• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.554-562
• /
• 2023

This research offers a sports video action recognition approach based on the fish swarm algorithm in light of the low accuracy of existing sports video action recognition methods. A modified fish swarm algorithm is proposed to construct invariant features and decrease the dimension of features. Based on this algorithm, local features and global features can be classified. The experimental findings on the typical sports action data set demonstrate that the key details of sports action can be successfully retained by the dimensionality-reduced fusion invariant characteristics. According to this research, the average recognition time of the proposed method for walking, running, squatting, sitting, and bending is less than 326 seconds, and the average recognition rate is higher than 94%. This proves that this method can significantly improve the performance and efficiency of online sports video motion recognition.

• Korean Journal of Applied Biomechanics
• /
• v.25 no.4
• /
• pp.465-474
• /
• 2015

Objective : A study and development of Korean Bobsleigh athletes's shoe which considers their physical condition has yet to be completed. So this study examines the effects of running shoes used by athletes based on plantar pressure and sprint time in order to provide raw data for the development of bobsleigh shoes suitable for Koreans. Method : The study selected seven bobsleigh athletes as subjects and selected three pairs of spiked running shoes from three companies, which will be referred to as Company N (Type A), Company A (Type B), and Company M (Type C). To analyze sprint time and plantar pressure for each shoe, the subject of the study were instructed to wear the selected shoes and to drag a sled at maximum sprint for 15 meters for 15 meters for in each condition that would be in real bobsleigh competitions. Results : The average sprint intervals for each athlete in each pair of shoes revealed Type C produce the fastest sprint in the order of Type C < Type A< Type B. Shoe Type C also had the largest contact area in order of Type C > Type B > Type A (p<.01). None of the three shoe types seem to yield a distinct advantage in terms of maximum average pressure or maximum pressure. Conclusion : In the future, functional analysis should be carried out by comparing the material properties, hardness, and toe spring of shoes based on the Type C shoe from Company M in order to develop bobsleigh shoes suitable for Koreans.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.8
• /
• pp.1179-1186
• /
• 2013

In this paper, an efficient vehicle detection and tracking algorithm for detection incident in tunnel is proposed. The proposed algorithm consists of three steps. The first one is a step for background estimates, low computational complexity and memory consumption Running Gaussian Average (RGA) is used. The second step is vehicle detection step, Adaboost algorithm is applied to this step. In order to reduce false detection from a relatively remote location of the vehicles, local features according to height of vehicles are used to detect vehicles. If the local features of an object are more than the threshold value, the object is classified as a vehicle. The last step is a vehicle tracking step, the Kalman filter is applied to track moving objects. Through computer simulations, the proposed algorithm was found that useful to detect and track vehicles in the tunnel.

• Journal of Biosystems Engineering
• /
• v.34 no.6
• /
• pp.411-419
• /
• 2009

This study was carried out to develop a shredding-burying machine for application of gramineae green manure crops that were tall and had high biomass yield such as sudan grass and rye. We made a prototype to operate both shredding and burying concurrently to attach at middle-sized tractors. Field tests were performed with the prototype to treat rye and sudan grass. The test results showed that the average cutting length became shorter and the quantity of entwined stem became obviously decreased when the PTO shaft speed was fast and running speed was slow. Also, We found, when the cut stem length became shorter, the burying ratio became more increasing and the PTO power requirement became more decreasing. Working efficiency of the prototype was better than conventional Rotary. The test results for treating rye/sudan grass with prototype showed that average cutting length was 21.2/22.5 cm and burying ratio was 98.4/98.1% when the PTO shaft speed was 1,000/1,000 rpm and running speed was 0.25/0.17 m/s. Also, the working performance of the prototype was 0.79 and 1.14 h/10 a for rye and sudan grass, respectively. Finally, we found that the prototype of shredding-burying machine was better for labor than conventional method that required at least 3 times bigger tractor.

• Fashion & Textile Research Journal
• /
• v.13 no.6
• /
• pp.943-951
• /
• 2011

The purpose of this study is to analyze the physiological effects of non-elastic corset on women's health and pain through measuring the clothing pressure, subjective pressure sensation, blood velocity and metabolism. 5 women in their twenties were picked as our subjects, their average size being 85cm at bust girth, 69 cm at waist girth. With the subjects each wearing a corset, we are testing in artificial environment with a treadmill according to the planned exercise procedures. The average pressure of the corset is 0.938 kPa (maximum 3.006 kPa at 45 degree front bowing), which is 10.2 times higher than the control group, averaging from 9.3 times higher at resting, 11.4 times at walking, 11.1 times at running. The effect of corset pressure on the physiological responses of the body is increased more when exercise than when resting. Clothing pressure increased in the order of the postures: sitting > standing with 45 degree bowing > standing. They experienced a high level of tighten discomfort of 5.6 in the scale of 1.0 to 7.0 due to the high pressure of the corset when resting, after intense exercise the level increased to 6.0, while without corset the level increased 1.7 to 2.2. With corset on, the blood circulation did not increase even though when the body exercised and blood flow became unbalanced making great gaps between both at the right and left finger tips. Perspiration of chest and back decreased 37.3% when wearing corset; 27.5% at resting, 56.7% at walking, 25.8% at running, and 39.0% at recovery. With corset on oxygen consume and metabolism increased 9.0%, 7.9%, respectively, which means the corset makes the body uncomfortable. Lung volume exchange VE decreased almost 4.1~7.3% with corset on and $VCO_2/VO_2$, RER and total volume in lung, VT also decreased too, which means the digestion of stomach and lung function are inhibited due to the high corset pressure.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.29 no.4
• /
• pp.365-374
• /
• 2009

