Scientific Journal

Applied Aspects of Information Technology


This work is devoted to the development of a distributed framework based on deep learning for processing data from various  sensors that are generated by transducer networks that are used in the field of smart buildings. The proposed framework allows you to process data that comes from sensors of various types to solve classification and regression problems. The framework architecture  consists of several subnets: particular convolutional net that handle input from the same type of sensors, a single convolutional fusion  net that processes multiple outputs of particular convolutional nets. Further, the result of a single convolutional fusion net is fed to  the input of a recurrent net, which allows extracting meaningful features from time sequences. The result of the recurrent net opera 

tion is fed to the output layer, which generates the framework output based on the type of problem being solved. For the experimental  evaluation of the developed framework, two tasks were taken: the task of recognizing human actions and the task of identifying a  person by movement. The dataset contained data from two sensors (accelerometer and gyroscope), which were collected from 9 users  who performed 6 actions. A mobile device was used as the hardware platforms, as well as the Edison Compute Module hardware  device. To compare the results of the work, variations of the proposed framework with different architectures were used, as well as  third-party approaches based on various methods of machine learning, including support machines of vectors, a random forest, lim 

ited Boltzmann machines, and so on. As a result, the proposed framework, on average, surpassed other algorithms by about 8% in  three metrics in the task of recognizing human actions and turned out to be about 13% more efficient in the task of identifying a per son by movement. We also measured the power consumption and operating time of the proposed framework and its analogues. It was  

found that the proposed framework consumes a moderate amount of energy, and the operating time can be estimated as acceptable.


1. BSRIA. “The Smart Building Market in Asia will exceed $1036bn by 2020”. – Available from:$1,036bn-by-2020. – [Accessed Feb 2021]. 

2. So, A. T. P. & Wong, K. C. “On the Quantitative Assessment of Intelligent Buildings”. Facilities.  2002; Vol. 20 No. 5/6: 208–216. DOI:

3. Azevedo Guedes, A. L., Carvalho Alvarenga, J., Dos Santos Sgarbi Goulart, M., Rodriguez y Rodri guez, M. V. & Pereira Soares, C. A. “Smart Cities: The Main Drivers for Increasing the Intelligence of Cit ies”. Sustainability. 2018; Vol. 10. 3121. DOI:

4. Antoshchuk, S. G., Shamin, I. I., Sharma, B. S. & Shcherbakova, G. Yu. “A Multi-Objective Optimi zation Problems of Clustering Protocols for Wireless Sensor Networks Using Meta-Heuristic Techniques”. Herald of Advanced Information TechnologyPubl. Nauka i Tekhnika. Odesa: Ukraine. 2018; Vol. 1 No. 1:  21–27. DOI: 10.15276/hait.01.2018.2. 

5. Lima, E. G., Chinelli, C. K., Guedes, A. L. A., Vazquez, E. G., Hammad, A. W. A., Haddad, A. N. &  Soares, C. A. P. “Smart and Sustainable Сities: The Main Guidelines of City Statute for Increasing the Intel ligence of Brazilian Cities”. Sustainability. 2020; Vol. 12 No. 3. 1025. DOI: 10.3390/su12031025. 

6. McGlinn, K., O’Neill, E., Gibney, A., O’Sullivan, D. & Lewis, D. “Simcon: A Tool to Support Rapid  Evaluation of Smart Building Application Design Using Context Simulation and Virtual Reality”. Journal of  Universal Computer Science. 2010; Vol. 16 No. 15: 1992–2018. DOI: 1992. 

7. Assunção, M. D., Calheiros, R. N., Bianchi, S., Netto, M. A. & Buyya, R. “Big Data Computing and  Clouds: Trends and Future Directions”. Journal of Parallel and Distributed Computing. 2015; Vol. 79-80:  3–15. DOI: 

8. Stojmenovic, I. & Wen, S. “The Fog Computing Paradigm: Scenarios and Security Issues”, Proceed ings of the 2014 Federated Conference on Computer Science and Information Systems. 2014; Vol. 2: 1– 8. DOI: 

9. Dastjerdi, A. V., Gupta, H., Calheiros, R. N., Ghosh, S. K. & Buyya, R. “Fog Computing: Principles,  Architectures and Applications”. Internet of Things, Principles and Paradigms. 2016: p. 61–75.  DOI: 

10. Mukherjee, M., Matam, R., Shu, L., Maglaras, L., Ferrag, M., A. Choudhury, N. & Kumar, V. “Se curity and Privacy in Fog Computing: Challenges”. IEEE Access. 2017; Vol. 5: 19293–19304.  DOI: 

11. Khan, S., Parkinson, S. & Qin, Y. “Fog Computing Security: A Review of Current Applications and  Security Solutions”. Journal of Cloud Computing. 2017; Vol. 6 No. 19. DOI: 10.1186/s13677-017-0090-3. 

12. Bonomi, F., Milito, R., Zhu, J. & Addepalli, S. “Fog Computing and its Role in the Internet of  Things”. Proceedings of the First Edition of the MCC Workshop on Mobile Cloud Computing. 2012. р. 13–16.  DOI: 

13. Sareen, P. & Kumar, P. “The Fog Computing Paradigm”. International Journal of Engineering & Technology. 2016; Vol. 4 No. 8: 55–60. 

