• Physical Therapy Korea
• /
• v.18 no.1
• /
• pp.9-17
• /
• 2011

The purpose of this study was to assess visual biofeedback's influence on trunk muscles' (EMG) activity and endurance holding time for correct position during whole-body tilt exercise. For the study, we recruited 14 volunteers who showed no symptom of lumbar disease during medical tests. We measured the EMG activity of their rectus abdominis, external abdominal oblique, internal abdominal oblique and erector spinae muscles, and their endurance holding time for correct position during $40^{\circ}$ anterior and posterior whole-body tilt under two conditions: whole-body tilt with and without visual biofeedback. Resistance with gravitational force on the trunk during whole-body tilt was applied by using a device that had a monitor on which the subjects could check their alignment and that sounded an alarm if a subject's alignment collapsed. The study showed an increase in the EMG activity of external abdominal oblique, internal abdominal oblique/rectus abdominis ratio and endurance holding time for correct position during both $40^{\circ}$ anterior and posterior whole-body tilt with visual biofeedback compared with without visual biofeedback (p<.05). We suggest that the whole-body tilt exercise with visual biofeedback could be a beneficial strategy for selectively strengthening the internal abdominal oblique muscle and minimizing the rectus abdominis muscle's activity while maintaining correct alignment during whole-body tilt exercise.

• Journal of the Korean Society of Physical Medicine
• /
• v.8 no.3
• /
• pp.337-342
• /
• 2013

PURPOSE: The Unilateral neglect is characterized by difficulty shifting attention to the side of space opposite the brain lesion and frequently reducing use of contralesional extremities. This study was to identify whether the visual deprivation was responsible for head position on unilateral neglect patient after stroke. METHODS: A patient with left middle cerebral artery infarction participated in the study. We assessed neglect using line bisection and star cancellation test. Patient was instructed to maintain correct alignment of trunk and head in a sit position. We evaluated degree of head lateral tilting and rotation. Then, patient was blocked visual input. Also, we evaluated head position in the same way. RESULTS: He scored 3 points in the line bisection test and 9 points star cancellation test. In postural evaluation, he had deviated posture such as lateral head tilting and rotation. After visual cue deprivation, patient showed different head position which was decreased degree of head tilting and rotation. CONCLUSION: For vertical body orientation, it was used multiple sensory references including the vestibular, somatosensory, and visual system. This finding suggested that abnormal posture of neglect patient could be related to the visual input. It has important clinical implications in terms of understanding the neglect.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2003.05a
• /
• pp.178-179
• /
• 2003

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.123-128
• /
• 2018

The aim of this study was to determine the effects of the action observation and visual feedback on the alignment, pain and function of forward head posture(FHP) and round shoulder(RS). A total of 24 participants with FHP and RSP were randomly assigned to general exercise(GE, n=8), action observation(AO, n=8), and visual feedback(VF, n=8). All subjects were exercised three times a week for four weeks. The groups were assessed for craniovertebral angle(CVA), round shoulder posture(RSP), visual analog scale(VAS), and neck disability index(NDI) before and after exercise, There was a significant difference in CVA in the GE, AO and RSP, VAS and NDI were significantly different in all groups. AO was more effective than GE, VF for VAS. The results of this study suggest that action observation may be effective to improve the FHP and RS.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.229-232
• /
• 2005

In this paper, an image-based "approach-align -grasp" visual servo control design is proposed for the problem of object grasping, which is based on the binocular stand-alone system. The basic idea consists of considering a vision system as a specific sensor dedicated a task and included in a control servo loop, and we perform automatic grasping follows the classical approach of splitting the task into preparation and execution stages. During the execution stage, once the image-based control modeling is established, the control task can be performed automatically. The proposed visual servoing control scheme ensures the convergence of the image-features to desired trajectories by using the Jacobian matrix, which is proved by the Lyapunov stability theory. And we also stress the importance of projective invariant object/gripper alignment. The alignment between two solids in 3-D projective space can be represented with view-invariant, more precisely; it can be easily mapped into an image set-point without any knowledge about the camera parameters. The main feature of this method is that the accuracy associated with the task to be performed is not affected by discrepancies between the Euclidean setups at preparation and at task execution stages. Then according to the projective alignment, the set point can be computed. The robot gripper will move to the desired position with the image-based control law. In this paper we adopt a constant Jacobian online. Such method describe herein integrate vision system, robotics and automatic control to achieve its goal, it overcomes disadvantages of discrepancies between the different Euclidean setups and proposes control law in binocular-stand vision case. The experimental simulation shows that such image-based approach is effective in performing the precise alignment between the robot end-effector and the object.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3383-3397
• /
• 2023

