2. Related Work
3.1. Comparison of Acceleration Sensors
3.2. An Assessment of Acceleration Sensors
3.3. Development of the Earthquake Alert Device
Earthquake Detection Algorithm
3.4. Use Cases
- Smart devices: In this scenario, the earthquake alert device sends a warning message to nearby devices such as a smartphone or TV that pops up appropriate emergency procedures (e.g., “protect yourself from falling objects such as signs or potted plants.”) according to the detected earthquake shaking using straightforward images. Figure 6 shows illustrations that are displayed on a smartphone or TV, and a case study that we developed using a smart TV and an AI-enabled speaker.
- Home Automation: In this scenario, according to the level of strength, the connected home-automation devices such as electricity, gas, and tap-water are automatically shut off as described in Figure 7.
4.1. Experimental Results
ANN Model Evaluation
- Three seconds of the strongest earthquake portion, with 1.5 s before and 1.5 s after the maximum vector sum is the optimal window size.
- Because IQR and CAV are based on the amplitude information of an earthquake, the dataset needs to be balanced in terms of a magnitude level. In other words, intra-class instances must be balanced. If the model is trained with higher magnitude earthquakes, it may not detect the moderate earthquakes in real-time. Similarly, if the model is trained with low earthquakes, it may confuse between the noise data and the earthquake data, thereby increasing false alarm rates.
- The model shows the same results on the Pohang data, whether including or excluding human activities. As earthquake detection devices are fixed and will not be affected by the human activities, it is unnecessary to include human activities such as car, bus, bicycle jump rope, and stairs, etc. Therefore, the detection ability of the model is most likely to depend on the earthquake class.
- The ZC feature is a critical feature and can affect the model performance.
4.2. Evaluation of Acceleration Sensors
4.3. Evaluation of the Earthquake Detection Algorithm
5. Future Work and Conclusions
Conflicts of Interest
- Gubbi, J.; Buyya, R.; Marusic, S.; Palaniswami, M. Internet of Things (IoT): A vision, architectural elements, and future directions. Future Gener. Comput. Syst. 2013, 29, 1645–1660. [Google Scholar] [CrossRef]
- Al-Fuqaha, A.; Guizani, M.; Mohammadi, M.; Aledhari, M.; Ayyash, M. Internet of things: A survey on enabling technologies, protocols, and applications. IEEE Commun. Surv. Tutor. 2015, 17, 2347–2376. [Google Scholar] [CrossRef]
- Komninos, N.; Philippou, E.; Pitsillides, A. Survey in smart grid and smart home security: Issues, challenges and countermeasures. IEEE Commun. Surv. Tutor. 2014, 16, 1933–1954. [Google Scholar] [CrossRef]
- Feng, G.; Mai, J.; Ban, Z.; Guo, X.; Wang, G. Floor pressure imaging for fall detection with fiber-optic sensors. IEEE Pervasive Comput. 2016, 15, 40–47. [Google Scholar] [CrossRef]
- Batista, M.A.; Gaglani, S.M. The future of smartphones in health care. AMA J. Ethics 2013, 15, 947–950. [Google Scholar]
- Schmitz Weiss, A. Exploring news apps and location-based services on the smartphone. J. Mass Commun. Q. 2013, 90, 435–456. [Google Scholar] [CrossRef]
- Available online: https://www.usgs.gov/faqs/why-are-we-having-so-many-earthquakes-has-naturally-occurring-earthquake-activity-been (accessed on 5 November 2019).
