• Journal of Auto-vehicle Safety Association
• /
• v.9 no.3
• /
• pp.31-38
• /
• 2017

For years, Q1.5 (anthropomorphic test device for 1.5 years old infant) and Q3 (anthropomorphic test device for 3 years old infant) dummy protection has been improved considerably by the effort of EuroNCAP. ISOFIX strength of vehicle structure has increased and many child occupant protection tests have made child restraint system (hereafter CRS) optimized for child safety. However, from 2016, EuroNCAP changed the dummy which is used for the child occupant protection from Q1.5/Q3 to Q6/Q10 and these were also adopted in KNCAP from 2017. Therefore, a new method is required to secure the safety for older children In this research, child dummies were tested by using adult safety systems, and the different results from each adult restraint system were compared. Finally, dummies were tested with the CRS harness belt commonly used for infants, which has yielded significant result. In this research, mid-sized sedan and small SUV were used for the test. The researchers of this paper performed sled tests to correlate between the different adult safety belt system and child injury. Following the sled test, an actual vehicle test was conducted to gather the injury data of Q-dummy with the CRS harness belts. This paper will show the advantages of applying a pre-tensioner in the second row for child protection and the necessity of CRS which has its own harness belts to improve safety for older children.

• Journal of the Institute of Convergence Signal Processing
• /
• v.16 no.1
• /
• pp.15-21
• /
• 2015

In this paper, a behavior notification system of the harness of a guide dog is implemented for a blind person to get helps for environmental and situational awareness while walking with the guide dog. IMU modules is attached on the guide dog's harness saddle and the acceleration sensor belt is mounted on its thigh. Gait estimation and behavior judgement are performed by recording and analyzing the outputs of the sensors. Performance analysis for seven different kinds of behaviors has been done. The seven different behaviors, which the guide dog recognizes, are descending stairs, climbing stairs, uphill, downhill, stop, flat road, and selective disobedience. Results for the performance analysis show that the average success rate of the behavior rule estimation of harness of the guide dog is 92.78% and the behavior notification system can be effectively used in real situations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.726-727
• /
• 2013

건설현장에서 가장 빈번하게 발생하는 추락사고는 작업자의 부주의와 안전장구의 불량으로 발생한다. 추락사고 예방을 위해 의무적으로 착용해야 하는 종래의 안전대는 수동적인 방식이기 때문에 사고 예방에 한계가 있다. 본 연구는 이러한 문제를 해결하기 위한 일환으로서 종래의 하네스식 안전대에 상황인식센서와 USN 등 ICT융합기술을 접목한 새로운 안전대시스템 개발 방안을 마련하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.2
• /
• pp.63-70
• /
• 2018

Safety management agent manages the risk behavior of the worker with the naked eye, but there is a real difficulty for one the agent to manage all the workers. In this paper, IoT device is attached to a harness safety belt that a worker wears to solve this problem, and behavior data is upload to the cloud in real time. We analyze the upload data through the deep learning and analyze the risk behavior of the worker. When the analysis result is judged to be dangerous behavior, we designed and implemented a system that informs the manager through monitoring application. In order to confirm that the risk behavior analysis through the deep learning is normally performed, the data values of 4 behaviors (walking, running, standing and sitting) were collected from IMU sensor for 60 minutes and learned through Tensorflow, Inception model. In order to verify the accuracy of the proposed system, we conducted inference experiments five times for each of the four behaviors, and confirmed the accuracy of the inference result to be 96.0%.