Scene graphs serve as semantic abstractions of images and play a crucial role in enhancing visual comprehension and reasoning. However, the performance of Scene Graph Generation is often compromised when working with biased data in real-world situations. While many existing systems focus on a single stage of learning for both feature extraction and classification, some employ Class-Balancing strategies, such as Re-weighting, Data Resampling, and Transfer Learning from head to tail. In this paper, we propose a novel approach that decouples the feature extraction and classification phases of the scene graph generation process. For feature extraction, we leverage a transformer-based architecture and design an adaptive calibration function specifically for predicate classification. This function enables us to dynamically adjust the classification scores for each predicate category. Additionally, we introduce a Distribution Alignment technique that effectively balances the class distribution after the feature extraction phase reaches a stable state, thereby facilitating the retraining of the classification head. Importantly, our Distribution Alignment strategy is model-independent and does not require additional supervision, making it applicable to a wide range of SGG models. Using the scene graph diagnostic toolkit on Visual Genome and several popular models, we achieved significant improvements over the previous state-of-the-art methods with our model. Compared to the TDE model, our model improved mR@100 by 70.5% for PredCls, by 84.0% for SGCls, and by 97.6% for SGDet tasks.

• International Journal of Highway Engineering
• /
• v.14 no.1
• /
• pp.1-8
• /
• 2012

The horizontal alignment of road is deeply related with the stability of the road and traffic capacity. It is necessary to analyze horizontal alignment of road accurately for efficient maintenance of the road and relevance judgment about the standard. Recently the study on horizontal alignment of road using Lidar data and GPS was concluded, but they were many problem analyzing horizontal alignment radius of curvature in wide area. In this study, the tool which the radius of curvature can evaluate the suitability about "Rules about the Road Structure & Facilities Standards" by using center lines of the road of the digital map tries to implement on GIS. The interface was designed and implemented which can automatically estimate the Road Centerline Horizontal Alignment by using $ESRI^{(R)}$ $ArcObject^{TM}$.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.17 no.6
• /
• pp.529-535
• /
• 2005

This study experimentally examines the air-side performance of spiral finned tube heat exchangers. The effects of fin spacing, fin height, and tube alignment were investigated. Reduction of fin spacing decreased the Colburn j factor. However, the effect of fin height on the Colburn j factor was negligible. An increase of tube row decreased the Nusselt number for both staggered and in-line tube alignments. However, the decrease of the Nusselt number for the in-line tube alignment was much more significant than that of the staggered tube alignment. The average Nusselt number of the staggered tube alignment was larger than that of the in-line tube alignment by $10\%$ when the Reynolds number ranged from 300 to 1700. An empirical correlation of the Nusselt number was developed by using geometric parameters of heat exchanger and correction factors. The correction factor considered the effects of tube alignment and number of tube rows on the heat transfer. The proposed correlation yielded a mean deviation of $4\%$ from the present data.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.10a
• /
• pp.123-128
• /
• 2003

Data acquired from digital Imagery were processed via Delphi, an object-oriented programming language to develop a computer aided program, that allows us to build up the information on road horizontal alignment(BC, EC, R, IP). And the developed program could maximize the visual effects better than traditional programs, because it used many image data. Comparing with data from traditional horizontal alignment extraction programs based on the principle of least square method, the data acquired by horizontal alignment information and kinematic GPS out of the developed road information systems showed the enhanced accuracy of IP value up to about 2m in the direction of X, Y axes, where the accuracy of curve radius(R) becomes enhanced up to about 2.5 m.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.9
• /
• pp.887-893
• /
• 2009

In this paper, a mask-panel alignment robot system is considered for IT industry applications. Two kinds of solutions are suggested which are required in constructing a control system for the alignment robot with actuation redundancy. First, the kinematic solution for the 4PPR parallel positioning mechanism is formulated for an arbitrary initial posture, which relates the mask-panel misalignment in the task space and the desired actuator displacements in the joint space. Secondly, in order to increase the stiffness of the control motion and also to avoid the mechanical lock which may happen due to the redundant actuation, a new synchronous control method is proposed which has the merit of coordinating joint control motions while not losing individual joint control performance. In addition, the engineering process to develop a visual alignment robot system is described with the results of experimental setup and GUI software. Finally, the experimental results demonstrate the effectiveness of the proposed alignment system control methodology and how much beneficial it will be in real industrial applications.