• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1427-1434
• /
• 2021

In this paper, we propose a psychological state estimation process that computes children's attention and tension in response to training stimuli. Joint attention was adopted as the training stimulus required for behavioral intervention, and the Discrete trial training (DTT) technique was applied as the training protocol. Three types of training stimulation contents are composed to check the user's attention and tension level and provided mounted on a character-shaped tabletop robot. Then, the gaze response to the user's training stimulus is estimated with the vision-based head pose recognition and geometrical calculation model, and the nervous system response is analyzed using the PPG and GSR bio-signals using heart rate variability(HRV) and histogram techniques. Through experiments using robots, it was confirmed that the psychological response of users to training contents on joint attention could be quantified.

• Physical Therapy Korea
• /
• v.28 no.3
• /
• pp.161-167
• /
• 2021

Understanding sciences behind fall-related hip fractures in older adults is important to develop effective interventions for prevention. The aim of this review is to provide biomechanical understanding and prevention strategies of falls and related hip fractures in older adults, in order to guide future research directions from biomechanical perspectives. While most hip fractures are due to a fall, a few of falls are injurious causing hip fractures, and most falls are non-injurious. Fall mechanics are important in determining injurious versus non-injurious falls. Many different biomechanical factors contribute to the risk of hip fracture, and effects of each individual factors are known well. However, combining effects, and correlation and causation among the factors are poorly understood. While fall prevention interventions include exercise, vision correction, vitamin D intake and environment modification, injury prevention strategies include use of hip protectors, compliant flooring and safe landing strategies, vitamin D intake and exercise. While fall risk assessments have well been established, limited efforts have been made for injury risk assessments. Better understanding is necessary on the correlation and causation among factors affecting the risk of falls and related hip fractures in older adults. Development of the hip fracture risk assessment technique is required to establish more efficient intervention models for fall-related hip fractures in older adults.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.1-9
• /
• 2021

Deep learning in computer vision has made accelerated improvement over a short period but large-scale learning data and computing power are still essential that required time-consuming trial and error tasks are involved to derive an optimal network model. In this study, we propose a similar image classification performance improvement method based on CR (Confusion Rate) that considers only the characteristics of the data itself regardless of network optimization or data reinforcement. The proposed method is a technique that improves the performance of the deep learning model by calculating the CRs for images in a dataset with similar characteristics and reflecting it in the weight of the Loss Function. Also, the CR-based recognition method is advantageous for image identification with high similarity because it enables image recognition in consideration of similarity between classes. As a result of applying the proposed method to the Resnet18 model, it showed a performance improvement of 0.22% in HanDB and 3.38% in Animal-10N. The proposed method is expected to be the basis for artificial intelligence research using noisy labeled data accompanying large-scale learning data.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.214-222
• /
• 2022

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.2_1
• /
• pp.177-184
• /
• 2022

The automatic defect sorting function of machinery parts is being introduced to the automation of the manufacturing process. In the final stage of automation of the manufacturing process, it is necessary to apply computer vision rather than human visual judgment to determine whether there is a defect. In this paper, we introduce a deep learning method to improve the classification performance of typical mechanical parts, such as welding parts, galvanized round plugs, and electro galvanized nuts, based on the results of experiments. In the case of poor welding, the method to further increase the depth of layer of the basic deep learning model was effective, and in the case of a circular plug, the surrounding data outside the defective target area affected it, so it could be solved through an appropriate pre-processing technique. Finally, in the case of a nut plated with zinc, since it receives data from multiple cameras due to its three-dimensional structure, it is greatly affected by lighting and has a problem in that it also affects the background image. To solve this problem, methods such as two-dimensional connectivity were applied in the object segmentation preprocessing process. Although the experiments suggested that the proposed methods are effective, most of the provided good/defective images data sets are relatively small, which may cause a learning balance problem of the deep learning model, so we plan to secure more data in the future.

