New method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting falls
Article Sidebar
Main Article Content
Abstract
Fall is one of the most critical accidents resulting in serious injuries and significant financial losses among people in all ages. This paper presents the application of full factorial design (FFD) to investigate fall detection algorithms that have multiple hyperparameters which are very difficult to identify the best values for the dataset. In this study, the algorithm factors are investigated from two motion sensors and six artifact neural network (ANN) parameters on seven possible outcomes of signal detection theory (SDT). It is found that only one accelerometer and one gyroscope and small size ANN with scaled conjugate gradient (SCG) and radial basis function (RBF) provide a higher performance classification with lower computational complexity. Experimental outcomes show the new method using statistical theory for the selection of the most effective performance of fall detection algorithm parameters. Findings from the current study could be applied to various types of classification model problems in engineering applications, such as the design of products and systems.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
World Health Organization. Falls [Internet]. 2021 [updated 2021 Apr 26; cited 2022 Jan 18]. Available from: https://www.who.int/news-room/fact-sheets/detail/falls.
Tinetti ME, Williams CS. Falls, Injuries Due to Falls, and the Risk of Admission to a Nursing Home. N Engl J Med. 1997;337(18):1279-84.
Koch S. Healthy ageing supported by technology - a cross-disciplinary research challenge. Inform Health Soc Care. 2010;35(3-4):81-91.
Er PV, Tan KK. Non-intrusive fall detection monitoring for the elderly based on fuzzy logic. Measurement. 2018;124:91-102.
Pierleoni P, Belli A, Palma L, Pellegrini M, Pernini L, Valenti S. A High Reliability Wearable Device for Elderly Fall Detection. IEEE Sens J. 2015;15(8):4544-53.
Pannurat N, Thiemjarus S, Nantajeewarawat E. A Hybrid Temporal Reasoning Framework for Fall Monitoring. IEEE Sens J. 2017;17(6):1749-59.
Ganapathy K, Vaidehi V, Poorani D. Sensor based efficient decision making framework for remote healthcare. J Ambient Intell Smart Environ. 2015;7(4):461-81.
Aziz O, Musngi M, Park EJ, Mori G, Robinovitch SN. A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials. Med Biol Eng Comput. 2017;55(1):45-55.
Yuwono M, Moulton BD, Su SW, Celler BG, Nguyen HT. Unsupervised machine-learning method for improving the performance of ambulatory fall-detection systems. BioMed Eng OnLine. 2012;11:1-11.
Sorvala A, Alasaarela E, Sorvoja H, Myllylä R. A two-threshold fall detection algorithm for reducing false alarms. In: 6th International Symposium on Medical Information and Communication Technology (ISMICT); 2012 Mar 25-29; La Jolla, USA. USA: IEEE; 2012. p. 1-4.
Abbate S, Avvenuti M, Corsini P, Light J, Vecchio A. Monitoring of human movements for fall detection and activities recognition in elderly care using wireless sensor network: a survey. In: Merrett GV, Tan YK, editors. Wireless Sensor Networks: Application-Centric Design. Shanghai: InTech; 2010. p. 1-20.
Zhang G, Patuwo BE, Hu MY. Forecasting with artificial neural networks:: The state of the art. Int J Forecast. 1998;14(1):35-62.
Balestrassi PP, Popova E, Paiva AP, Marangon Lima JW. Design of experiments on neural network’s training for nonlinear time series forecasting. Neurocomputing. 2009;72(4-6):1160-78.
Mahdi SQ, Gharghan SK, Hasan MA. FPGA-Based neural network for accurate distance estimation of elderly falls using WSN in an indoor environment. Measurement. 2021;167:108276.
Wickens TD. Elementary signal detection theory. New York: Oxford University Press; 2002.
Proctor RW, Van Zandt T. Human factors in simple and complex systems. Boston: Allyn & Bacon; 1993.
Lin PH, Chen CH. Evaluating autostereoscopic 3D baseball games using signal detection theory and receiver operating characteristic space. Int J Ind Ergon. 2019;72:390-7.