This study was carried out in thoroughbred colts grazed in pasture at summer season of Jeju island, Korea, from June 23 to 29 in 2007. We investigated the behavioral pattern of the thoroughbred colts (n=23) at the age of 3-year-old (n=11) and 1-year-old (n=12). The group behavioral pattern of thoroughbred colts was different according to the age. It was shown that eating 56%, standing 23%, lying 10%, walking 5%, running 2.5% and drinking 3% in the 1-year-old thoroughbred colts group. Especially, it was significantly individual difference (P<0.05) in the average behavioral expression ratio of 1-year-old thoroughbred colts (n=3), which was eating 53%, standing 29%, lying 11%, walking 5%, drinking 1% and running 1%. On the other hand, it was investigated that eating 54%, standing 27%, walking 13%, running and drinking 1.5%, lying 1% in the 3-year-old thoroughbred colts group. Also, the individual behavioral expression ratio of the 3-year-old thoroughbred colts was eating 53%, standing 32%, walking 10%, running and drinking 1%, which was a similar pattern to the result of 1-year-old colts. It is considered that this is the first study regarding a pasturage action of a racehorse produced in Korea. These data cannot be enough, but this data will be based on the production of racehorses and fostered in the management.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.814-818
• /
• 2004

Off-line handwritten character recognition is in difficulty of incomplete preprocessing because it has not dynamic and timing information besides has various handwriting, extreme overlap of the consonant and vowel and many error image of stroke. Consequently off-line handwritten character recognition needs to study about preprocessing of various methods such as binarization and thinning. This paper considers running time of watershed algorithm and the quality of resulting image as preprocessing For off-line handwritten Korean character recognition. So it proposes application of effective watershed algorithm for segmentation of character region and background region in gray level character image and segmentation function for binarization image and segmentation function for binarization by extracted watershed image. Besides it proposes thinning methods which effectively extracts skeleton through conditional test mask considering running time and quality. of skeleton, estimates efficiency of existing methods and this paper's methods as running time and quality. Watershed image conversion uses prewitt operator for gradient image conversion, extracts local minima considering 8-neighborhood pixel. And methods by using difference of mean value is used in region merging step, Converted watershed image by means of this methods separates effectively character region and background region applying to segmentation function. Average execution time on the previous method was 2.16 second and on this paper method was 1.72 second. We prove that this paper's method removed noise effectively with overlap stroke as compared with the previous method.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1405-1411
• /
• 2011

It is very often for the experienced diesel locomotive drivers to identify the proper replacing time for the fuel adjustment tube only based on their experience. Because of that, sometimes the locomotive's fuel is burned out due to the unnecessary torque. Or sometimes, the locomotive does not operate with its accelerating performance because the fuel is not supplied at the appropriate moment. Meanwhile, recent typical auto vehicles provide drivers with the average fuel efficiency and the instant fuel efficiency in real-time. By providing the real time display mentioned above, it is one of the good examples that those drivers, who had driven their cars not properly and used a lot of fuel with their bad driving habits, obtain the efficient driving pattern by continuous educating effect. Similarly, if the diesel locomotive provides the train driver with the optimal driving pattern within a certain driving section, it will be effective for fuel saving. It is possible to make the most effective driving pattern by performing the repeated trial running especially for the railway because the track's operating routes, its grades, and etc are relatively precise. This research analyzes the result data which was obtained by many times trial running on the identical section after equipping the fuel use measuring device to a certain test vehicle, and confirms the fuel saving effect depending on the driving pattern along the test section. At the same time, the research to establish the optimal driving pattern was progressed.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.46-53
• /
• 2020

Gait analysis is an effective clinical tool across a wide range of applications. Recently, inertial measurement units have been extensively utilized for gait analysis. Effective gait analyses require good estimates of heel-strike and toe-off events. Previous studies have focused on the effective device position and type of triaxis direction to detect gait events. This study proposes an effective heel-strike and toe-off detection algorithm using a smart insole with inertial measurement units. This method detects heel-strike and toe-off events through a time-frequency analysis by limiting the range. To assess its performance, gait data for seven healthy male subjects during walking and running were acquired. The proposed heel-strike and toe-off detection algorithm yielded the largest error of 0.03 seconds for running toe-off events, and an average of 0-0.01 seconds for other gait tests. Novel gait analyses could be conducted without suffering from space limitations because gait parameters such as the cadence, stance phase time, swing phase time, single-support time, and double-support time can all be estimated using the proposed heel-strike and toe-off detection algorithm.

• Journal of Biomedical Engineering Research
• /
• v.27 no.6
• /
• pp.301-309
• /
• 2006

The main purpose of this study is to derive a regression equation that predicts the individual differences in activity energy expenditure (AEE) using accelerometer during different types of activity. Two subject groups were recruited separately in time: One is a homogeneous group of 94 healthy young adults with age ranged from $20\sim35$ yrs. The other subject group has a broad spectrum of physical characteristics in terms of age and fat ratio. 226 adolescents and adults of age ranged from $12\sim57$ yrs and fat ratio from $4.1\sim39.7%$ were in the second group. The wireless 3-axis accelerometers were developed and carefully fixed at the waist belt level. Simultaneously the total calorie expenditure was measured by gas analyzer. Each subject performed walking and running at speeds of 1.5, 3.0, 4.5, 6.0, 6.5, 7.5, and 8.5 km/hr. A generalized sensor-independent regression equation for AEE was derived. The regression equation was developed fur walking and running. The regression coefficients were predicted as functions of physical factors-age, gender, height, and weight with multivariable regression analysis. The generalized calorie estimation equation predicts AEE with correlation coefficient of 0.96 and the average accuracy of the accumulated calorie was $89.6{\pm}7.9%$.