Page 277 - Handbook of Deep Learning in Biomedical Engineering Techniques and Applications

268 Chapter 9 Applications of deep learning in biomedical engineering

polluted particles in air. Air pollution dynamics can be repre-
sented by various factors such as the temperature, humidity,
rain fall, wind speed and direction, snow fall, and so on.
Short-term forecasting model based on DL is built for PM2.5
(particulate matter with an aerodynamic diameter less than or
equal to 2.5 m) concentration. The testing is done over the
Beijing PM2.5 data set in UCI machine learning repository
providing the accurate prediction over air pollution [40].
Mobile phone metadata are used to study the human
behavior. Previous approaches of learning human behavior
depend on hand-engineered features. But recent trends rely on
DL techniques. This technique uses convolution neural network.
These techniques implemented over standard mobile phone
metadata. The standard mobile phone metadata incorporate
the text message that the user receives and sends or a phone
call that the user dials or receives, how long the call continues,
who calls, and the caller information. This information is used
to predict the user's age, gender, and psychological behavior [41].

44. Conclusion

DL, the emerging technology, is being applied in all the areas
of biomedical engineering such as omics, medical image analysis,
BBMI, and public health management system. This chapter
reveals that deep architectures overcome the traditional practices
of biomedicine in all the aspects by learning the features auto-
matically. In the recent years, genomics data are involved in
many researches including drug discovery, disease diagnosing,
and analysis. These high-dimensional and complex data are
interpreted extremely using DL. CNN architecture is the most
competent architecture in medical image classification. GAN
emanates in the field of biomedicine. Even though DL equips
many advantages, it has complexities too, which needs to be
resolved. Thus, DL will be the most indispensable technology in
the future of biomedicine.

References

[1] https://www.livescience.com/48001-biomedical-engineering.html.
[2] R. Zemouri, N. Zerhouni, D. Racoceanu, Deep learning in the biomedical
applications: recent and future status, Appl. Sci. (April 2019), https://
doi.org/10.3390/app9081526.
[3] https://innovatemedtec.com/digital-health/medical-imaging.