• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.58-64
• /
• 2021

As the number of registered vehicles increases, traffic congestion will worsen worse, which may act as an inhibitory factor for urban social and economic development. Through accurate traffic flow prediction, various AI techniques have been used to prevent traffic congestion. This paper uses the data from a VDS (Vehicle Detection System) as input variables. This study predicted traffic flow in five levels (free flow, somewhat delayed, delayed, somewhat congested, and congested), rather than predicting traffic flow in two levels (free flow and congested). The Catboost model, which is a machine-learning algorithm, was used in this study. This model predicts traffic flow in five levels and compares and analyzes the accuracy of the prediction with other algorithms. In addition, the preprocessed model that went through RandomizedSerachCv and One-Hot Encoding was compared with the naive one. As a result, the Catboost model without any hyper-parameter showed the highest accuracy of 93%. Overall, the Catboost model analyzes and predicts a large number of categorical traffic data better than any other machine learning and deep learning models, and the initial set parameters are optimized for Catboost.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.31-37
• /
• 2021

As the size of buildings increases due to urbanization due to the development of industry, the need to purify the air and maintain a comfortable indoor environment is also increasing. With the development of monitoring technology for refrigeration systems, it has become possible to manage the amount of electricity consumed in buildings. In particular, refrigeration systems account for about 40% of power consumption in commercial buildings. Therefore, in order to develop the refrigeration system failure diagnosis algorithm in this study, the purpose of this study was to understand the structure of the refrigeration system, collect and analyze data generated during the operation of the refrigeration system, and quickly detect and classify failure situations with various types and severity . In particular, in order to improve the classification accuracy of failure types that are difficult to classify, a three-step diagnosis and classification algorithm was developed and proposed. A model based on SVM and LGBM was presented as a classification model suitable for each stage after a number of experiments and hyper-parameter optimization process. In this study, the characteristics affecting failure were preserved as much as possible, and all failure types, including refrigerant-related failures, which had been difficult in previous studies, were derived with excellent results.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.1
• /
• pp.161-166
• /
• 2020

This paper suggests an extension of the unified Bayesian Tikhonov regularization method. The unified method establishes the relationship between Tikhonov regularization parameter and Bayesian hyper-parameters, and presents a formula for obtaining the regularization parameter using the maximum posterior probability and the evidence framework. When the dimension of the data matrix is m by n (m >= n), we derive that the total misfit has the range of m ± n instead of m. Thus the search range is extended from one to 2n + 1 integer points. Golden section search rather than linear one is applied to reduce the time. A new benchmark for optimizing relative error and new model selection criteria to target it are suggested. The experimental results show the effectiveness of the proposed method in the image restoration problem.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.5 s.311
• /
• pp.52-61
• /
• 2006

Orthogonal wavelet tansform which is generally used in image and signal processing applications has limited performance because of lack of shift invariance and low directional selectivity. To overcome these demerits complex wavelet transform has been proposed. In this paper, we present an efficient image denoising method using dual-tree complex wavelet transform and Bernoulli-Gauss prior model. In estimating hyper-parameters for Bernoulli-Gaussian model, we present two simple and non-iterative methods. We use hypothesis-testing technique in order to estimate the mixing parameter, Bernoulli random variable. Based on the estimated mixing parameter, variance for clean signal is obtained by using maximum generalized marginal likelihood (MGML) estimator. We simulate our denoising method using dual-tree complex wavelet and compare our algorithm to well blown denoising schemes. Experimental results show that the proposed method can generate good denoising results for high frequency image with low computational cost.

• Journal of Korea Water Resources Association
• /
• v.48 no.1
• /
• pp.37-44
• /
• 2015

A Bayesian nonstationary probability rainfall estimation model using the Grid method is developed. A hierarchical Bayesian framework is consisted with prior and hyper-prior distributions associated with parameters of the Gumbel distribution which is selected for rainfall extreme data. In this study, the Grid method is adopted instead of the Matropolis Hastings algorithm for random number generation since it has advantage that it can provide a thorough sampling of parameter space. This method is good for situations where the best-fit parameter values are not easily inferred a priori, and where there is a high probability of false minima. The developed model was applied to estimated target year probability rainfall using hourly rainfall data of Seoul station from 1973 to 2012. Results demonstrated that the target year estimate using nonstationary assumption is about 5~8% larger than the estimate using stationary assumption.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.71-78
• /
• 2022

