Aug. 2020, Accessed: Aug. 05, 2026. [Online]. Available: http://arxiv.org/abs/2008.05756.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0