• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.323-333
• /
• 2023

Facial expression recognition can aid in the development of fatigue driving detection, teaching quality evaluation, and other fields. In this study, a facial expression recognition method was proposed with a residual masking reconstruction network as its backbone to achieve more efficient expression recognition and classification. The residual layer was used to acquire and capture the information features of the input image, and the masking layer was used for the weight coefficients corresponding to different information features to achieve accurate and effective image analysis for images of different sizes. To further improve the performance of expression analysis, the loss function of the model is optimized from two aspects, feature dimension and data dimension, to enhance the accurate mapping relationship between facial features and emotional labels. The simulation results show that the ROC of the proposed method was maintained above 0.9995, which can accurately distinguish different expressions. The precision was 75.98%, indicating excellent performance of the facial expression recognition model.

• Clinical and Experimental Pediatrics
• /
• v.56 no.6
• /
• pp.235-241
• /
• 2013

Repair of tetralogy of Fallot (TOF) has shown excellent outcomes. However it leaves varying degrees of residual hemodynamic impairment, with severe pulmonary stenosis (PS) and free pulmonary regurgitation (PR) at both ends of the spectrum. Since the 1980s, studies evaluating late outcomes after TOF repair revealed the adverse impacts of residual chronic PR on RV volume and function; thus, a turnaround of operational strategies has occurred from aggressive RV outflow tract (RVOT) reconstruction for complete relief of RVOT obstruction to conservative RVOT reconstruction for limiting PR. This transformation has raised the question of how much residual PS after conservative RVOT reconstruction is acceptable. Besides, as pulmonary valve replacement (PVR) increases in patients with RV deterioration from residual PR, there is concern regarding when it should be performed. Regarding residual PS, several studies revealed that PS in addition to PR was associated with less PR and a small RV volume. This suggests that PS combined with PR makes RV diastolic property to protect against dilatation through RV hypertrophy and supports conservative RVOT enlargement despite residual PS. Also, several studies have revealed the pre-PVR threshold of RV parameters for the normalization of RV volume and function after PVR, and based on these results, the indications for PVR have been revised. Although there is no established strategy, better understanding of RV mechanics, development of new surgical and interventional techniques, and evidence for the effect of PVR on RV reverse remodeling and its late outcome will aid us to optimize the management of TOF.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.4
• /
• pp.308-312
• /
• 2002

To determine the natural frequencies and damping ratios of composite laminated plates, we present an officient modal parameter estimation technique by developing residual spectrum based structural system reconstruction. The modal parameters can be estimated from poles and residues of the system transfer functions, derived from the state space system matrices. From vibration tests on cross-ply and angle-ply composite laminates, the natural frequencies and damping ratios can be estimated using the modal coordinates of the structural dynamic system reconstructed from the experimental frequency response functions. These results are compared with those of finite element analysis and single-degree-of-freedom curve fitting.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.150-150
• /
• 2000

We as modal parameter estimation technique by developing a residual based system reconstruction and using the system matrix coordinate transformation. The modal parameters can be estimated from and residues of the system transfer functions expressed in modal coordinate basis, derived from the state space system matrices. However, for modal parameter estimation of multivariable and order structural systems over broad frequency bands, this non-iterative algorithm gives high accuracy in the natural fre- and damping ratios. From vibration tests on cross-ply and angle-ply composite laminates, the natural frequencies and damping ratios on be estimated using tile coordinates of the structural system reconstructed fro the experimental frequency response. These results are compared with those of finite element analysis and single-degree-of-freedom curve-fitting.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.527-527
• /
• 2000

Wean modal parameter estiimation technique by developing a residual based system reconstruction and using the system matrix coordinate transformation. The modal parameters can be estimated from and residues of the system transfer functions expressed in modal coordinate basis, derived from the state space system matrices. However, for modal parameter estimation of mllltivariable and order structural systems over broad frequency bands, this non-iterative algorithm gives high accuracy in the natural fre and damping ratios. From vibration tests on cross-ply and angle-ply composite laminates, the natural frequencies and damping ratios can be estimated using the coordinates of the structural system reconstructed from the experimental frequency response. These results are compared with those of finite element analysis and single-degree-of-freedom curve-fitting..

