• Journal of Sensor Science and Technology
• /
• v.31 no.2
• /
• pp.96-101
• /
• 2022

As the elderly population gradually increases, the risk of fatal fall accidents among the elderly is increasing. One way to cope with a fall accident is to determine the fall direction before impact using a wearable inertial measurement unit (IMU). In this context, a previous study proposed a method of classifying fall directions using a support vector machine with sensor velocity, acceleration, and tilt angle as input parameters. However, in this method, the IMU signals are processed through several processes, including a Kalman filter and the integration of acceleration, which involves a large amount of computation and error factors. Therefore, this paper proposes a machine learning-based method that classifies the fall direction before impact using IMU raw signals rather than processed data. In this study, we investigated the effects of the following two factors on the classification performance: (1) the usage of processed/raw signals and (2) the selection of machine learning techniques. First, as a result of comparing the processed/raw signals, the difference in sensitivities between the two methods was within 5%, indicating an equivalent level of classification performance. Second, as a result of comparing six machine learning techniques, K-nearest neighbor and naive Bayes exhibited excellent performance with a sensitivity of 86.0% and 84.1%, respectively.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.2
• /
• pp.31-37
• /
• 2016

Falling situations are extremely critical events for the elderly person who requires timely and adequate emergency service. For the case of emergency, the information of falling and its direction can be used as an important information for the first aid treatment of the injured person. In this paper, a falling detection system which can pinpoint the falling event with the falling direction is implemented. In order to detect the fall situation, a single gyroscope (MPU-6050) is used in the developed system. The fall detection algorithm that can classify 8 different fall directions such as front, back, left, right and in between falls is proposed. The direction of the fall is decided by examining the acceleration values of X and Y directions of the sensor. It is shown that the proposed algorithm successfully detects the falling event and the falling direction with probability of 97% for a selected value of acceleration threshold.

• Journal of Sensor Science and Technology
• /
• v.24 no.1
• /
• pp.47-53
• /
• 2015

Fall-related injuries in elderly people are a major health care problem. This paper introduces determination of fall direction before impact using support vector machine (SVM). Once a falling phase is detected, dynamic characteristic parameters measured by the accelerometer and gyroscope and then processed by a Kalman filter are used in the SVM to determine the fall directions, i.e., forward (F), backward (B), rightward (R), and leftward (L). This paper compares the determination sensitivities according to the selected parameters for the SVM (velocities, tilt angles, vs. accelerations) and sensor attachment locations (waist vs. chest) with regards to the binary classification (i.e., F vs. B and R vs. L) and the multi-class classification (i.e., F, B, R, vs. L). Based on the velocity of waist which was superior to other parameters, the SVM in the binary case achieved 100% sensitivities for both F vs. B and R vs. L, while the SVM in the multi-class case achieved the sensitivities of F 93.8%, B 91.3%, R 62.3%, and L 63.6%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.5
• /
• pp.1564-1572
• /
• 2010

In this study, the falls detection and direction classification system was implemented using 3-axial acceleration signal. The acceleration signals were acquired from the 3-axial accelerometer(MMA7260Q, Freescale, USA), and then transmitted to the computer through USB interface. The implemented system can detect falls using the newly proposed algorithm, and also classify the direction of falls using fuzzy classifier. The 6 subjects was selected for experiment and the accelerometer was attached on each subject's chest. Each subject walked in normal pace for 5 seconds, and then the fall down according to the four direction(front_fall, back_fall, left_fall and right_fall) during at least 2 second. The falls was easily detect using the newly proposed algorithm in this study. The acquired signals were analyzed after 1 second from generating falls. The fuzzy classifier was used to classify the direction of falls. The mean value of the falls detection rate was 94.79%. The classifier rate according to falls direction were 95.83% in case of front falls, 100% incase of back falls, 87.5% in case of left falls, and 95.83% in case of right falls.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.10a
• /
• pp.447-448
• /
• 2006

