▷ Behavioral Signal Processing with Machine Learning based on #FPGA

⭐⭐⭐⭐⭐ Behavioral Signal Processing with Machine Learning based on #FPGA from Victor Asanza

• ➡️ #DigitalSystems #DigitalElectronic #DigitalCircuits #HDL #VHDL #FPGA
• ➡️ ICCIS2020: 1st International Conference on Systems and Information Sciences
• ⭐ Read full paper: https://doi.org/10.1007/978-3-030-59194-6_17
• ✅ Read Proceedings: https://link.springer.com/book/10.1007/978-3-030-59194-6
• When using this resource, please cite the original publication:
• Asanza V., Sanchez G., Cajo R., Peláez E. (2021) Behavioral Signal Processing with Machine Learning Based on FPGA. In: Botto-Tobar M., Zamora W., Larrea Plúa J., Bazurto Roldan J., Santamaría Philco A. (eds) Systems and Information Sciences. ICCIS 2020. Advances in Intelligent Systems and Computing, vol 1273. Springer, Cham. https://doi.org/10.1007/978-3-030-59194-6_17

• ✅ Video of the talk:

✅ Published in: https://link.springer.com/chapter/10.1007%2F978-3-030-59194-6_17

✅ Paper content:

• Introduction:

• Sedentary lifestyle.
• 21-25% of breast and colon cancer
• 27% of diabetes
• 30% of heart disease
• Behavior of Physical Activity (PA).
• Martín et al., Social Cognitive Theory.
• Narayanan et al., Behavioral Signal Processing #BSP
• Asanza et al., using dynamical model.

• Related Work:

• L. Vachhani et al., proposed diferent hypotheses on the step count, which resulted in social feedback and feedback on the progress of the individual every day.
• Freigoun et al., implemented a smartphone application called “Just Walk” for adaptive walking intervention for sedentary and overweight adults.
• Martin et al., SCT is implemented in the study of the behavior of an individual for management of well-being and health.
• CARIMA-type models.
• Deep neural networks are more efficient for modeling and allow continuous decision making with the help of Internet of Things #IoT technologies.
• Khan et al., proposed a physical activity recognition system based on machine learning decision tree algorithm with data from 3D acceleration sensors.

• Discussion and Conclusions:

• Features used in the dataset allowed us to contextualize the behavior of individuals based on the variables of the environment.
• Ambient temperature
• It was implemented using an #FPGA development card that provides great flexibility in its structuring.
• Was possible to obtain an accuracy of 93.0% in the prediction of the data.
• Multiprocessor computer in the #FPGA development card
• Without extra components

• References:

