• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3144-3164
• /
• 2019

Face recognition systems have several potential applications, such as security and biometric access control. Ongoing research is focused to develop a robust face recognition algorithm that can mimic the human vision system. Face pose, non-uniform illuminations, and low-resolution are main factors that influence the performance of face recognition algorithms. This paper proposes a novel method to handle the aforementioned aspects. Proposed face recognition algorithm initially uses 68 points to locate a face in the input image and later partially uses the PCA to extract mean image. Meanwhile, the AdaBoost and the LDA are used to extract face features. In final stage, classic nearest centre classifier is used for face classification. Proposed method outperforms recent state-of-the-art face recognition algorithms by producing high recognition rate and yields much lower error rate for a very challenging situation, such as when only frontal ($0^{\circ}$) face sample is available in gallery and seven poses ($0^{\circ}$, ${\pm}30^{\circ}$, ${\pm}35^{\circ}$, and ${\pm}45^{\circ}$) as a probe on the LFW and the CMU Multi-PIE databases.

• Proceedings of the KIPE Conference
• /
• 2019.07a
• /
• pp.11-13
• /
• 2019

This paper proposes a novel high step-up non-isolated DC-DC converter, suitable for regulating dc bus in various inherent low voltage micro sources especially for photovoltaic (PV) and fuel cell sources. This novel high voltage Non-isolated Boost DC-DC converter topology is best replacement, where high voltage conversion ratio is required without the transformer and also need continuous input current. Since the proposed topology utilizes the stack-based structure, the voltage gain, and the efficiency are higher than other conventional non-isolated converters. Switches in this topology is easier to control since its control signal is grounding reference. Also, there is no need of extra gate driver and extra power supply for driver circuit, which reduces the cost and size of system. In order to show the feasibility and practicality of the proposed topology principle operation, steady state analysis and simulation result is presented and analyzed in detail. To verify the performance of proposed converter and theoretical analysis 360W laboratory prototype is implemented.

• Journal of Power Electronics
• /
• v.19 no.1
• /
• pp.220-233
• /
• 2019

This work aims to study and analyze the various operating modes of universal power converter which is powered by solar and thermoelectric generators. The proposed converter is operated in a DC-DC (buck or boost mode) and DC-AC (single phase) inverter with high efficiency. DC power sources, such as solar photovoltaic (SPV) panels, thermoelectric generators (TEGs), and Li-ion battery, are selected as input to the proposed converter according to the nominal output voltage available/generated by these sources. The mode of selection and output power regulation are achieved via control of the metal-oxide semiconductor field-effect transistor (MOSFET) switches in the converter through the modified stepped perturb and observe (MSPO) algorithm. The MSPO duty cycle control algorithm effectively converts the unregulated DC power from the SPV/TEG into regulated DC for storing energy in a Li-ion battery or directly driving a DC load. In this work, the proposed power sources and converter are mathematically modelled using the Scilab-Xcos Simulink tool. The hardware prototype is designed for 200 W rating with a dsPIC30F4011 digital controller. The various output parameters, such as voltage ripple, current ripple, switching losses, and converter efficiency, are analyzed, and the proposed converter with a control circuit operates the converter closely at 97% efficiency.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.103-111
• /
• 2021

Among transport vehicles, Special Vehicles (SVs) are seriously exposed to energy and environmental problems. In particular, elevator cars used when moving objects in high-rise buildings increase the engine's rotational speed (radian per second: RPM). At this time, when the vehicle accelerates rapidly while idling, energy consumption increases explosively along with the engine speed, and a lot of soot is generated. The purpose of this paper is to develop a bi-directional DC-DC converter for control of vehicle power and secondary battery used in an elevated ladder vehicle (EC) used in the moving industry. As a result of this paper, the performance test of the converter was conducted. The charging/discharging state of the converter was simulated using DC power supply and DC electronic load, and a performance experiment was conducted to measure the input/output power of the converter through a power meter. Through this experimental result, it was confirmed that the efficiency was more than 92% in Buck mode and Boost mode at maximum 1.2kW output.