Montgomery DC. Design and analysis of experiments. 9th ed. New Jersey: John Wiley & Sons; 2017.
Pontes FJ, Amorim GF, Balestrassi PP, Paiva AP, Ferreira JR. Design of experiments and focused grid search for neural network parameter optimization. Neurocomputing. 2016;186:22-34.
Gökler SH, Boran S. Prediction of demand for red blood cells using ridge regression, artificial neural network, and integrated taguchi-artificial neural network approach. Int J Ind Eng: Theory Appl Pract. 2022;29(1):64-77.
Lujan-Moreno GA, Howard PR, Rojas OG, Montgomery DC. Design of experiments and response surface methodology to tune machine learning hyperparameters, with a random forest case-study. Expert Syst Appl. 2018;109:195-205.
Moreira MO, Balestrassi PP, Paiva AP, Ribeiro PF, Bonatto BD. Design of experiments using artificial neural network ensemble for photovoltaic generation forecasting. Renewable Sustainable Energy Rev. 2021;135:110450.
Santos MS, Ludermir TB. Using factorial design to optimize neural networks. International Conference on Neural Networks; 1999 Jul 10-16; Washington, USA. USA: IEEE; 1999. p. 857-61.
Nukala BT, Shibuya N, Rodriguez A, Tsay J, Lopez J, Nguyen T, et al. An efficient and robust fall detection system using wireless gait analysis sensor with artificial neural network (ANN) and support vector machine (SVM) algorithms. Open J. Appl. Biosens. 2014;3(4):29-39.
Wang HK, Wang ZH, Wang MC. Using the Taguchi method for optimization of the powder metallurgy forming process for Industry 3.5. Comput Ind Eng. 2020;148:106635.
Kaur P, Wang Q, Shi W. Fall detection from audios with Audio Transformers. Smart Health. 2022;26:100340.
Xu T, Se H, Liu J. A fusion fall detection algorithm combining threshold-based method and convolutional neural network. Microprocess Microsyst. 2021;82:103828.
Sucerquia A, López JD, Vargas-Bonilla JF. SisFall: a fall and movement dataset. Sensors. 2017;17(1):198.
Luna-Perejón F, Domínguez-Morales MJ, Civit-Balcells A. Wearable fall detector using recurrent neural networks. Sensors. 2019;19(22):4885.
Musci M, De Martini D, Blago N, Facchinetti T, Piastra M. Online fall detection using recurrent neural networks. arXiv:1804.04976. 2018:1-6.
Waheed M, Afzal H, Mehmood K. Nt-fds—a noise tolerant fall detection system using deep learning on wearable devices. Sensors. 2021;21(6):1-26.
Yu X, Koo B, Jang J, Kim Y, Xiong S. A comprehensive comparison of accuracy and practicality of different types of algorithms for pre-impact fall detection using both young and old adults. Measurement. 2022;201:111785.
Noury N, Rumeau P, Bourke AK, ÓLaighin G, Lundy JE. A proposal for the classification and evaluation of fall detectors. IRBM. 2008;29(6):340-9.
Wang G, Li Q, Wang L, Zhang Y, Liu Z. Elderly fall detection with an accelerometer using lightweight neural networks. Electronics. 2019;8(11):1354.
Casilari E, Santoyo-Ramón JA, Cano-García JM. Analysis of public datasets for wearable fall detection systems. Sensors. 2017;17(7):1513.
Hosseinian SM, Zhu Y, Mehta RK, Erraguntla M, Lawley MA. Static and dynamic work activity classification from a single accelerometer: implications for ergonomic assessment of manual handling tasks. IISE Trans Occup Ergon Hum Factors. 2019;7(1):59-68.
Kangas M, Vikman I, Wiklander J, Lindgren P, Nyberg L, Jämsä T. Sensitivity and specificity of fall detection in people aged 40 years and over. Gait Posture. 2009;29(4):571-4.