1. World Health Organization, WHO.: Physical activity, February 2018. https://www.who.int/es/news-room/fact-sheets/detail/physical-activity. Accessed 6 Apr 2020
2. Bauer, U.E., Briss, P.A., Goodman, R.A., Bowman, B.A.: Prevention of chronic disease in the 21st century: elimination of the leading preventable causes of premature death and disability in the USA. Lancet 384(9937), 45–52 (2014). https://doi.org/10.1016/S0140-6736(14)60648-6
3. Freigoun, M.T., Mart´ın, C.A., Magann, A.B., Rivera, D.E., Phatak, S.S., Korinek, E.V., Hekler, E.B.: System identification of just walk: a behavioral mHealth intervention for promoting physical activity. In: 2017 American Control Conference (ACC), pp. 116-121 (2017). https://doi.org/10.23919/ACC.2017.7962940
4. Richardson, C.R., Newton, T.L., Abraham, J.J., Sen, A., Jimbo, M., Swartz, A.M.: A meta-analysis of pedometer-based walking interventions and weight loss. Ann. Fam. Med. 6, 69–77 (2008). https://doi.org/10.1370/afm.761
5. Narayanan, S., Georgiou, P.: Behavioral signal processing: deriving human behavioral informatics from speech and language. In: Proceedings of the IEEE Institute of Electrical and Electronics Engineers, vol. 101(5), pp. 1203-1205 (2013). https://doi.org/10.1109/JPROC.2012.2236291
6. Fujiki, Y., Kazakos, K., Puri, C., Starren, J., Pavlidis, I., Levine, J.: NEAT-ogames: ubiquitous activity-based gaming. In: Proceedings of the 2007 ACM Conference on Human Factors in Computing Systems (CHI), pp. 2369-2374. ACM Press (2007). https://doi.org/10.1145/1240866.1241009
7. Asanza, V., Martin, C.A., Eslambolchilar, P., van Woerden, H., Cajo, R., Salazar, C.: Finding a dynamical model of a social norm physical activity intervention. In: 2017 IEEE Second Ecuador Technical Chapters Meeting (ETCM), Salinas, pp. 1–6 (2017). https://doi.org/10.1109/ETCM.2017.8247450
8. Bandura, A.: Social Foundations of Thought and Action: A Social Cognitive Theory. Prentice-Hall series in social learning theory. Prentice-Hall, Upper Saddle River (1986)
9. Martín, C.A., Rivera, D.E., Riley, W.T., Hekler, E.B., Buman, M.P., Adams, M.A., King, A.C.: A dynamical systems model of social cognitive theory. In: Proceedings of the American Control Conference, pp. 2407–2412 (2014). https://doi.org/10.1109/ACC.2014.6859463
10. Nagarajan, K., Holland, B., George, A.D., Clint, K., Lam, H.: accelerating machinelearning algorithms on FPGAs using pattern-based decomposition. J. Sign. Process. Syst. 62, 271–350 (2011). https://doi.org/10.1007/s11265-008-0337-9
11. Harries, T., Eslambolchilar, P., Rettie, R., et al.: Effectiveness of a smartphone app in increasing physical activity amongst male adults: a randomised controlled trial. BMC Public Health 16(925), 1–10 (2016). https://doi.org/10.1186/s12889-016-3593-9
12. Vachhani, L., Sridharan, K.: Hardware-efficient prediction-correction-based generalized-Voronoi-diagram construction and FPGA implementation. IEEE Trans. Ind. Electron. 55(4), 1558–1569 (2008). https://doi.org/10.1109/TIE.2008.917161
13. Rixen, M., Ferreira-Coelho, E., Signell, R.: Surface drift prediction in the Adriatic sea using hyper-ensemble statistics on atmospheric, ocean and wave models: uncertainties and probability distribution areas. J. Mar. Syst. 69(1–2), 86–98 (2008). https://doi.org/10.1016/j.jmarsys.2007.02.015
14. Kanawaday, A., Sane, A.: Machine learning for predictive maintenance of industrial machines using IOT sensor data. In: 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), pp. 87-90. IEEE (2017). https://doi.org/10.1109/ICSESS.2017.8342870
15. Azorín, J., Saval, M., Fuster, A., Oliver, A.: A predictive model for recognizing human behaviour based on trajectory representation. In: International Joint Conference on Neural Networks (IJCNN), Beijing, pp. 1494–1501 (2014). https://doi.org/10.1109/IJCNN.2014.6889883
16. Pentland, A., Liu, A.: Modeling and prediction of human behavior. Neural Comput. 11(1), 229–242 (1999). https://doi.org/10.1162/089976699300016890
17. Khan, A., Lawo, M., Homer, P.:Wearable recognition system for physical activities. In: 9th International Conference on Intelligent Environments, Athens, pp. 245–249 (2013). https://doi.org/10.1109/IE.2013.50
18. Tirkaz, C., Bruckner, D., Yin, G.Q., Haase, J.: Activity recognition using a hierarchical model. In: IECON 2012—38th Annual Conference on IEEE Industrial Electronics Society, pp. 2814–2820 (2012)
19. Santhiranayagam, B.K., Lai, D.T., Jiang, C., Shilton, A., Begg, R.: Automatic detection of different walking conditions using inertial sensor data. In: the 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2012). https://doi.org/10.1109/IJCNN.2012.6252501
20. Upegui, A., Pe˜na, C., Sanchez, E.: An FPGA platform for on-line topology exploration of spiking neural networks. Microprocess. Microsyst. 29(5), 211–223 (2005). https://doi.org/10.1016/j.micpro.2004.08.012
21. Lacey, G., Taylor, G., Areibi, S.: Deep learning on FPGAs: Past, present, and future. arXiv preprint arXiv:1602.04283 (2016)

• Read related topics:

• ✅ Paper: Finding a Dynamical Model of a Social Norm Physical Activity Intervention
• ✅ Paper: Implementation Of Automated System For The Reservoir 66 of the Irrigation System Chambo Guano
• ✅ Implementation of a Classification System of #EEG Signals Based on #FPGA
• ✅ Artificial Neural Network based #EMG recognition for gesture communication (#InnovateFPGA)
• ✅ Projects Digital Systems Design #FPGA
• ✅ 2020 PAO1: Proyectos Propuestos
• ✅ End Device #Arduino #FreeRTOS
• ✅ End Device + Coordinator #Raspberry Pi #Python