Open Access Open Access  Restricted Access Subscription Access

AI-based safety tips wearables

Chien-Hung Wu,
Hsin-Te Wu,

Abstract


Nowadays, all countries in the world are actively promoting leisure sports, especially water sports, which are actively participated by young people. Although diving in water sports is currently equipped with sufficient equipment, diving needs relevant training to avoid Decompression sickness, or when divers encounter abnormal conditions, they need a coach. Or they cannot be notified through emergency alerts when their partners assist. At present, many divers wear emergency survival equipment, but because the equipment is expensive, and in the event of an accident, divers tend to forget how to operate the equipment. This article is mainly based on machine learning. Safety reminder wearable device, the main features of this article are as follows: 1. This article uses cheap sensors to detect diver status, 2. This article uses AIS combined with GPS for help and the location of the diver, 3. This article uses Bluetooth communication to determine diving Whether the personnel are out of the safety range preset by the instructor. 4. This article uses machine learning to determine whether the sensor detects whether the current state of the diver is dangerous. The lights in the frog mirror pay attention to dangerous situations. This article has verified it through actual experiments. From the experimental results, it can be known that the method proposed in this article is feasible, and the sensors used are relatively cheap, which helps the equipment to be popularized and improved. diver safety.


Citation Format:
Chien-Hung Wu, Hsin-Te Wu, "AI-based safety tips wearables," Communications of the CCISA, vol. 28, no. 1 , pp. 23-30, Feb. 2022.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.





Published by Chinese Cryptology and Information Security Association (CCISA), Taiwan, R.O.C
CCCISA Editorial Office, No.1, Sec. 1, Shennong Rd., Yilan City, Yilan County 260, Taiwan (R.O.C.)
E-mail: ccisa.editor@gmail.com