Lees MN, Lee JD. The influence of distraction and driving context on driver response to imperfect collision warning systems. Ergonomics. 2007;50(8):1264-86.
Moon H, Han SH, Chun J. Applying signal detection theory to determine the ringtone volume of a mobile phone under ambient noise. Int J Ind Ergon. 2015;47:117-23.
Huang YY, Menozzi M, Favey C. A screening tool for occupations requiring a high level of attentional performance. Int J Ind Ergon. 2019;72:86-92.
Jiang X, Khasawneh MT, Master R, Bowling SR, Gramopadhye AK, Melloy BJ, at al. Measurement of human trust in a hybrid inspection system based on signal detection theory measures. Int J Ind Ergon. 2004;34(5):407-19.
Liang SFM, Menozzi M, Huang YYR. A mechanism based on finger-sliding behavior for designing radial menus. Int J Ind Ergon. 2019;74:102869.
Liu CL. Countering the loss of extended vigilance in supervisory control using a fuzzy logic model. Int J Ind Ergon. 2009;39(6):924-33.
Michel S, Mendes M, de Ruiter JC, Koomen GCM, Schwaninger A. Increasing X-ray image interpretation competency of cargo security screeners. Int J Ind Ergon. 2014;44(4):551-60.
Seong Y, Nam CS. Capturing judgment policy on customers’ creditworthiness: a lens model and SDT approach. Int J Ind Ergon. 2008;38(7-8):593-600.
Grier JB. Nonparametric indexes for sensitivity and bias: Computing formulas. Psychol Bull. 1971;75(6):424-9.
Edgar GK, Catherwood D, Baker S, Sallis G, Bertels M, Edgar HE, et al. Quantitative analysis of situation awareness (QASA): modelling and measuring situation awareness using signal detection theory. Ergonomics. 2018;61(6):762-77.
Stanislaw H. Calculation of signal detection theory measures. Behav Res Meth Instrum Comput. 1999;31:137-49.
Lim S, D’Souza C. A narrative review on contemporary and emerging uses of inertial sensing in occupational ergonomics. Int J Ind Ergon. 2020;76:102937.
Tausendschön J, Radl S. Deep neural network-based heat radiation modelling between particles and between walls and particles. Int J Heat Mass Transf. 2021;177:121557.
Abbate S, Avvenuti M, Bonatesta F, Cola G, Corsini P, Vecchio A. A smartphone-based fall detection system. Pervasive Mob Comput. 2012;8(6):883-99.
Gharghan SK, Mohammed SL, Al-Naji A, Abu-AlShaeer MJ, Jawad HM, Jawad AM, et al. Accurate fall detection and localization for elderly people based on neural network and energy-efficient wireless sensor network. Energies. 2018;11(11):2866.
Munadhil Z, Gharghan SK, Mutlag AH, Al-Naji A, Chahl J. Neural Network-Based Alzheimer’s Patient Localization for Wireless Sensor Network in an Indoor Environment. IEEE Access. 2020;8:150527-38.
Shrestha SB, Song Q. Adaptive learning rate of SpikeProp based on weight convergence analysis. Neural Networks. 2015;63:185-98.
Al-Majidi SD, Abbod MF, Al-Raweshidy HS. A particle swarm optimisation-trained feedforward neural network for predicting the maximum power point of a photovoltaic array. Eng Appl Artif. Intell. 2020;92:103688.
Cameron R, Zuo Z, Sexton G, Yang L. A fall detection/recognition system and an empirical study of gradient-based feature extraction approaches. In: Chao F, Schockaert S, Zhang Q, editor. Advances in Computational Intelligence Systems. UKCI 2017. Advances in Intelligent Systems and Computing Volume 650. Cham: Springer; 2018. p. 276-89.
Chernbumroong S, Cang S, Atkins A, Yu H. Elderly activities recognition and classification for applications in assisted living. Expert Syst Appl. 2013;40(5):1662-74.