• Journal of Korea Trade
• /
• v.25 no.8
• /
• pp.25-44
• /
• 2021

Purpose - This research aims to provide empirical evidence that highlights the importance of imported intermediate goods in long-term economic growth. To this end, this paper develops an index that measures the productivity gains associated with a country's intermediate goods imports using highly disaggregated trade data. Design/methodology - The basic hypothesis is that countries sourcing higher-productivity (or higher-quality) inputs from developed economies derive a larger benefit from foreign R&D. To explore this hypothesis, standard cross-country growth regressions are performed using the highly disaggregated data from the United Nations (UN) Commodity Trade Statistics Database (COMTRADE). To address the endogeneity issue, I apply an instrumental variable (IV) approach. Findings - The results of this study demonstrate that the index predicts subsequent economic growth in middle- and low-income countries. This finding is consistent with previous studies that have argued that developing countries can achieve substantial productivity gains by importing intermediate inputs from developed countries. By contrast, there is no evidence of a significant association between the index and economic growth in high-income countries. Originality/value - This paper contributes to our understanding of the causal relationship between international trade and economic growth. From an economic policy perspective, the results suggest that developing countries with limited technology endowment can boost growth from input-tariff liberalization.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.252-255
• /
• 2020

Unsupervised deep learning methods have shown impressive results for the challenging monocular depth estimation task, a field of study that has gained attention in recent years. A common approach for this task is to train a deep convolutional neural network (DCNN) via an image synthesis sub-task, where additional views are utilized during training to minimize a photometric reconstruction error. Previous unsupervised depth estimation networks are trained within a fixed depth estimation range, irrespective of its possible range for a given image, leading to suboptimal estimates. To overcome this suboptimal limitation, we first propose an unsupervised adaptive depth estimation method guided by minimum and maximum (min-max) depth priors for a given input image. The incorporation of min-max depth priors can drastically reduce the depth estimation complexity and produce depth estimates with higher accuracy. Moreover, we propose a novel network architecture for adaptive depth estimation, called the AdaMM-DepthNet, which adopts the min-max depth estimation in its front side. Intensive experimental results demonstrate that the adaptive depth estimation can significantly boost up the accuracy with a fewer number of parameters over the conventional approaches with a fixed minimum and maximum depth range.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.3
• /
• pp.569-575
• /
• 2020

Recently, research on renewable energy technologies has come into the spotlight due to rising concerns over the depletion of fossil fuels and greenhouse gas emissions. Demand for portable electronic and wearable devices is increasing, and electronic devices are becoming smaller. Energy harvesting is a technology for overcoming limitations such as battery size and usage time. In this paper, the V-I characteristic curve and internal resistance of thermal electric devices were analyzed, and MPPT control methods were compared. The Perturbation and Observation (P&O) control method is economically inefficient because two sensors are required to measure the voltage and current of a Thermoelectric Generator(TEG). Therefore, this paper proposes a new MPPT control method that tracks MPP using only one sensor for the regulation of the output voltage. The proposed MPPT control method uses the relationship between the output voltage of the load and the duty ratio. Control is done by periodically sampling the output voltage of the DC-DC converter to increase or decrease the duty ratio to find the optimal duty ratio and maintain the MPP. A DC-DC converter was designed using a cascaded boost-buck converter, which has a two-switch topology. The proposed MPPT control method was verified by simulations using PSIM, and the results show that a voltage, current, and power of V=4.2 V, I=2.5 A, and P=10.5 W were obtained at the MPP from the V-I characteristic curve of the TEG.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.749-754
• /
• 2011

In this study, we propose the design of optimized pRBFNNs-based face recognition system using two-dimensional Image and ASM algorithm. usually the existing 2 dimensional face recognition methods have the effects of the scale change of the image, position variation or the backgrounds of an image. In this paper, the face region information obtained from the detected face region is used for the compensation of these defects. In this paper, we use a CCD camera to obtain a picture frame directly. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. AdaBoost algorithm is used for the detection of face image between face and non-face image area. We can butt up personal profile by extracting the both face contour and shape using ASM(Active Shape Model) and then reduce dimension of image data using PCA. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of RBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to real-time face image database and then demonstrated from viewpoint of the output performance and recognition rate.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.112-118
• /
• 2009

This paper proposes a rapid detection algorithm of a salient region for music video browsing system, which can be applied to mobile device and digital video recorder (DVR). The input music video is decomposed into the music and video tracks. For the music track, the music highlight including musical chorus is detected based on structure analysis using energy-based peak position detection. Using the emotional models generated by SVM-AdaBoost learning algorithm, the music signal of the music videos is classified into one of the predefined emotional classes of the music automatically. For the video track, the face scene including the singer or actor/actress is detected based on a boosted cascade of simple features. Finally, the salient region is generated based on the alignment of boundaries of the music highlight and the visual face scene. First, the users select their favorite music videos from various music videos in the mobile devices or DVR with the information of a music video's emotion and thereafter they can browse the salient region with a length of 30-seconds using the proposed algorithm quickly. A mean opinion score (MOS) test with a database of 200 music videos is conducted to compare the detected salient region with the predefined manual part. The MOS test results show that the detected salient region using the proposed method performed much better than the predefined manual part without audiovisual processing.