• International Journal of Computer Science & Network Security
• /
• v.21 no.4
• /
• pp.131-139
• /
• 2021

In current time, anomaly detection is the primary concern of the administrative authorities. Suspicious activity identification is shifting from a human operator to a machine-assisted monitoring in order to assist the human operator and react to an unexpected incident quickly. These automatic surveillance systems face many challenges due to the intrinsic complex characteristics of video sequences and foreground human motion patterns. In this paper, we propose a novel approach to detect anomalous human activity using a hybrid approach of statistical model and Genetic Programming. The feature-set of local motion patterns is generated by a statistical model from the video data in an unsupervised way. This features set is inserted to an enhanced Genetic Programming based classifier to classify normal and abnormal patterns. The experiments are performed using publicly available benchmark datasets under different real-life scenarios. Results show that the proposed methodology is capable to detect and locate the anomalous activity in the real time. The accuracy of the proposed scheme exceeds those of the existing state of the art in term of anomalous activity detection.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.10
• /
• pp.1095-1102
• /
• 2014

In this paper, We proposed the approach of GPU and motion vector to analysis the Human activity in real-time surveillance system. The most important part, that is detect blob(human) in the foreground. We use to detect Adaptive Gaussian Mixture, Weighted subtraction image for salient motion and motion vector. And then, We use motion vector for human activity analysis. In this paper, the activities of human recognize and classified such as meta-classes like this {Active, Inactive}, {Position Moving, Fixed Moving}, {Walking, Running}. We created approximately 300 conditions for the simulation. As a result, We showed a high success rate about 86~98%. The results also showed that the high resolution experiment by the proposed GPU-based method was over 10 times faster than the cpu-based method.

• Journal of Korea Multimedia Society
• /
• v.14 no.8
• /
• pp.992-999
• /
• 2011

This paper proposed a human body posture recognition program based on haar-like feature and hand activity detection. Its distinguishing features are the combination of face detection and motion detection. Firstly, the program uses the haar-like feature face detection to receive the location of human face. The haar-like feature is provided with the advantages of speed. It means the less amount of calculation the haar-like feature can exclude a large number of interference, and it can discriminate human face more accurately, and achieve the face position. Then the program uses the frame subtraction to achieve the position of human body motion. This method is provided with good performance of the motion detection. Afterwards, the program recognises the human body motion by calculating the relationship of the face position with the position of human body motion contour. By the test, we know that the recognition rate of this algorithm is more than 92%. The results show that, this algorithm can achieve the result quickly, and guarantee the exactitude of the result.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.9
• /
• pp.825-831
• /
• 2015

In this paper, capture motion and visual information from a virtual reality luge simulator to analyze muscular activity in the lower limbs. The Luge Simulator consists of a motion platform with a pneumatic module for weight distribution. We recruited luge athletes and healthy subjects and made real-time surface EMG measurements to estimate the muscular activity in the lower limbs according to the motion protocol of a simulator, and a test was conducted for each subject. The results indicated that the rectus femoris had the highest muscular activity according to the level of the slope and velocity of the luge. The soleus muscle showed a high level of activity during a turn in the luge according to the direction. We found that the development of a virtual reality sports simulator based on physical reaction results could bring positive effects to optimize reality and human cenesthesia.

• Physical Therapy Rehabilitation Science
• /
• v.11 no.4
• /
• pp.400-408
• /
• 2022

Objective: The purpose of this study is to compare EMG activity during horticulture motion and upper limb rehabilitation motion, to confirm whether horticulture motion is suitable for upper extremity rehabilitation of hemiparesis. Design: Three-group cross-sectional design. Methods: The 45 subjects were divided into three groups: hemiparesis (n=15), elderly (n=15) and healthy (n=15). We have recorded EMG signals of six upper limb muscles Upper trapezius (UT), Middle deltoid (MD), Anterior deltoid (AD), Biceps brachii (BB), Triceps brachii (TB), Brachioradialis (BR) during horticultural motions and three upper limb rehabilitative motions. The dependent variables were peak EMG, integral EMG, co-contraction ratio. A two-way repeated measures ANOVA was used to compare the horticultural motion and rehabilitation motion of the three groups. Results: The peak EMG was significantly different in MD, AD, BB, TB according to the motion(p<0.05), and the UT, BB were significant differences according to the group(p<0.05). The integral EMG was significantly different in MD, AD, BB, TB, BR according to the motion(p<0.05), and the BB were significant differences according to the group(p<0.05). The co-contraction ratio was significantly different in TB/BB according of the motion, and there was no difference between the groups. Conclusions: As a result of this study, horticultural motion alone was insufficient for upper arm rehabilitation, and horticultural motion alone was insufficient to induce continuous activity of the forearm.

• Physical Therapy Korea
• /
• v.13 no.1
• /
• pp.54-60
• /
• 2006

This study aimed to compare movement patterns of shoulder joints between the right and left symmetry in stroke patients and control subjects. This study proposes use of the voluntary response index (VRI) calculated from quantitative analysis of surface electromyographic (sEMG) and motion data recorded during voluntary movement as a feeding task. The VRI is comprised of two numeric values, one derived from the total muscle activity recorded for the voluntary motor task (magnitude), and the other from the sEMG distribution across the recorded muscles with the similarity index (SI). Five stroke patients and five age-matched healthy controls were recruited. Feeding motion was performed using the provided spoon five times with rests taken on a chair in between tasks. EMG data were digitized and analyzed on the basis of the root mean square (RMS) envelope of activity. The average amplitude of responses was calculated. Responsiveness and clinically meaningful levels of discrimination between stroke patients and control for EMG magnitude and SI were determined. The similarity index of the results from two successive examinations of both sides apart for stroke patients and control subjects were .86 and .95 in motion analysis and .84 and .99 in electromyographic analysis. The SI of sEMG data and motion data was significantly correlated in stroke patients. The data suggest that SI is a sensitive program for comparing and analyzing the symmetry of muscle activity and motion in both sides. This analysis method has a clinical value in grading muscular activity and movement impairment after brain injury.

