This paper describes the development of a human gait activity recognition system. A multi-sensor recognition system, which has been developed for this purpose, was reduced to a single sensor-based recognition system. A sensor election method was devised based on the maximum relevance minimum redundancy feature selector to determine the sensor’s optimum position regarding activity recognition. The election method proved that the thigh has the highest contribution to recognize walking, stairs and ramp ascending, and descending activities. A recognition algorithm (which depends mainly on features that are classified by random forest, and selected by a combined feature selector using the maximum relevance minimum redundancy and genetic algorithm) has been modified to compensate the degradation that occurs in the prediction accuracy due to the reduction in the number of sensors. The first modification was implementing a double layer classifier in order to discriminate between the interfered activities. The second modification was adding physical features to the features dictionary used. These modifications succeeded to improve the prediction accuracy to allow a single sensor recognition system to behave in the same manner as a multi-sensor activity recognition system.
CherellePGrosuVMatthysA, et al. Design and validation of the ankle mimicking prosthetic (AMP-) foot 2.0. IEEE Trans Neural Syst Rehabil Eng2013; 22(1): 138–148.
2.
DabiriYNajarianSEslamiMR, et al. A powered prosthetic knee joint inspired from musculoskeletal system. Biocybern Biomed Eng2013; 33(2): 118–124.
3.
IgnatovA. Real-time human activity recognition from accelerometer data using convolutional neural networks. Appl Soft Comput2018; 62: 915–922.
4.
JainAKanhangadV. Human activity classification in smartphones using accelerometer and gyroscope sensors. IEEE Sens J2018; 18: 1169–1177.
5.
WagenaarRCRCSapirIZhangY. Continuous monitoring of functional activities using wearable, wireless gyroscope and accelerometer technology. In: 33rd Annual international conference of the IEEE EMBS, Tokyo, Japan, 30 August–3 September 2011, pp.4844–4847.
6.
ShahMShihabHMasnadM, et al. Human activity recognition using smartphone sensors with context filtering. In: The 9th international conference on advances in computer-human interactions, Venice, Italy, 24–28 April 2016, pp.67–73.
7.
LiHDerrodeSPieczynskiW. Lower limb locomotion activity recognition of healthy individuals using Semi-Markov model and single wearable inertial sensor. Sensors2019; 19(19): 4242.
8.
ColeyBNajafiBParaschivIonescuA, et al. Stair climbing detection during daily physical activity using a miniature gyroscope. Gait Posture2005; 22: 287–294.
9.
OlsonJSRedkarS. A survey of wearable sensor networks in health and entertainment. MOJ Appl Bionics Biomech2018; 2(5): 280–287.
10.
DopplerJHollGFerschaA. Variability in foot-worn sensor placement for activity recognition. In: International symposium on wearable computers, Linz, Austria, 4–7 September 2009.
11.
OrhaIOnigaS. Study regarding the optimal sensors placement on the body for human activity recognition. In: 20th International symposium for design and technology in electronic package (SITME), Bucharest, Romania, 23–26 October 2014.
12.
TwomeyNDietheTFafoutisX, et al. A comprehensive study of activity recognition using accelerometers. Informatics2018; 5: 27–27.
13.
GigginsOMSweeneyKTCaulfieldB. Rehabilitation exercise assessment using inertial sensors: a cross-sectional analytical study. J Neuroeng Rehabil2014; 11(158): 158.
14.
WhelanDFO’ReillyMAWardTE, et al. Technology in rehabilitation: evaluating the single leg squat exercise with wearable inertial measurement units. Methods Inf Med2017; 56(2): 88–94.
15.
DingC. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell2005; 27: 1226–1238.
16.
BoutenCVKoekkoekKTVerduinM, et al. A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity. IEEE Trans Biomed Eng1997; 44(3): 136–147.
17.
MohamedHAwadMMagdyM. Lower limb motion tracking using IMU sensor. In: 7th Cairo international biomedical engineering conference, Giza, Egypt, 11–13December2014, pp.28–33.
