• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.203-211
• /
• 2020

This study proposes a method for estimating gender and age that is robust to various external environment changes by applying deep learning-based learning. To improve the accuracy of the proposed algorithm, an improved CNN network structure and learning method are described, and the performance of the algorithm is also evaluated. In this study, in order to improve the learning method based on CNN composed of 6 layers of hidden layers, a network using GoogLeNet's inception module was constructed. As a result of the experiment, the age estimation accuracy of 5,328 images for the performance test of the age estimation method is about 85%, and the gender estimation accuracy is about 98%. It is expected that real-time age recognition will be possible beyond feature extraction of face images if studies on the construction of a larger data set, pre-processing methods, and various network structures and activation functions have been made to classify the age classes that are further subdivided according to age.

• Journal of the Korean Mathematical Society
• /
• v.58 no.3
• /
• pp.723-740
• /
• 2021

Design and maintenance of large span roof structures require an analysis of their static and dynamic behavior depending on the physical parameters defining the structures. Therefore, it is highly desirable to estimate the parameters from observations of the system. In this paper we study the parameter estimation problem for damped shallow arches. We discuss both symmetric and non-symmetric shapes and loads, and provide theoretical and numerical studies of the model behavior. Our study of the behavior of such structures shows that it is greatly affected by the existence of critical parameters. A small change in such parameters causes a significant change in the model behavior. The presence of the critical parameters makes it challenging to obtain good estimation. We overcome this difficulty by presenting the Parameter Estimation Algorithm that identifies the unknown parameters sequentially. It is shown numerically that the algorithm achieves a successful parameter estimation for models defined by arbitrary parameters, including the critical ones.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.209-215
• /
• 2022

This paper proposes a novel approach for training an unsupervised depth estimation algorithm. The objective of unsupervised depth estimation is to estimate pixel-wise distances from camera without external supervision. While most previous works focus on model architectures, loss functions, and masking methods for considering dynamic objects, this paper focuses on the training framework to effectively use depth cue. The main loss function of unsupervised depth estimation algorithms is known as the photometric error. In this paper, we claim that direct depth cue is more effective than the photometric error. To obtain the direct depth cue, we adopt the technique of knowledge distillation which is a teacher-student learning framework. We train a teacher network based on a previous unsupervised method, and its depth predictions are utilized as pseudo labels. The pseudo labels are employed to train a student network. In experiments, our proposed algorithm shows a comparable performance with the state-of-the-art algorithm, and we demonstrate that our teacher-student framework is effective in the problem of unsupervised depth estimation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.2
• /
• pp.69-76
• /
• 2010

This paper proposed a new fast multi-reference frame motion estimation algorithm. The proposed algorithm reduces search areas of motion estimation using a linear relation of motion vector with distance of each reference frame. New algorithm executes full search area motion estimation in reference frame 0 and reference frame 1. After that, search areas in reference frame 2, reference frame 3 and reference frame 4 are minimized by distance of each reference frame and results of motion estimation in reference frame 0 and reference frame 1. The proposed algorithm does not use a threshold value which is obstacle of hardware implementation and processing time schedule. Also, it reduced computation quantity of multi-reference motion estimation. Hardware implementation of multi-reference frame motion estimation is possible by these features. Simulation results show that PSNR drop and bitrate increase of proposed algorithm are lower than those of previous fast multi-reference frame motion estimation algorithm The number of computation of new algorithm is reduced 52.5% and quality of result is negligible when compared with full search area motion estimation which has 5 reference frames.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.11
• /
• pp.192-199
• /
• 2002

This paper demonstrates that hybrid neural-genetic multimodel parameter estimation algorithm can be applied to structured system Identification of electro-hydraulic servo system. This algorithm are consist of a recurrent incremental credit assignment (ICRA) neural network and a genetic algorithm. The ICRA neural network evaluates each member of a generation of model and genetic algorithm produces new generation of model. We manufactured electro-hydraulic servo system and the hybrid neural-genetic multimodel parameter estimation algorithm is applied to the task to find the parameter values(mass, damping coefficient, bulk modulus, spring coefficient) which minimize total square error.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.6
• /
• pp.442-447
• /
• 2003