• Physical Therapy Korea
• /
• v.28 no.1
• /
• pp.84-91
• /
• 2021

Background: A hip fracture may occur spontaneously prior to the hip impact, due to the muscle pulling force exceeding the strength of the femur. Objects: We conducted falling experiments with humans to measure the activity of the hip muscles, and to examine how this was affected by the fall type. Methods: Eighteen individuals fell and landed sideways on a mat, by mimicking video-captured real-life older adults' falls. Falling trials were acquired with three fall directions: forward, backward, or sideways, and with three knee positions at the time of hip impact, where the landing side knee was free of constraint, or contacted the mat or the contralateral knee. During falls, the activities of the iliopsoas (Ilio), gluteus medius (Gmed), gluteus maximus (Gmax) and adductor longus (ADDL) muscles were recorded. Outcome variables included the time to onset, activity at the time of hip impact, and timing of the peak activity with respect to the time of hip impact. Results: For Ilio, Gmed, Gmax, and ADDL, respectively, EMG onset averaged 292, 304, 350, and 248 ms after fall initiation. Timing of the peak activity averaged 106, 96, 84, and 180 ms prior to the hip impact, and activity at the time of hip impact averaged 72.3, 45.2, 64.3, and 63.4% of the peak activity. Furthermore, the outcome variables were associated with fall direction and/or knee position in all but the iliopsoas muscle. Conclusion: Our results provide insights on the hip muscle activation during a fall, which may help to understand the potential injury mechanism of the spontaneous hip fracture.

• Physical Therapy Korea
• /
• v.30 no.1
• /
• pp.78-85
• /
• 2023

Background: Despite fall prevention strategies suggested by researchers, falls are still a major health concern in older adults. Understanding factors that differentiate successful versus unsuccessful balance recovery may help improve the prevention strategies. Objects: The purpose of this review was to identify biomechanical factors that differentiate successful versus unsuccessful balance recovery in the event of a fall. Methods: The literature was searched through Google Scholar and PubMed. The following keywords were used: 'falls,' 'protective response,' 'protective strategy,' 'automated postural response,' 'slips,' 'trips,' 'stepping strategy,' 'muscle activity,' 'balance recovery,' 'successful balance recovery,' and 'failed balance recovery.' Results: A total of 64 articles were found and reviewed. Most of studies included in this review suggested that kinematics during a fall was important to recover balance successfully. To be successful, appropriate movements were required, which governed by several things depending on the direction and characteristics of the fall. Studies also suggested that lower limb muscle activity and joint moments were important for successful balance recovery. Other factors associated with successful balance recovery included fall direction, age, appropriate protective strategy, overall health, comorbidity, gait speed, sex and anticipation of the fall. Conclusion: This review discusses biomechanical factors related to successful versus unsuccessful balance recovery to help understand falls. Our review should help guide future research, or improve prevention strategies in the area of fall and injuries in older adults.

• The Korean Journal of Rehabilitation Nursing
• /
• v.1 no.1
• /
• pp.43-50
• /
• 1998

The literature review for fall in the elderly has been done for the better quality of life of increasing elderly people toward 21 st century. Because 30 to 50% of over sixty five years old persons have experiences of fall, five percent of the fallen have trauma such as bone fracture requiring hospitalization and three quarter of people who die as fall are over 65 year old, fall is important health problem of them. There are very little societal interest in and research related to fall. Therefore, among recent foreign and our literatures studying literature review of frequency of fall, risk factors and assessing method for tall, and the management of fall prevention program, I would like to find research direction. Conclusivelly, we should study extensively the survey of the elderly's fall and on the basis of it. developing fall prevention program, promote the elderly's health through fall prevention.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.2
• /
• pp.336-342
• /
• 2015

Fall-related injuries are the most common cause of accidental death for the elderly and the most frequent work-related injuries in construction sites. Due to the growing popularity of smartphones, there has been a number of research work related to the use of sensors embedded in the smartphone for fall detection. Falls can be detected easily by measuring the magnitude and direction of acceleration vectors. In general, the direction of the acceleration vector does not show the object movement, but the velocity vector directly indicates the tangential direction in which the object is moving. In this paper, we proposed a new method for computing the fall direction based on the characteristics of the velocity vector extracted from the accelerometer.

• Proceedings of KOSOMES biannual meeting
• /
• 2003.11a
• /
• pp.163-166
• /
• 2003

The seasonal mean wind direction and wind speed in a greater coasting area are investigated using the ECMWF(European Centre for Medium-Range Weather Forecasts) data for 11 years from 1985 to 1995. In winter, the main wind direction in Korea and vicinity, Taiwan and vicinity, and the North Pacific Ocean of middle latitudes is a northwesterly wind, northeasterly wind, and westerly wind respectively. The wind speed is strongest in the East China Sea, the South China Sea, and the North Pacific Ocean of low latitudes(Beaufort wind scale 5-6). A distribution pattern of wind direction in spring and fall is similar to that in winter. Seasonal mean wind speed is strongest in winter and the next is fall. The wind speed in summer is generally weak. However, that in the Indochina and vicinity is strong by the influence of Asian monsoon.