• Smart Structures and Systems
• /
• v.12 no.6
• /
• pp.661-678
• /
• 2013

In this paper, a wireless sensing system for structural field evaluation and rating of bridges is presented. The system uses a wireless platform integrated with traditional analogue sensors including strain gages and accelerometers along with the operating software. A wireless vehicle position indicator is developed using a tri-axial accelerometer node that is mounted on the test vehicle, and was used for identifying the moving truck position during load testing. The developed software is capable of calculating the theoretical bridge rating factors based on AASHTO Load and Resistance Factor Rating specifications, and automatically produces the field adjustment factor through load testing data. The sensing system along with its application in bridge deck rating was successfully demonstrated on the Evansville Bridge in West Virginia. A finite element model was conducted for the test bridge, and was used to calculate the load distribution factors of the bridge deck after verifying its results using field data. A confirmation field test was conducted on the same bridge and its results varied by only 3% from the first test. The proposed wireless sensing system proved to be a reliable tool that overcomes multiple drawbacks of conventional wired sensing platforms designed for structural load evaluation of bridges.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.523-528
• /
• 2020

With a widespread of sensor-rich mobile devices, the analysis of human activities becomes more general and simpler than ever before. In this paper, we propose two deep neural networks that efficiently and accurately perform human activity recognition (HAR) using tri-axial accelerometers. In combination with powerful modern deep learning techniques like batch normalization and LSTM networks, our model outperforms baseline approaches and establishes state-of-the-art results on WISDM dataset.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.4
• /
• pp.781-788
• /
• 2013

In this paper, we introduce a quadruped robot-based alarm system for monitoring the emergency situation due to falling in the elderly. Quadruped robot includes the FPGA Board(Field Programmable Gate Array) applying a red-color tracking algorithm. To detect a falling of the elderly, a sensor node is worn on chest and accelerations and angular velocities measured by the sensor node are transferred to quadruped robot, and then the emergency signal is transmitted to manager if a fall is detected. Manager controls the robot and then he judges the situation by monitoring the real-time images transmitted from the robot. If emergency situation is decided by the manager, he calls 119. When the fall detection system using only sensor nodes is used, sensitivity of 100% and specificity of 98.98% were measured. Using the combination of the fall detection system and portable camera (robot), the emergency situation was detected to 100 %.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.8
• /
• pp.1901-1906
• /
• 2010

This classification of walking patterns is important and many kinds of applications. Therefore, we attempted to classify walking on level ground from slow walking to fast walking using a waist acceleration signal. A tri-axial accelerometer was fixed to the subject's waist and the three acceleration signals were recorded by bluetooth module at a sampling rate of 100 Hz eleven healthy. The data were analyzed using discrete wavelet transform. Walking patterns were classified using two parameters; One was the ratio between the power of wavelet coefficients which were corresponded to locomotion and total power in the anteroposterior direction (RPA). The other was the ratio between root mean square of wavelet coefficients at the anteroposterior direction and that at the vertical direction(RAV). Slow walking could be distinguished by the smallest value in RPA from other walking pattern. Fast walking could be discriminated from level walking using RAV. It was possible to classify the walking pattern using acceleration signal in healthy people.

• Physical Therapy Korea
• /
• v.25 no.4
• /
• pp.9-18
• /
• 2018

Background: Leg length discrepancy (LLD) leads to many musculoskeletal disorders and affects daily activities such as walking. In the majority of the population, mild LLD is a common condition. Nevertheless, it is still controversy among researchers and clinicians on the effects of mild LLD during gait, and available studies have largely overlooked this issue. Objects: The purpose of the present study is to investigate the effects of mild LLD on the gait parameters and trunk acceleration. Methods: A total of 15 female and male participants with no evidence of LLD of >.5 ㎝ participated in the present study. All participants walked under the following two conditions: (1) The non-LLD condition, where the participants walked in shoes of the same heel height; (2) A mild LLD condition induced by wearing a 1.5 ㎝ higher heel on the right shoe. The GAITRite system and tri-axial accelerometer were used to measure gait parameters and trunk acceleration. To compare the variation of each variable, a paired t-test was performed. Results: Compared to the non-LLD condition, step time and swing phase were significantly increased in the mild LLD condition, while stance phase, single support phase, and double support phase significantly decreased in the short limb (p<.05). In the long limb of the mild LLD condition, single support phase significantly increased, while swing phase significantly decreased (p<.05). Furthermore, significant decrease in the gait velocity and cadence in the mild LLD condition were observed (p<.05). In the comparison between both limbs in the mild LLD condition, the step time and swing phase of the short limb significantly increased compared with the long limb, while step length, stance phase, and single support phase of the long limb significantly increased compared with the short limb (p<.05). Additionally, trunk acceleration of all directions (anterior-posterior, medial-lateral, vertical) significantly increased in the mild LLD condition (p<.05). Conclusion: The results of the present study demonstrate that mild LLD causes altered and asymmetrical gait patterns and affects the trunk, resulting in inefficient gait. Therefore, mild LLD should not be overlooked and requires adequate treatment.