• PNF and Movement
• /
• v.18 no.3
• /
• pp.323-331
• /
• 2020

Purpose: This study was conducted to determine the effects of motion taping on muscle activity and the WOMAC in a rehabilitation exercise program for elderly women with knee joint osteoarthritis. Methods: The subjects were 28 elderly women aged over 65 years with knee joint osteoarthritis. The subjects were divided into two groups: one experimental and one control group. During the study period, a total of 26 patients completed the experiment, with one drop each from the experimental group and control group. The experimental group applied motion taping and conducted a rehabilitation exercise program. The control group experienced a rehabilitation exercise program without motion taping. The rehabilitation exercise program consisted of warm-up exercises, maximum isometric exercises, the range of motion of the joints, and leg stretching exercises. The intervention was conducted three times a week for six weeks. To investigate the effects of the intervention, muscle activity and the WOMAC were measured. The WOMAC is a tool that can be used to evaluate the pain, stiffness, and physical function of osteoarthritis patients; it has 29 items in three areas. Results: The change in muscle activity according to the intervention showed a statistically significant increase in both the experimental group and control group. The WOMAC also showed statistically significant changes in terms of pain, stiffness, and physical function in both the experimental and control groups. The experimental group showed a greater functional improvement than the control group. Conclusion: For older women with osteoarthritis of the knee, a rehabilitation exercise program is a good intervention. When motion-taping is applied, it is considered to be an intervention program that can be expected to have a better effect on knee joint osteoarthritis.

• Journal of International Academy of Physical Therapy Research
• /
• v.3 no.1
• /
• pp.364-369
• /
• 2012

The purpose of this study was to analyze lower limb muscle activity and 3D motion analysis according to change foot arch height during walking. We selected 9 young and healthy people who have been normal foot. And we selected 7 young and healthy people who have been flatfoot. So, people were divided into 2 groups and walked platform during 2 minutes twice for checked by 3D motion analysis. These data were characterized by EMG measurements of three muscles( tibialis anterior, medial and lateral gastrocnemius) while they were walking. The collected data were analyzed by Independent t test using the SPSS statistics program(Ver 12.0). In foot arch change, there were no significant difference in three muscles 3D motion analysis also found that there were no significant difference in joint angles. In this study was to analyze lower limb muscle activity and 3D motion analysis according to change foot arch, but there were no significant difference in 6 muscles neither joint angles.

• 한국체육학회지인문사회과학편
• /
• v.54 no.1
• /
• pp.515-525
• /
• 2015

The purpose of this study was to compare muscular activities according to the mastery of Taekwondo kicking motions with the subjects of 8 demonstration team members and 8 undergraduates in Taekwondo major at University. The muscles mainly used for Taekwondo's front kick, tornado kick, or turning hook kick are total 8 trunk muscles and 8 lower limb muscles of the kicking foot as well as the supporting foot. Analyzing the muscular activities of those areas comparatively, the study has reached the following results. At the front kick, non-experts showed higher lower abdominal muscle, biceps thigh muscle activity of the kicking foot and lateral gastrocnemius muscle activity of the supporting foot but lower 2 spinals muscular activity than experts. At the tornado kick (or turning kick), in the turning motion, experts indicated higher activity in biceps muscle of thigh and spinalis than non-experts whereas in the kicking motion, they didn't show the difference between groups except biceps thigh muscle activity. At the turning hook kick, non-experts indicated higher lateral gastrocnemius muscle activity of the kicking foot and quadricpes femoris muscle activity of supporting foot muscular activity than experts. In summary, experts tend to use their trunk in the turning motion for rapid turning and show rather low muscular activity of their kicking foot. However, non-experts indicate high muscular activity in their kicking foot and supporting foot, which means to maintain balance in the kicking motion, they tend to make use of their lower limb more than trunk muscle, and it leads to an inefficient motion.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.443-452
• /
• 2020

Worker's awkward postures and unreasonable physical load can be corrected by monitoring construction activities, thereby increasing the safety and productivity of construction workers and projects. However, manual identification is time-consuming and contains high human variance. In this regard, an automated activity recognition system based on inertial measurement unit can help in rapidly and precisely collecting motion data. With the acceleration data, the machine learning algorithm will be used to train classifiers for automatically categorizing activities. However, input acceleration data are extracted either from designed experiments or simple construction work in previous studies. Thus, collected data series are discontinuous and activity categories are insufficient for real construction circumstances. This study aims to collect acceleration data during long-term continuous work in a construction project and validate the feasibility of activity recognition algorithm with the continuous motion data. The data collection covers two different workers performing formwork at the same site. An accelerator, as well as portable camera, is attached to the worker during the entire working session for simultaneously recording motion data and working activity. The supervised machine learning-based models are trained to classify activity in hierarchical levels, which reaches a 96.9% testing accuracy of recognizing rest and work and 85.6% testing accuracy of identifying stationary, traveling, and rebar installation actions.