• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1165-1173
• /
• 2017

Deep learning method, which is one of the most famous machine learning algorithms, has proven its applicability in various applications and is widely used in digital signal processing. However, it is difficult to apply deep learning technology to IoT devices with limited CPU performance and memory capacity, because a large number of training samples requires a lot of memory and computation time. In particular, if the Arduino with a very small memory capacity of 2K to 8K, is used, there are many limitations in implementing the algorithm. In this paper, we propose a method to optimize the ELM algorithm, which is proved to be accurate and efficient in various fields, on Arduino board. Experiments have shown that multi-class learning is possible up to 15-dimensional data on Arduino UNO with memory capacity of 2KB and possible up to 42-dimensional data on Arduino MEGA with memory capacity of 8KB. To evaluate the experiment, we proved the effectiveness of the proposed algorithm using the data sets generated using gaussian mixture modeling and the public UCI data sets.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.8
• /
• pp.890-895
• /
• 2016

As the wireless communication technique is developing rapidly, the use of smart devices is increasing. Due to gradually increasing data traffic, a new area, more than 6GHz of bandwidth to increase capacity of the network, has been studied. Millimeter Wave(MmWave) communications utilizes the bandwidth above 6GHz, which makes it possible to achieve one gigabit per second data rate. To overcome the path loss due to the smaller wavelength, the mass of the antenna arrangement is used. This paper presents an algorithm that maximizes the spectral efficiency of the system in the pre-coding process using a hybrid beamforming. Also it is suggested with the optimization of the number of beams that maximizes the spectral efficiency was maximized by the propose method.

• Composites Research
• /
• v.24 no.2
• /
• pp.38-45
• /
• 2011

In this paper, we present an optimization method for the single Dallenbach-layer type microwave absorbers composed of E-glass fabric/epoxy composite laminates. The composite prepreg containing carbon nanotubes (CNT) was used to control the electrical property of the composites laminates. The design technology using the genetic algorithm was used to get the optimal thicknesses of the laminates and the filler contents at various center frequencies, for which the numerical model of the complex permittivity of the composite laminate was incorporated. In the optimal design results, the content of CNT increased in proportion to the center frequency, but, on the contrary, the thickness of the microwave absorbers decreased. The permittivity and reflection loss are measured using vector network analyzer and 7 mm coaxial airline. The influence of the mismatches in between measurement and prediction of the thickness and the complex permittivity caused the shift of the center frequency, blunting of the peak at the center frequency and the reduction of the absorbing bandwidth.

• Journal of the Society of Disaster Information
• /
• v.14 no.2
• /
• pp.219-229
• /
• 2018

Purpose: This research proposes an optimization model for effective evacuation routing and scheduling of civilians near the border area when full-scale war threats heighten. Method: To reflect the reality, administrative unit network is created using Kruscal's Algorithm, Harmony Search, CCRP based on the geographical features, population, and traffic data of real cities, and then, optimal civilian evacuation routes are found. Results: Optimal evacuation routes and schedules are computed by repetitive experiments, and it is found that the scenario that minimizes the average civilian evacuation time is effective for the civilian evacuation plan. Conclusion: By using the civilian evacuation plan this research proposes, at the time of establishing the actual civilian evacuation plan, quantitative analysis is used for the effective plan making rather than only depending.

• Journal of Internet Computing and Services
• /
• v.17 no.4
• /
• pp.19-26
• /
• 2016

In this paper, the dynamic buffering based smart OTT platform was proposed, and analyzed for adaptive bit-rate video delivery with the optimization of HLS (HTTP Live Streaming). This platform consists of the software platform between sever and client which detects the bandwidth capacity, and adjusts the quality of the streaming for multiple bit-rates resolutions. In order to apply adaptive buffering, two buffers are added to the basic HLS player, and each buffer is responsible for constantly buffering a previous and the next channels relative to the current channel. This adaptive transmitting with smart OTT platform is superior to delivering a static video file at a single buffering, because the video stream of adaptive double buffers can be switched streaming according to client's available network speed. As a result, this proposed smart OTT can be cooperated to the application of HLS server with segmented H.265 MPEG-2 TS video & m3u8 files with its information based on the optimized transmission channel state of live and VOD, and applied to PLC transmission, too.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.12
• /
• pp.4697-4706
• /
• 2010

