Did you know that one of the biggest problems South Korea has is the high suicide rate among its population? According to official figures, in 2019 Korea had a suicide rate of 37%, which places it with the highest rate among OECD countries.[1]
In Korea, it is not unusual for people who are going to commit suicide to do so on one of the 500 bridges that span the Han River over a distance of 500 km [1]. At present, Korea is one of the countries with the best CCTV coverage, making it a fairly safe country.
However, how can this problem be mitigated using artificial intelligence, and what constitutes this tool that is gaining relevance in so many applications related to the fourth industrial revolution and Industry 4.0?
Artificial intelligence is a set of skills programmed into computers that allow a machine to adapt to certain situations based on previous historical data. This type of technology allows decisions to be made based on data from previously performed processes, which considerably reduces the elaboration of mathematical models and the improvement of existing ones. On the other hand, it allows access to these data from any device using the cloud (Cloud technology).
Some sectors that are using these technologies to optimize their processes are:
- Information Technology
- Financial
- Food
- Chemical industry
- Healthcare
The subfield of artificial intelligence that allows machines to learn, improve and perform a specific task using data without being explicitly programmed is known as Machine Learning [2]. The process it uses for problem-solving is as follows:
To mitigate the high suicide rate, the alternative proposed by South Korea is to use the robust CCTV system that the country has and through machine learning and deep learning techniques, it seeks to study historical data of suicide cases that were previously presented to train the machine to alert the cases that look suspicious and present a high risk of committing suicide.
The Machine learning model would be trained using human behavioral patterns, which would indicate which people would be at a high potential risk of committing suicide using the captured CCTV images. Analyses can be tedious and inefficient if performed by psychologists and human behavioral science professionals.
However, to improve the accuracy of such models, the images captured are not enough. Many social problems such as political polarization, competition in private education, rising suicide rate, youth unemployment, low birth rate, and hate crimes have anxiety as a background.
Increased social anxiety can intensify competition and conflict, which can interfere with social solidarity and lead to decreased social trust[3]. To improve the models proposed above, some studies in Korea propose to complement the model of captured images with monitoring of the anxiety levels of the population using artificial intelligence models that identify the emotional traits of subjects at risk of suicide. If these emotional responses on the Internet and geographic locations can be captured in real-time through machine learning, their time-space distribution could be visualized to observe their current state and changes by geographic region[3].
This, in combination with the behaviors captured by CCTV cameras, could identify at-risk populations and facilitate the work of psychology professionals, reducing suicide rates.
In conclusion, the 4th industrial revolution technologies, which use information from the past to allow machines to learn certain phenomena and behaviors, are not only applicable to optimize and control industrial processes, make financial decisions, etc. but can also be used to address social problems such as anxiety and suicide. These tools can facilitate the initial diagnostic work of mental health professionals and reduce the suicide rate in countries such as South Korea by identifying patterns of behavior in the population. However, they are part of an initial diagnosis, therefore they must be complemented with psychological assistance programs for the identified at-risk individuals to guarantee their effectiveness.
Written by: C.E. Hernán Felipe Puentes Cantor
Reviewed by: Angie Salavarria
Bibliography
[2] Kim, DH., Kim, T.J.Y., Wang, X. et al. Smart Machining Process Using Machine Learning: A Review and Perspective on Machining Industry. Int. J. of Precis. Eng. and Manuf.-Green Tech. 5, 555–568 (2018). https://doi.org/10.1007/s40684-018-0057-y .
https://link.springer.com/article/10.1007/s40684-018-0057-y
[3] Kim Y., Cha J. (2019) Artificial Intelligence Technology and Social Problem Solving. In: Koch F., Yoshikawa A., Wang S., Terano T. (eds) Evolutionary Computing and Artificial Intelligence. GEAR 2018. Communications in Computer and Information Science, vol 999. Springer, Singapore. https://doi.org/10.1007/978-981-13-6936-0_2
https://link.springer.com/chapter/10.1007/978-981-13-6936-0_2