This paper demonstrates that a modified hybrid neural-genetic multimodel parameter estimation algorithm can be applied to structured system identification of an electro-hydraulic servo system. This algorithm is consists of a recurrent incremental credit assignment(ICRA) neural network and a genetic algorithm. The ICRA neural network evaluates each member of a generation of model and genetic algorithm produces new generation of model. The modified hybrid neural-genetic multimodel parameter estimation algorithm is applied to an electro-hydraulic servo system the task to find the parameter values such as mass, damping coefficient, bulk modulus, spring coefficient and disturbance, which minimizes the total square error.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.5
• /
• pp.196-203
• /
• 2003

This paper demonstrates that an improved hybrid neural-genetic multimodel parameter estimation algorithm can be applied to the structured system identification of an electro-hydraulic servo system. This algorithm is consists of a recurrent incremental credit assignment (ICRA) neural network and a genetic algorithm, The ICRA neural network evaluates each member of a generation of model and the genetic algorithm produces new generation of model. We manufactured an electro-hydraulic servo system and the improved hybrid neural-genetic multimodel parameter estimation algorithm is applied to the task to find the parameter values, such as mass, damping coefficient, bulk modulus, spring coefficient and disturbance, which minimize total square error.

• ETRI Journal
• /
• v.45 no.3
• /
• pp.379-393
• /
• 2023

Underwater communication (UWC) is widely used in coastal surveillance and early warning systems. Precise channel estimation is vital for efficient and reliable UWC. The sparse direct-adaptive filtering algorithms have become popular in UWC. Herein, we present an improved adaptive convex-combination method for the identification of sparse structures using a reweighted normalized leastmean-square (RNLMS) algorithm. Moreover, to make RNLMS algorithm independent of the reweighted l₁-norm parameter, a modified sparsity-aware adaptive zero-attracting RNLMS (AZA-RNLMS) algorithm is introduced to ensure accurate modeling. In addition, we present a quantitative analysis of this algorithm to evaluate the convergence speed and accuracy. Furthermore, we derive an excess mean-square-error expression that proves that the AZA-RNLMS algorithm performs better for the harsh underwater channel. The measured data from the experimental channel of SPACE08 is used for simulation, and results are presented to verify the performance of the proposed algorithm. The simulation results confirm that the proposed algorithm for underwater channel estimation performs better than the earlier schemes.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.6
• /
• pp.1455-1461
• /
• 2012

MIMO-OFDM which is one of core techniques for the high-speed mobile communication system requires the efficient channel estimation method with low estimation error and computational complexity, for accurately receiving data. In this paper, we propose a channel estimation algorithm with low channel estimation error comparing with LS which is primarily employed to the MIMO-OFDM system, and with low computational complexity comparing with MMSE. The proposed algorithm estimates channel vectors based on the LMS adaptive algorithm in the time domain, and the estimated channel vector is sent to the detector after FFT. We also suggest a preamble architecture for the proposed MIMO-OFDM channel estimation algorithm. The computer simulation example is provided to illustrate the performance of the proposed algorithm.

• Journal of Digital Convergence
• /
• v.12 no.3
• /
• pp.249-254
• /
• 2014

Wireless LAN system is evolving toward high-speed data transmission and more accurate channel estimation is necessarily required to improve communication performance. The PLCP preamble field in IEEE 802.11 based wireless MODEM consists of ten short symbols and two long symbols and is used for synchronization and channel estimation. The existing least square (LS) channel estimation is based on only two long training symbols. After estimating channel response separately by using each long training symbol, the final channel estimation is obtained by the average of each estimation. In this paper, a new channel estimation algorithm is presented to improve the performance of the existing LS channel estimation algorithm. From the fact that the short training symbol consists of 12 non-zero subcarriers, it gives us a clue of being able to additionally estimate at least one fourth of channel coefficients. The new LS algorithm performs channel estimation based on both two long training symbols and a short training symbol. The proposed LS algorithm shows a little bit performance improvement over the existing LS estimation and it will be able to be applied to the IEEE 802.11p WAVE system.