• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.11
• /
• pp.901-907
• /
• 2021

The present study introduces an artificial neural network (ANN) that can predict the missile aerodynamic coefficients for various missile nose shapes and flow conditions such as Mach number and angle of attack. A semi-empirical missile aerodynamics code is utilized to generate a dataset comprised of the geometric description of the nose section of the missiles, flow conditions, and aerodynamic coefficients. Data normalization is performed during the data preprocessing step to improve the performance of the ANN. Dropout is used during the training phase to prevent overfitting. For the missile nose shape and flow conditions not included in the training dataset, the aerodynamic coefficients are predicted through ANN to verify the performance of the ANN. The result shows that not only the ANN predictions are very similar to the aerodynamic coefficients produced by the semi-empirical missile aerodynamics code, but also ANN can predict missile aerodynamic coefficients for the untrained nose section of the missile and flow conditions.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.531-539
• /
• 2019

This paper proposes the training features for malware family analysis and analyzes the multi-classification performance of ensemble models. We construct training data by extracting API and DLL information from malware executables and use Random Forest and XGBoost algorithms which are based on decision tree. API, API-DLL, and DLL-CM features for malware detection and family classification are proposed by analyzing frequently used API and DLL information from malware and converting high-dimensional features to low-dimensional features. The proposed feature selection method provides the advantages of data dimension reduction and fast learning. In performance comparison, the malware detection rate is 93.0% for Random Forest, the accuracy of malware family dataset is 92.0% for XGBoost, and the false positive rate of malware family dataset including benign is about 3.5% for Random Forest and XGBoost.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.19-28
• /
• 2021

Nowadays, interest in health care is increasing due to Coronavirus (COVID-19), and a lot of people are doing home training as there are more difficulties in using fitness centers and public facilities that are used together. In this paper, we propose a personalized exercise recommendation algorithm using personalized propensity information to provide more accurate and meaningful exercise recommendation to home training users. Thus, we classify the data according to the criteria for obesity with a k-nearest neighbor algorithm using personal information that can represent individuals, such as eating habits information and physical conditions. Furthermore, we differentiate the exercise dataset by the level of exercise activities. Based on the neighborhood information of each dataset, we provide personalized exercise recommendations to users through a dimensionality reduction algorithm (SVD) among model-based collaborative filtering methods. Therefore, we can solve the problem of data sparsity and scalability of memory-based collaborative filtering recommendation techniques and we verify the accuracy and performance of the proposed algorithms.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.1
• /
• pp.30-37
• /
• 2022

This paper compares and evaluates model performance from two perspectives according to the learning target and network structure for training Deep Neural Network (DNN)-based speech enhancement models in the frequency domain. In this case, spectrum mapping and Time-Frequency (T-F) masking techniques were used as learning targets, and a real network and a complex network were used for the network structure. The performance of the speech enhancement model was evaluated through two objective evaluation metrics: Perceptual Evaluation of Speech Quality (PESQ) and Short-Time Objective Intelligibility (STOI) depending on the scale of the dataset. Test results show the appropriate size of the training data differs depending on the type of networks and the type of dataset. In addition, they show that, in some cases, using a real network may be a more realistic solution if the number of total parameters is considered because the real network shows relatively higher performance than the complex network depending on the size of the data and the learning target.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• Journal of Broadcast Engineering
• /
• v.28 no.2
• /
• pp.238-241
• /
• 2023

Recently deep learning models are widely used for various tasks such as facial recognition and face editing. Their training process often involves a dataset with imbalanced age distribution. It is because some age groups (teenagers and middle age) are more socially active and tends to have more data compared to the less socially active age groups (children and elderly). This imbalanced age distribution may negatively impact the deep learning training process or the model performance when tested against those age groups with less data. To this end, we propose an age-controllable face synthesis technique using a feature decomposition to classify age from facial images which can be utilized to synthesize novel data to balance out the age distribution. We perform extensive qualitative and quantitative evaluation on our proposed technique using the FFHQ dataset and we show that our method has better performance than existing method.

• Current Optics and Photonics
• /
• v.7 no.3
• /
• pp.237-247
• /
• 2023

In middle- and long-distance imaging systems, due to the atmospheric turbulence caused by temperature, wind speed, humidity, and so on, light waves propagating in the air are distorted, resulting in image-quality degradation such as geometric deformation and fuzziness. In remote sensing, astronomical observation, and traffic monitoring, image information loss due to degradation causes huge losses, so effective restoration of degraded images is very important. To restore images degraded by atmospheric turbulence, an image-restoration method based on improved compound multibranch feature fusion (CMFNetPro) was proposed. Based on the CMFNet network, an efficient channel-attention mechanism was used to replace the channel-attention mechanism to improve image quality and network efficiency. In the experiment, two-dimensional random distortion vector fields were used to construct two turbulent datasets with different degrees of distortion, based on the Google Landmarks Dataset v2 dataset. The experimental results showed that compared to the CMFNet, DeblurGAN-v2, and MIMO-UNet models, the proposed CMFNetPro network achieves better performance in both quality and training cost of turbulent-image restoration. In the mixed training, CMFNetPro was 1.2391 dB (weak turbulence), 0.8602 dB (strong turbulence) respectively higher in terms of peak signal-to-noise ratio and 0.0015 (weak turbulence), 0.0136 (strong turbulence) respectively higher in terms of structure similarity compared to CMFNet. CMFNetPro was 14.4 hours faster compared to the CMFNet. This provides a feasible scheme for turbulent-image restoration based on deep learning.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.59-67
• /
• 2023

Recently, research on behavior analysis tracking human posture and movement has been actively conducted. In particular, OpenPose, an open-source software developed by CMU in 2017, is a representative method for estimating human appearance and behavior. OpenPose can detect and estimate various body parts of a person, such as height, face, and hands in real-time, making it applicable to various fields such as smart healthcare, exercise training, security systems, and medical fields. In this paper, we propose a method for classifying four exercise movements - Squat, Walk, Wave, and Fall-down - which are most commonly performed by users in the gym, using OpenPose-based deep learning models, DNN and CNN. The training data is collected by capturing the user's movements through recorded videos and real-time camera captures. The collected dataset undergoes preprocessing using OpenPose. The preprocessed dataset is then used to train the proposed DNN and CNN models for exercise movement classification. The performance errors of the proposed models are evaluated using MSE, RMSE, and MAE. The performance evaluation results showed that the proposed DNN model outperformed the proposed CNN model.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.305-312
• /
• 2023

Physics-Informed Neural Network (PINN) is used to invert bubble size distributions from attenuation losses. By considering a linear system for the bubble population inversion, Adaptive Learned Iterative Shrinkage Thresholding Algorithm (Ada-LISTA), which has been solved linear systems in image processing, is used as a neural network architecture in PINN. Furthermore, a regularization based on the linear system is added to a loss function of PINN and it makes a PINN have better generalization by a solution satisfying the bubble physics. To evaluate an uncertainty of bubble estimation, deep ensemble is adopted. 20 Ada-LISTAs with different initial values are trained using the same training dataset. During test with attenuation losses different from those in the training dataset, the bubble size distribution and corresponding uncertainty are indicated by average and variance of 20 estimations, respectively. Deep ensemble Ada-LISTA demonstrate superior performance in inverting bubble size distributions than the conventional convex optimization solver of CVX.