- Holzer, T.L.; Savage, J.C. Global earthquake fatalities and population. Earthq. Spectra 2013, 29, 155–175. [Google Scholar] [CrossRef]
- D’Alessandro, A.; Vitale, G.; Scudero, S.; D’Anna, R.; Costanza, A.; Fagiolini, A.; Greco, L. Characterization of MEMS accelerometer self-noise by means of PSD and Allan Variance analysis. In Proceedings of the 2017 7th IEEE International Workshop on Advances in Sensors and Interfaces (IWASI), Vieste, Italy, 15–16 June 2017; pp. 159–164. [Google Scholar]
- Kong, Q.; Allen, R.M.; Schreier, L.; Kwon, Y.W. MyShake: A smartphone seismic network for earthquake early warning and beyond. Sci. Adv. 2016, 2, e1501055. [Google Scholar] [CrossRef] [PubMed]
- Kong, Q.; Kwony, Y.W.; Schreierz, L.; Allen, S.; Allen, R.; Strauss, J. Smartphone-based networks for earthquake detection. In Proceedings of the 2015 15th International Conference on Innovations for Community Services (I4CS), Nuremberg, Germany, 8–10 July 2015; pp. 1–8. [Google Scholar]
- Kong, Q.; Lv, Q.; Allen, R.M. Earthquake Early Warning and Beyond: Systems Challenges in Smartphone-based Seismic Network. In Proceedings of the 20th International Workshop on Mobile Computing Systems and Applications, Santa Cruz, CA, USA, 27–28 February 2019; ACM: New York, NY, USA, 2019; pp. 57–62. [Google Scholar]
- Luetgert, J.; Oppenheimer, D.; Hamilton, J. The NetQuakes Project-Research-quality Seismic Data Transmitted via the Internet from Citizen-Hosted Instruments; AGU Fall Meeting Abstracts; AGU: Washington, DC, USA, 2010. [Google Scholar]
- Cochran, E.; Lawrence, J.; Christensen, C.; Chung, A. A novel strong-motion seismic network for community participation in earthquake monitoring. IEEE Instrum. Meas. Mag. 2009, 12, 8–15. [Google Scholar] [CrossRef]
- Clayton, R.W.; Heaton, T.; Chandy, M.; Krause, A.; Kohler, M.; Bunn, J.; Guy, R.; Olson, M.; Faulkner, M.; Cheng, M.; et al. Community seismic network. Ann. Geophys. 2012, 54. [Google Scholar] [CrossRef]
- Horiuchi, S.; Horiuchi, Y.; Yamamoto, S.; Nakamura, H.; Wu, C.; Rydelek, P.A.; Kachi, M. Home seismometer for earthquake early warning. Geophys. Res. Lett. 2009, 36. [Google Scholar] [CrossRef]
- D’Alessandro, A. Tiny accelerometers create Europe’s first urban seismic network. Eos 2016, 97. [Google Scholar] [CrossRef]
- Wu, Y.M. Progress on development of an earthquake early warning system using low-cost sensors. Pure Appl. Geophys. 2015, 172, 2343–2351. [Google Scholar] [CrossRef]
- Evans, J.; Allen, R.M.; Chung, A.; Cochran, E.; Guy, R.; Hellweg, M.; Lawrence, J. Performance of several low-cost accelerometers. Seismol. Res. Lett. 2014, 85, 147–158. [Google Scholar] [CrossRef]
- Rong, K.; Yoon, C.E.; Bergen, K.J.; Elezabi, H.; Bailis, P.; Levis, P.; Beroza, G.C. Locality-sensitive hashing for earthquake detection: A case study of scaling data-driven science. Proc. VLDB Endow. 2018, 11, 1674–1687. [Google Scholar] [CrossRef]
- Perol, T.; Gharbi, M.; Denolle, M. Convolutional neural network for earthquake detection and location. Sci. Adv. 2018, 4, e1700578. [Google Scholar] [CrossRef] [PubMed]
- Available online: https://www.analog.com/media/en/technical-documentation/data-sheets/adxl354_355.pdf (accessed on 5 November 2019).
- Available online: https://www.st.com/resource/en/datasheet/lis3dhh.pdf (accessed on 5 November 2019).
- Available online: https://www.invensense.com/wp-content/uploads/2015/02/PS-MPU-9250A-01-v1.1.pdf (accessed on 5 November 2019).
- Available online: https://www.nxp.com/docs/en/data-sheet/MMA8452Q.pdf (accessed on 5 November 2019).
- Bishop, C. Neural Networks for Pattern Recognition; Oxford University Press: New York, NY, USA, 1996. [Google Scholar]
- Hecht-Nielsen, R. Theory of the backpropagation neural network. In Neural Networks for Perception; Elsevier: Amsterdam, The Netherlands, 1992; pp. 65–93. [Google Scholar]
- Haykin, S.; Network, N. A comprehensive foundation. Neural Netw. 2004, 2, 41. [Google Scholar]
- Bottou, L. Large-scale machine learning with stochastic gradient descent. In Proceedings of COMPSTAT’2010; Springer: Berlin/Heidelberg, Germany, 2010; pp. 177–186. [Google Scholar]
- Hartigan, J.A.; Wong, M.A. Algorithm AS 136: A k-means clustering algorithm. J. R. Stat. Society. Ser. C Appl. Stat. 1979, 28, 100–108. [Google Scholar] [CrossRef]
- Powers, D.M. Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation; Flinders University: Adelaide, Australia, 2011. [Google Scholar]
- Fawcett, T. An introduction to ROC analysis. Pattern Recognit. Lett. 2006, 27, 861–874. [Google Scholar] [CrossRef]
- National Research Institute for Earth Science and Disaster Prevention. Available online: http://www.kyoshin.bosai.go.jp (accessed on 5 November 2019).
- Peer Ground Motion Database, Pacific Earthquake Engineering Research Center. Available online: https://ngawest2.berkeley.edu/ (accessed on 5 November 2019).
|Data output (bit)||20||16||12||16|
|Max. output (Hz)||1000||1100||800||4000|
|MCU||ARM Cortex M3|
|1||0.02 g–0.16 g|
|2||0.16 g–0.33 g|
|3||over 0.33 g|
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).