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.142-146
• /
• 2023

We present a method for generating 3D structures and rendering objects by combining VAE (Variational Autoencoder) and GAN (Generative Adversarial Network). This approach focuses on generating and rendering 3D models with improved quality using residual learning as the learning method for the encoder. We deep stack the encoder layers to accurately reflect the features of the image and apply residual blocks to solve the problems of deep layers to improve the encoder performance. This solves the problems of gradient vanishing and exploding, which are problems when constructing a deep neural network, and creates a 3D model of improved quality. To accurately extract image features, we construct deep layers of the encoder model and apply the residual function to learning to model with more detailed information. The generated model has more detailed voxels for more accurate representation, is rendered by adding materials and lighting, and is finally converted into a mesh model. 3D models have excellent visual quality and accuracy, making them useful in various fields such as virtual reality, game development, and metaverse.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.10
• /
• pp.51-59
• /
• 2003

A method of autonomous update is presented for onboard orbit propagator. On board propagator is an alternative means that could be used for navigation purpose in case of CPS receiver's failure. Although the ground station is not a able to upload a new propagator, the onboard propagator must be maintained most up-to-date. For this, a filtering technique is proposed wherein GPS data are effectively used to continuously update the on board propagator which was uploaded previously. Even if the ground station has generated the on board propagator based on the wrong information, the onboard propagator with updating scheme can automatically correct the errors in the coefficients of residual reconstruction function. Several scenarios were used to show the validity of the scheme for updating the onboard propagator using KOMPSAT-1 orbit data.

• Journal of Korean Foot and Ankle Society
• /
• v.25 no.2
• /
• pp.95-99
• /
• 2021

The surgical treatment of Achilles tendinopathy can be considered after the failure of conservative treatment, and the surgical methods may be divided into two groups; treatments for insertional and non-insertional tendinopathy. In the case of insertional tendinopathy, debridement including tendon and calcification of the diseased lesion, reattachment of the tendon, and calcaneal ostectomy of the Haglund lesion are the primary treatments. If reattachment is not possible, reconstruction should be performed by other methods such as tendon transfer. As a result of surgery for insertional tendinopathy, there is an improvement in the pain and function after surgery, but there are some patients whose pain does not completely disappear. Some residual pain may persist; therefore, the overall success rate of the surgery can be expected to be 80% to 90%. For the patients of non-insertional tendinopathy, conservative treatment through eccentric exercise is the primary treatment, and most of them have reported good results. In case of failure after various conservative treatments, debridement of the diseased lesion and repair of the remaining tendon would be the primary surgical treatments. If the remaining tendon is not sufficient, reconstruction such as tendon transfer should be considered.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.2
• /
• pp.279-286
• /
• 2015

EMD is a fully data-driven signal processing method without using any predetermined basis function and requiring any user parameters setting. However EMD experiences a problem of mode mixing which interferes with decomposing the signal into similar oscillations within a mode. To overcome the problem, EEMD method was introduced. The algorithm performs the EMD method over an ensemble of the signal added independent identically distributed white noise of the same standard deviation. Even so EEMD created problems when the decomposition is complete. The ensemble of different signal with added noise may produce different number of modes and the reconstructed signal includes residual noise. This paper propose an modified EEMD method to overcome mode mixing of EMD, to provide an exact reconstruction of the original signal, and to separate modes with lower cost than EEMD's. The experimental results show that the proposed method provides a better separation of the modes with less number of sifting iterations, costs 20.87% for a complete decomposition of the signal and demonstrates superior performance in the signal reconstruction, compared with EEMD.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.15 no.4
• /
• pp.338-345
• /
• 1993

Mandibular discontinuity defect due to benign tumor, malignant tumor, infection, or truma results in major esthetic and biologic compromise. The primary goal of reconstruction is full restitution of function, which secondarily lead to normalization of the cosmetic deformity. The authors make a clinical study of 61 consecutive bone graft cases for mandibular reconstruction of discontinuity defect which were studied retrospectively using clinical data and radiographic findings. The cases were reviewed to evaluate the clinical success in the period from 1981 to 1990 in the Dept. of Oral & maxillofacial Surgery, Seoul National University Hospital. The criteria of the success in bone graft, are no residual infection, graft in with maintain its integrity, and remain over a half of its original size of graft in the radiographic features. The purpose of this clinical survey is to study of the mandibular discontinuity defects and success rate of free bone graft in mandibular defects. To summarize the clinical study of free bone graft, the main type of autogenous bone graft is iliac bone and corticocancellous type. Overall success rate is 80.3% in 61 followup cases over 6 months. Wire fixation and Extraoral approach has realtively better prognosis than other methods. It showed relatively poor prognosis in symphysis defects than other recipient site.