Xiao WB, Nazario G, Wu HM, Zhang HM, Cheng F. A neural network based computational model to predict the output power of different types of photovoltaic cells. PLoS One 2017;12(9):e0184561.
Mittal M, Bora B, Saxena S, Gaur AM. Performance prediction of PV module using electrical equivalent model and artificial neural network. Sol Energy. 2018;176:104-17.
Armstrong RA, Eperjesi F, Gilmartin B. The application of analysis of variance (ANOVA) to different experimental designs in optometry. Ophthalmic Physiol Opt. 2002;22(3):248-56.
Smalheiser NR. ANOVA. In: Smalheiser NR, editor. Data literacy: how to make your experiments robust and reproducible. London: Academic Press; 2017. p. 149-55.
Packianather MS, Drake PR, Rowlands H. Optimizing the parameters of multilayered feedforward neural networks through Taguchi design of experiments. Qual Reliab Eng Int. 2000;16(6):461-73.
Gibson RM, Amira A, Ramzan N, Casaseca-De-La-Higuera P, Pervez Z. Multiple comparator classifier framework for accelerometer-based fall detection and diagnostic. Appl Soft Comput. 2016;39:94-103.
Mustafa MR, Rezaur RB, Rahardjo H, Isa MH. Prediction of pore-water pressure using radial basis function neural network. Eng Geol. 2012;135-136:40-7.
Mustafa MR, Isa MH, Rezaur RB. A comparison of artificial neural networks for prediction of suspended sediment discharge in river-a case study in Malaysia. World Acad Sci Eng Technol. 2011;81:372-6.
Khosravi A, Koury RNN, Machado L, Pabon JJG. Prediction of hourly solar radiation in Abu Musa Island using machine learning algorithms. J Clean Prod. 2018;176:63-75.
Vaziri N, Hojabri A, Erfani A, Monsefi M, Nilforooshan B. Critical heat flux prediction by using radial basis function and multilayer perceptron neural networks: a comparison study. Nucl Eng Des. 2007;237(4):377-85.
Yilmaz AS, Özer Z. Pitch angle control in wind turbines above the rated wind speed by multi-layer perceptron and radial basis function neural networks. Expert Syst Appl. 2009;36(6):9767-75.
Huda ASN, Taib S. Suitable features selection for monitoring thermal condition of electrical equipment using infrared thermography. Infrared Phys Technol. 2013;61:184-91.
Rezaeian-Zadeh M, Tabari H, Abghari H. Prediction of monthly discharge volume by different artificial neural network algorithms in semi-arid regions. Arab J Geosci. 2013;6:2529-37.
Møller MF. A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks. 1993;6(4):525-33.
Villar JR, Chira C, de la Cal E, González VM, Sedano J, Khojasteh SB. Autonomous on-wrist acceleration-based fall detection systems: unsolved challenges. Neurocomputing. 2021;452:404-13.
Khojasteh SB, Villar JR, Chira C, González VM, de la Cal E. Improving fall detection using an on-wrist wearable accelerometer. Sensors (Basel). 2018;18(5):1-28.
Martínez-Villaseñor L, Ponce H, Brieva J, Moya-Albor E, Núñez-Martínez J, Peñafort-Asturiano C. Up-fall detection dataset: a multimodal approach. Sensors. 2019;19(9):1988.
Naranjo-Hernández D, Reina-Tosina J, Roa LM. Special issue “Body sensors networks for e-health applications”. Sensors. 2020;20(14):1-7.
Al-Rakhami MS, Gumaei A, Altaf M, Hassan MM, Alkhamees BF, Muhammad K, et al. FallDeF5: A fall detection framework using 5G-based deep gated recurrent unit networks. IEEE Access. 2021;9:94299-308.
Mubashir M, Shao L, Seed L. A survey on fall detection: Principles and approaches. Neurocomputing. 2013;100:144-52.
Putra IPES, Brusey J, Gaura E, Vesilo R. An event-triggered machine learning approach for accelerometer-based fall detection. Sensors. 2018;18(1):1-18.