• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.21-22
• /
• 2023

본 논문에서는 낙상과 비낙상 구별을 위한 분류 모델을 제안한다. 일상생활과 낙상을 구분해 내는 것은 낙상이 발생하기 이전에 감지하고 사고를 예방할 수 있다. 낙상은 일상생활 중 일어나기 쉬우며, 노인들에게는 골절 및 기관 파열 등과 같은 심각한 부상을 초래할 수 있기 때문에 낙상 방지를 위한 낙상과 비낙상 행동의 구분은 중요한 문제이다. 따라서 실시간으로 수집되는 다양한 활동에서의 센서 데이터를 활용하여 낙상과 비낙상의 행동을 구분하였다.

• Journal of Biomedical Engineering Research
• /
• v.24 no.3
• /
• pp.233-239
• /
• 2003

Falling related injuries are categorized as the most serious and common medical problems experienced by the elderly, hip joint fracture, one of the most serious consequences of falling in the elderly, occurs in only about 1% of falling. Nevertheless, hip fracture accounts for a considerable part of the disability, death, and medical costs associated with falling. In this study, we considered the impact angle and displacement rate in falling as another factor affecting femoral strength. Using a fresh-frozen human femur, we developed system to simulate the falling condition and then conducted the experiments changing the impact angle (0$^{\circ}$, 15$^{\circ}$, 30$^{\circ}$) of proximal femur. Also, in order to analyze the relative risk due to falling to normal situation in proximal femur, we did the static test simulating the two-legged stance condition. The results showed that the change in impact angle affected the strain distribution in proximal femur, and that a large deformation in femoral neck than in other sites. Furthermore despite low impact velocity, a large deformation in proximal femur occurred in the impact test and different strain distribution was observed compare to the static case.

• Journal of Korean Academy of Nursing
• /
• v.31 no.3
• /
• pp.443-453
• /
• 2001

Purpose: To identify age, gender, medication, seasons and place of fall, and areas of the fractures from the fall among the hospitalized elderly patients in order to provide the basic data for future fall prevention program for the elderly. Methods: This study was conducted for 106 elderly patients admitted into a university hospital by fractures from the fall during the period from January 1, 1999 to December 31, 1999. Data on the age, gender, medication, season and place of the fall, areas of the fracture were collected based on their medical records. Result: The age range of the subjects were from 60 to 96 years old. The subjects were aged between 60-69 years old 49(46.2%), between 70-79 years old 31(29.2%), between 80-89 years old 24(22.6%), and over 90 years old 2(1.9%). Male patients comprised was 34(28.3%), while female patients comprised 76(71.7%). The fall occurred in Winter most frequently 34(32%). The place of the fall included room 81(76.4%), streets 13(12.3%), bathroom 6(5.7%), stair 4(3.8%), and mountain 2(1.9%). Twenty-two subjects (20.8%) had medication regularly, while 84 subjects (79.2%) had no medication. The areas of the fracture from the fall included upper extremities 20(18.9%) and lower extremities 86(81.1%). Radius fracture (7.5%) was the area where the fracture occurred most frequently in upper extremities and femur fracture (52.8%) was the area where the fracture occurred most frequently in lower extremities. A significant difference was found in the fracture area by age, season and place of the fall (p<.05). No significant difference was found in the fracture area by gender and medication. In all age groups, seasons and places of the fall, occurrence of fracture in lower extremity was significantly higher than that in upper extremity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.2
• /
• pp.401-406
• /
• 2008

Fall event detection is one of the most common problems for elderly people, especially those living alone because falls result in serious injuries such as joint dislocations, fractures, severe head injuries or even death. In order to prevent falls or fall-related injuries, several previous methods based on video sensor showed low fall detection rates in recent years. To improve this problem and outperform the system performance, this paper presented a novel approach for fall event detection in the elderly using a subtraction between successive difference images and temporal templates in real time environment. The proposed algorithm obtained the successful detection rate of 96.43% and the low false positive rate of 3.125% even though the low-quality video sequences are obtained by a USB PC camera sensor. The experimental results have shown very promising performance in terms of high detection rate and low false positive rate.