18.
LucianC. Applying Kalman filtering on a quadruped. Thesis, Ecole Polytechnique Federale Ce Lausanne, Switzerland, 2012.
19.
HamdiMMAwadMIAbdelhameedMM, et al. Lower limb gait activity recognition using inertial measurement. In: International Conference on Advanced Robotics (ICAR), Istanbul, Turkey, 27–31 July 2015, pp.316–322.
20.
LeeMHKimJKimK. Physical activity recognition using a single tri-axial accelerometer. In: Proceedings of the world congress on engineering and computer science, San Francisco, CA, 20–22 October 2009.
21.
StikicMHuynhTVan LaerhoveK. ADL recognition based on the combination of RFID and accelerometer sensing. In: 2nd International conference on pervasive computing technologies for healthcare, Tampere, Finland, 30 January–1 February 2008, pp.258–263.
22.
GhasemzadehHLoseuVGuentE. Sport training using body sensor networks: a statistical approach to measure wrist rotation for golf swing. In: 4th International conference on body area networks, Los Angeles, CA, USA, 9 April 2009.
23.
YangJYWangJSChenYP. Using acceleration measurements for activity recognition: an effective learning algorithm for constructing neural classifiers. Pattern Recognit Lett2008; 29: 2213–2220.
24.
MaurerUSimailagieA. Activity recognition and monitoring using multiple sensors on different body positions. In: International workshop on wearable and implantable body sensor network, Cambridge, MA, 3–5 April 2006.
25.
LombriserCBharatulaNBRoggenD. On-body activity recognition in a dynamic sensor network. In: 2nd International conference on body area network, body nets, Brussels, Belgium, 11–13 June 2007.
26.
ShiaokaiWWilliamPPopeA-M. Common sense based joint training of human activity recognizers. In: 20th International joint conference on artificial intelligence, Hyderabad, India, 6–12 January 2007.
27.
ShenWDengKXiangB. Exemplar-based human action pose correction and tagging. In: IEEE conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, 16–21 June 2012.
28.
LiangDJian-KangWU. Tracking of thigh flexion angle during gait cycles in an ambulatory activity monitoring sensor network. Zidonghua Xuebao2006; 32(6): 938–946.
29.
SiggYJ. Activity recognition from radio frequency data: multi-stage recognition and features. In: IEEE vehicular technology conference, Quebec City, QC, Canada, 3–6 September 2012.
30.
FishBChehadeNChiehC. Feature selection based on mutual information for human activity recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, 25–30 March 2012, pp.1729–1732.
31.
MuhammedSScholtenHHavingaPJ. Towards physical activity recognition using smartphone sensors. In: IEEE 10th international conference on ubiquitous intelligence & computing, Vietri sul Mare, Italy, 18–21 December 2013, pp.80–87.
32.
HowcroftJKofmanJLemaireED. Feature selection for elderly faller classification based on wearable sensors. J Neuroeng Rehabil2017; 14: 47.
33.
ZhangYPanGJiaK, et al. Accelerometer-based gait recognition by sparse representation of signature points with clusters. IEEE Trans Cybern2015; 45(9): 1864–1875.
34.
MartindaleCFHoenigFStrohrmannC, et al. Smart annotation of cyclic data using hierarchical hidden Markov models. Sensors2017; 17(10): 2328.
35.
MartindaleCFSpragerSEskofierBM. Hidden Markov model-based smart annotation for benchmark cyclic activity recognition database using wearables. Sensors2019; 19: 1–21.
36.
BevilacquaAMacDonaldKRangareA. Human activity recognition with convolutional neural networks. In: Joint European conference on machine learning and knowledge discovery in databases, Dublin, Ireland, September, 2018, pp.541–552.
37.
AbhayasingheNMurrayI. Human activity recognition using thigh angle derived from single thigh mounted IMU data. In: International conference on indoor positioning and indoor navigation, Busan, Korea, 27–30 October 2014, pp.111–115.