• Archives of Plastic Surgery
• /
• v.49 no.1
• /
• pp.29-33
• /
• 2022

The application of minimal invasive mastectomy has allowed surgeons to perform nipples-paring mastectomy via a shorter, inconspicuous incision under clear vision and with more precise hemostasis. However, it poses new challenges in microsurgical breast reconstruction, such as vascular anastomosis and flap insetting, which are considerably more difficult to perform through the shorter incision on the lateral breast border. We propose an innovative technique of transcutaneous medial fixation sutures to help in flap insetting and creating and maintaining the medial breast border. The sutures are placed after mastectomy and before flap transfer. Three 4-0 nylon suture loops are placed transcutaneously and into the pocket at the markings of the preferred lower medial border of the reconstructed breast. After microvascular anastomosis and temporary shaping of the flap on top of the mastectomy skin, the three corresponding points for the sutures are identified. The three nylon loops are then sutured to the dermis of the corresponding medial point of the flap. The flap is placed into the pocket by a simultaneous gentle pull on the three sutures and a combined lateral push. The stitches are then tied and buried after completion of flap inset.

• The Journal of Korean Academy of Orthopedic Manual Physical Therapy
• /
• v.28 no.2
• /
• pp.35-44
• /
• 2022

Background: This study aimed to compare the effects of the Mulligan mobilization with movement and McKenzie exercise after applying conservative physical therapy to patients with knee pain. Methods: Patients were randomly allocatied into two groups: the Mulligan mobilization with movement (10 subjects) and the McKenzie technique (10 subjects). Each group was givenr conservative physical therapy and manual therapy sessions, three times week, for four weeks. The pain intensity was measured using the visual analogue scale (VAS). The cervical range of motion (ROM) was measured with a goniometer. Balance was measured using the modified Berg balance scale (BBS). Results: After four weeks of therapy, VAS (p<.05) decreased significantly, and ROM and balance increased siginficantly in both groups(p<.05). There was a significant improvement in knee extension (p<.05) in the McKenzie group compared to the Mulligan group. No intergroup differences were found with respect to the knee flex, VAS, and BBS (p>.05). Conclusion: The McKenzie exercises are more effective than Mulligan mobilization with movement for improving knee extension. Both interventions have the same effects on pain relief, in increasing knee flexion ROM and improving balance in patients with knee pain.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.109-115
• /
• 2022

The CNN (Convolution Neural Network) algorithm which combines a deep learning technique, and a computer vision technology, makes image classification feasible with the high-performance computing system. In this thesis, the CNN algorithm is applied to the classification problem, by using a typical deep learning framework of TensorFlow and machine learning techniques. The data set required for supervised learning is generated with the same type of bolts. some of which have undamaged threads, but others have damaged threads. The learning model with less quantity data showed good classification performance on detecting damage in a bolt image. Additionally, the model performance is reviewed by altering the quantity of convolution layers, or applying selectively the over and under fitting alleviation algorithm.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.487-498
• /
• 2022

Depth map is an image that contains distance information in 3D space on a 2D plane and is used in various 3D vision tasks. Many existing depth estimation studies mainly use narrow FoV images, in which a significant portion of the entire scene is lost. In this paper, we propose a technique for generating 360° omnidirectional RGBD images from a sparse set of narrow FoV images. The proposed generative adversarial network based image generation model estimates the relative FoV for the entire panoramic image from a small number of non-overlapping images and produces a 360° RGB and depth image simultaneously. In addition, it shows improved performance by configuring a network reflecting the spherical characteristics of the 360° image.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.351-363
• /
• 2023

Visual structural inspections are an inseparable part of post-earthquake damage assessments. With unmanned aerial vehicles (UAVs) establishing a new frontier in visual inspections, there are major computational challenges in processing the collected massive amounts of high-resolution visual data. We propose twin deep learning models that can provide accurate high-resolution structural components and damage segmentation masks efficiently. The traditional approach to cope with high memory computational demands is to either uniformly downsample the raw images at the price of losing fine local details or cropping smaller parts of the images leading to a loss of global contextual information. Therefore, our twin models comprising Trainable Resizing for high-resolution Segmentation Network (TRS-Net) and DmgFormer approaches the global and local semantics from different perspectives. TRS-Net is a compound, high-resolution segmentation architecture equipped with learnable downsampler and upsampler modules to minimize information loss for optimal performance and efficiency. DmgFormer utilizes a transformer backbone and a convolutional decoder head with skip connections on a grid of crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost performance further and reduce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on the 3D physics-based graphics models (PBGMs) synthetic environments in the QuakeCity dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling). The models were developed as part of the 2^nd International Competition for Structural Health Monitoring.