14. Vaquero, L. M. & Rodero-Merino, L. “Finding Your Way in the Fog: Towards a Comprehensive  Definition of Fog Computing”. ACM SIGCOMM Computer Communication Review. 2014; Vol. 44 No. 5:  27–32. DOI: 

15. Saharan, K. P. & Kumar, A. “Fog in Comparison to Cloud: A Survey”. International Journal of  Computer Applications. 2015; Vol. 122 No. 3: 10–12. DOI:

16. Antoshchuk, S. G., Lobachev, I. M. & Maleryk, R. P. “Method of the Sensor Network Resources  Allocation in the Conditions of Edge Computing”. Herald of Advanced Information TechnologyPubl. Nau ka i Tekhnika. Odesa: Ukraine. 2018; Vol. 1 No. 1: 28–35. DOI:

17. Shi, W., Cao, J., Zhang, Q., Li, Y. & Xu, L. “Edge Computing: Vision and Challenges”. IEEE In ternet Things Journal. 2016; Vol. 3 No. 5: 637–646. DOI:

18. Mahmud, R., Kotagiri, R. & Buyya, R. “Fog Computing: A Taxonomy, Survey and Future Direc tions”. Internet of Everything. 2018: 103–130. DOI:

19. Kamath, G., Agnihotri P., Valero, M., Sarker, K. & Song, W.-Z. “Pushing Analytics to the Edge”. IEEE Global Communications Conference (GLOBECOM). 2016. p. 1–6. DOI: GLOCOM.2016.7842181. 

20. Azimi, I., Anzanpour, A., Rahmani, A. M., Liljeberg, P. & Salakoski T. “Medical Warning System  Based on Internet of Things Using Fog Computing”. International Workshop on Big Data and Information  Security (IWBIS). 2016. р. 19–24. DOI: 

21. Lu, L., Xu, L., Xu, B., Li, G. & Cai, H. “Fog Computing Approach for Music Cognition System  Based on Machine Learning Algorithm”. IEEE Transactions on Computational Social Systems. 2018; Vol. 5  No. 4: 1142–1151. DOI: 

22. Li, L., Ota, K. & Dong M. “Deep Learning for Smart Industry: Efficient Manufacture Inspection Sys tem with Fog Computing”. IEEE Transactions on Industrial Informatics. 2018; Vol. 14 No. 10: 4665–4673.  DOI: 

23. Sheremet, O. I., Korobov, O. Ye., Sadovoi, O. V. & Sokhina, Y. V. “Intelligent System Based on a  Convolutional Neural Network for Identifying People Without Breathing Masks”. Applied Aspects of Infor mation TechnologyPubl. Nauka i Tekhnika. Odesa: Ukraine. 2020; Vol.3 No.3: 133–144.  DOI: 

24. Pérez, J. L., Gutierrez-Torre, A., Berral, J. L. & Carrera D. “A Resilient and Distributed Near Real time Traffic Forecasting Application for Fog Computing Environments”. Future Generation Computer Sys tems. 2018; Vol. 87: 198–212. DOI: 

25. Kimovski, D., Ijaz, H., Saurabh, N. & Prodan R. “Adaptive Nature-inspired Fog Architecture”,  IEEE 2nd International Conference on Fog and Edge Computing (ICFEC). 2018. р. 1–8.  DOI: 10.1109/CFEC.2018.8358723. 

26. Lu, J., Xiang, X., Shen, D., Chen, G., Chen, N., Blasch, E., Pham K. & Chen, Y. “Artificial Intelli gence Based Directional Mesh Network Design for Spectrum Efficiency”. IEEE Aerospace Conference.  2018. р. 1–9. DOI: 10.1109/AERO.2018.8396558. 

27. Costa, R., Jardim-Goncalves, R., Figueiras, P., Forcolin, M., Jermol, M. & Stevens R. ‘‘Smart Car go for Multimodal Freight Transport: When ‘Cloud’ Becomes ‘Fog’’. IFAC-PapersOnLine. 2016; Vol. 49  No. 12: 121–126. DOI: 

28. Stisen, A., Blunck, H., Bhattacharya, S., Prentow, T. S., Kjaergaard M. B., Dey, A., Sonne, T. &  Jensen M. M. “Smart Devices are Different: Assessing and Mitigating Mobile Sensing Heterogeneities for  Activity Recognition”. SenSys '15: Proceedings of the 13th ACM Conference on Embedded Networked Sen sor Systems. 2015. p. 127–140. DOI: 

29. Figo, D., Diniz, P. C., Ferreira, D. R. & Cardoso, J. M. “Preprocessing Techniques for Context  Recognition from Accelerometer Data”. Personal and Ubiquitous Computing. 2010; Vol. 14: 645–662.  DOI: 

30. Hammerla, N. Y., Kirkham, R., Andras, P. & Ploetz, T. “On Preserving Statistical Characteristics  of Accelerometry Data Using Their Empirical Cumulative Distribution”. ISWC '13: Proceedings of the 2013  International Symposium on Wearable Computers. 2013. р. 65–68. DOI: 10.1145/2493988.2494353. 

31. Bhattacharya, S. & Lane, N. D. “From Smart to Deep: Robust Activity Recognition on Smartwatch es Using Deep Learning”. IEEE International Conference on Pervasive Computing and Communication  Workshops (PerCom Workshops). 2016. р. 1–6. DOI: 10.1109/PERCOMW.2016.7457169. 

32. Radu, V., Lane, N. D., Bhattacharya, S., Mascolo, C., Marina, M. K. & Kawsar, F. “Towards Multi modal Deep Learning for Activity Recognition on Mobile Devices”. UbiComp '16: Proceedings of the 2016  ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct. 2016. р. 185–188. DOI:

33. Thang, H. M., Viet, V. Q., Thuc, N. D. & Choi, D. “Gait Identification Using Accelerometer on  Mobile Ohone”. International Conference on Control, Automation and Information Sciences (ICCAIS).  2012. р. 344–348. DOI: 

34. Gadaleta, M. & Rossi, M. “Idnet: Smartphone-based Gait Recognition with Convolutional Neural  Networks”. Pattern Recognition. 2018; Vol. 74: 25–37. DOI:
Last download:
17 May 2022


[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2018.]