MULTI-CHANNELS DEEP CONVOLUTION NEURAL NETWORK FOR EARLY CLASSIFICATION OF MULTIVARIATE TIME SERIES
Abstract
Today, many time series forecasting approaches require data pre-processing and analysis to make accurate predictions. This study uses Deep Neural Networks to examine the performance of the most popular Time Series estimators on a variety of EEG sensing field series (DNN). All DNN models have automated hyper-parameter search. So it may be used on the EEG dataset without understanding the model. These advertisements were automatically launched using internal feature extraction and benchmarking of 61 EEG features. Deep learning-based DNN model that refined data engineering with 97.00% accuracy performed well in the research. The thesis evaluates two shallow networks, one DNN and one LSTM, to overcome this limitation and better explain DNN outcomes in time series classification. We broaden the few experimental parallels to include a baseline study of the two categorization fields for time series, where studies are scarce. We designed an extensible experiment structure and cross validated our models on three datasets to do this. Engine-operating depressives are classified. The method tested DNN and LSTM independently for each dataset and is generalizable to other neural network models for comparison research. Basic DNN performs like LSTM and trains faster. When DNN uses more workouts, we notice a balance in seconds and repeats. DNNs are better than LSTM for time series classification due to their efficiency and faster preparation.
References
2. Lines, J.; Taylor, S.; Bagnall, A. Time Series Classification with HIVE-COTE: The Hierarchical Vote Collective of Transformation-Based Ensembles. ACM Trans. Knowl. Discov. Data 2018, 12.
3. Fawaz, H.I.; Forestier, G.; Weber, J.; Idoumghar, L.; Muller, P.A. Deep learning for time series classification: A review. Data Min. Knowl. Discov. 2019, 33, 1–47.
4. Zheng, Y.; Liu, Q.; Chen, E.; Ge, Y.; Zhao, J.L. Time series classification using multi-channels deep convolutional neural networks. In Proceedings of the International Conference on Web-Age Information Management, Macau, China, 16–18 June 2014; pp. 298–310.
5. Wang, Z.; Yan, W.; Oates, T. Time series classification from scratch with deep neural networks: A strong baseline. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA, 14–19 May 2017; pp. 1578–1585.
6. Blundell, C.; Cornebise, J.; Kavukcuoglu, K.; Wierstra, D. Weight uncertainty in neural networks. arXiv 2015, arXiv:1505.05424. 30. Shridhar, K.; Laumann, F.; Liwicki, M. A comprehensive guide to bayesian convolutional neural network with variational inference. arXiv 2019, arXiv:1901.02731.
7. Leibig, C.; Allken, V.; Ayhan, M.S.; Berens, P.; Wahl, S. Leveraging uncertainty information from deep neural networks for disease detection. Sci. Rep. 2017, 7, 17816.
8. Abideen, Z.U.; Ghafoor, M.; Munir, K.; Saqib, M.; Ullah, A.; Zia, T.; Tariq, S.A.; Ahmed, G.; Zahra, A. Uncertainty Assisted Robust Tuberculosis Identification with Bayesian Convolutional Neural Networks. IEEE Access 2020, 8, 22812–22825.
9. Kendall, A.; Cipolla, R. Modelling uncertainty in deep learning for camera relocalization. In Proceedings of the 2016 IEEE International Conference on Robotics and Automation (ICRA), Stockholm, Sweden, 16–21 May 2016; pp. 4762–4769.
10. Malde, K.; Handegard, N.O.; Eikvil, L.; Salberg, A.B. Machine intelligence and the data-driven future of marine science. ICES J. Mar. Sci. 2019.
11. Biancofiore, F.; Busilacchio, M.; Verdecchia, M.; Tomassetti, B.; Aruffo, E.; Bianco, S.; Di Tommaso, S.; Colangeli, C.; Rosatelli, G.; Di Carlo, P. Recursive neural network model for analysis and forecast of PM10 and PM2. 5. Atmos. Pollut. Res. 2017, 8, 652–659.
12. Available Online: https://stackoverflow.com/questions/43019109/initializing-lstm-for-time-series-classification-on-tensorflow.
13. Blackford, J.; Alendal, G.; Avlesen, H.; Brereton, A.; Cazenave, P.W.; Chen, B.; Dewar, M.; Holt, J.; Phelps, J. Impact and detectability of hypothetical CCS offshore seep scenarios as an aid to storage assurance and risk assessment. Int. J. Greenh. Gas Control 2020, 95, 102949.
14. Cañizo, Mikel & Triguero, Isaac & Conde, Angel & Onieva, Enrique. (2019). Multi-Head CNN-RNN for Multi-Time Series Anomaly Detection: An industrial case study. Neurocomputing. 363. 10.1016/j.neucom.2019.07.034.
15. Butenschön, M.; Clark, J.; Aldridge, J.N.; Allen, J.I.; Artioli, Y.; Blackford, J.; Bruggeman, J.; Cazenave, P.; Ciavatta, S.; Kay, S.; et al. ERSEM 15.06: A generic model for marine biogeochemistry and the ecosystem dynamics of the lower trophic levels. Geosci. Model Dev. 2016, 9, 1293–1339.
16. Vielstädte, L.; Karstens, J.; Haeckel, M.; Schmidt, M.; Linke, P.; Reimann, S.; Liebetrau, V.; McGinnis, D.F.; Wallmann, K. Quantification of methane emissions at abandoned gas wells in the Central North Sea. Mar. Pet. Geol. 2015, 68, 848–860.
17. Ruthotto, L.; Haber, E. Deep neural networks motivated by partial differential equations. J. Math. Imaging Vis. 2019, 62, 1–13.
18. Alendal, G. Cost efficient environmental survey paths for detecting continuous tracer discharges. J. Geophys. Res. Ocean. 2017, 122, 5458–5467.
19. Oleynik, A.; García-Ibáñez, M.I.; Blaser, N.; Omar, A.; Alendal, G. Optimal sensors placement for detecting CO2 discharges from unknown locations on the seafloor. Int. J. Greenh. Gas Control 2020, 95, 102951.
20. Botnen, H.; Omar, A.; Thorseth, I.; Johannessen, T.; Alendal, G. The effect of submarine CO2 vents on seawater: Implications for detection of subsea Carbon sequestration leakage. Limnol. Oceanogr. 2015, 60 402–410.
21. Domínguez-Tejo, E.; Metternicht, G.; Johnston, E.; Hedge, L. Marine Spatial Planning advancing the Ecosystem-Based Approach to coastal zone management: A review. Mar. Policy 2016, 72, 115–130.
22. Hylland, K.; Burgeot, T.; Martínez-Gómez, C.; Lang, T.; Robinson, C.D.; Svavarsson, J.; Thain, J.E.; Vethaak, A.D.; Gubbins, M.J. How can we quantify impacts of contaminants in marine ecosystems? The ICON project. Mar. Environ. Res. 2017, 24, 2–10.
23. Smirnov, Denis & Mephu Nguifo, Engelbert. (2018). Time Series Classification with Recurrent Neural Networks.
24. Sadouk, Lamyaa. (2018). CNN Approaches for Time Series Classification. 10.5772/intechopen.81170.