This paper proposes an algorithm for 3D object detection by processing point cloud data of 3D LiDAR. Unlike 2D LiDAR, 3D LiDAR-based data was too vast and difficult to process in three dimensions. This paper introduces various studies based on 3D LiDAR and describes 3D LiDAR data processing. In this study, we propose a method of processing data of 3D LiDAR using clustering techniques for object detection and design an algorithm that fuses with cameras for clear and accurate 3D object detection. In addition, we study models for clustering 3D LiDAR-based data and study hyperparameter values according to models. When clustering 3D LiDAR-based data, the DBSCAN algorithm showed the most accurate results, and the hyperparameter values of DBSCAN were compared and analyzed. This study will be helpful for object detection research using 3D LiDAR in the future.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.41-43
• /
• 2019

Image-to-image 변환에서 인상적인 성능을 보이는 StarGAN 은 모델의 성능에 중요한 영향을 끼치는 adversarial weight, classification weight, reconstruction weight 라는 세가지 하이퍼파라미터의 결정을 전제로 하고 있다. 본 연구에서는 이 중 conditional GAN loss 인 adversarial loss 와 classification loss 를 대치할 수 있는 attribute loss를 제안함으로써, adversarial weight와 classification weight 를 최적화하는 데 걸리는 시간을 attribute weight 의 최적화에 걸리는 시간으로 대체하여 하이퍼파라미터 탐색에 걸리는 시간을 획기적으로 줄일 수 있게 하였다. 제안하는 attribute loss 는 각 특징당 GAN 을 만들 때 각 GAN 의 loss 의 합으로, 이 GAN 들은 hidden layer 를 공유하기 때문에 연산량의 증가를 거의 가져오지 않는다. 또한 reconstruction loss 를 단순화시켜 연산량을 줄인 simplified content loss 를 제안한다. StarGAN 의 reconstruction loss 는 generator 를 2 번 통과하지만 simplified content loss 는 1 번만 통과하기 때문에 연산량이 줄어든다. 또한 이미지 Framing 을 통해 배경의 왜곡을 방지하고, 양방향 성장을 통해 학습 속도를 향상시킨 아키텍쳐를 제안한다.

• Convergence Security Journal
• /
• v.19 no.4
• /
• pp.181-188
• /
• 2019

Recently, attempts to apply artificial intelligence technology to create the normal profile in Anomaly-based intrusion detection systems have been made actively. But existing studies that proposed the application of artificial intelligence technology mostly focus on improving the structure of artificial neural networks and finding optimal hyper-parameter values, and fail to address various problems that may arise from the misconfiguration of learning data. In this paper, we identify the main problems that may arise due to the misconfiguration of learning data through experiment. And we also propose a novel approach that can address such problems and improve the detection performance through reconstruction of learning data.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.53 no.12
• /
• pp.691-699
• /
• 2004

SRM(Switched Reluctance Motor) drives require the accurate position information of the rotor. These informations are generally provided by a tacho generator or digital shaft-position encoder These speed sensors lower the system reliability and require special attention to noise. This paper describes a new approach to estimating SRM speed from measured terminal voltages and currents for speed sensorless control. The described method is based on the sliding mode observer. The rotor speed and position observers are estimated by the adaptation law using the real and estimated currents. However, the conventional adaptive sliding mode observer based on the variable structure control theory has some disadvantages that the estimated values including the high-frequency chattering and the steady state error generated due to the infinite feedback gain chosen and the discontinuous control input. To reduce the chattering and steady state error, an integrator is also inserted in the sliding mode observer strategy. The described adaptive sliding mode observer decreases the vibration to the switching hyper-plane of the sliding mode by adding integrator. The described methodology incorporates the Lyapunov algorithm to drive the rotor speed and the stator resistance such that it can overcome the problem of sensitivity in the face of SRM parameter variation. Also, without any mechanical information. The rotor speed of SRM is obtained form adaptive scheme. The described method is verified through the simulation and experiment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.18-23
• /
• 2006

The complex system synchronization methods improve based on synchronization theory; however, due to deeper level of complexity within complex system compared to that of chaos system, it is difficult to synchronize complex signals from complex system. In this paper, we proposed coupled-synchronization theory in the n-double scroll circuit and new embedding driven-synchronization theory, a method of accomplishing synchronization with only one parameter out of may parameters, in hyper-chaos circuit to apply synchronization in the complex system. By applying proposed synchronization method using computer simulation, we confirmed the accomplishment of superior synchronization in complex system.