This paper suggested the optimal operating design method using simulation and ANP(Analytic Network Process) for mass-customization in the automotive component manufacturing industry. For this, first of all, we built the simulation model including various and complex factors in the field, and estimated the meta-model by RSM(Response Surface Method). Secondly using ANP, we calculated the weight of relative importance of evaluation factors gathered from decision makers. And then, we proposed the optimal operation designs by MOGA(Multi-Objective Genetic Algorithm), analyzed results of them. Moreover, by comparing the results with the consequences using AHP(Analytic Hierarchy Process), we showed its superiority of suggested method to the manner using AHP, because it reflects inner, outer dependency, and inter-relation among judgement factors. In conclusion, through this process, we can present the better way to serve mover effective, precise, and accurate information to decision makers when they build operation design for mass-customization system as automotive parts production system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.8
• /
• pp.1401-1406
• /
• 2006

Mobile Ad-hoc networks have recently attracted a lot of attention in the research community as well as in industry. Although the previous research mainly focused on various of Ad-hoc in routing, we consider, in this paper, how to efficiently support applications such as variable Goocasting basd on Ad-hoc networks. The goal of a geocasting uotocol is deliver data packets to a group of nodes that are located within a specified geocasting region. Previous research that support geocast nice in mobilie computing based on Ad-hoc have the non-optimization problem of data delivery path, overhead by frequent reconstruction of the geocast tree, and service disruption problem. In this paper, we propose the mobility pattern based geocast technique using variable service range according to the nobility of destination node and resource reservation to solve this problem. The experimental results show that our proposed mechanism has improved performance of Connection & Network Overhead than previous research.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.54 no.8
• /
• pp.375-387
• /
• 2005

This paper presents an application of parallel Genetic Algorithm-Tabu Search (GA-TS) algorithm to search an optimal solution of a service restoration in distribution systems. The main objective of service restoration of distribution systems is, when a fault or overload occurs, to restore as much load as possible by transferring the do-energized load in the out of service area via network reconfiguration to the appropriate adjacent feeders at minimum operational cost without violating operating constraints, which is a combinatorial optimization problem. This problem has many constraints with many local minima to solve the optimal switch position. This paper develops parallel GA-TS algorithm for service restoration of distribution systems. In parallel GA-TS, GA operators are executed for each processor. To prevent solutions of low fitness from appearing in the next generation, strings below the average fitness are saved in the tabu list. If best fitness of the GA is not changed for several generations, TS operators are executed for the upper $10\%$ of the population to enhance the local searching capabilities. With migration operation, best string of each node is transferred to the neighboring node after predetermined iterations are executed. For parallel computing, we developed a PC cluster system consists of 8 PCs. Each PC employs the 2 GHz Pentium IV CPU and is connected with others through ethernet switch based fast ethernet. To show the validity of the proposed method, proposed algorithm has been tested with a practical distribution system in Korea. From the simulation results, we can find that the proposed algorithm is efficient for the distribution system service restoration in terms of the solution quality, speedup, efficiency and computation time.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.3
• /
• pp.409-413
• /
• 2014

GIS partial discharge that occurred in the UHF band signal is effectively detected by the method to IEC60270 5pc the apparent minimum discharge can be detected over the GIS arrangement of the sensor interior and exterior of the UHF in accordance with the optimized position signal by considering the damping ratio is selected so that the signals can be obtained to be mounted. 362kV, 800kV GIS is installed on the internal and external sensors are UHF band signal attenuation is set by measuring the reference value, but the operation, 170kV case 362kV, 800kV on the basis of the measurement data and to be installed and operated. When 170kV per 1Bay by installing the built-in sensor 1 for detecting a partial discharge signal, But, GIS signal attenuation is large in the case of an internal partial discharge signal is not detected in some cases. Where the attenuation is great UHF signal of the sensor by increasing the quantity of partial discharge signals were acquired to allow relocation. The greater the spacing between the sensor and the sensor is applied simplifies the installation and reduces the cost in terms of maintenance of appropriate optimal position is calculated to detect the partial discharge signal is needed. Thus 170kV GIS signal power attenuation of a partial discharge by measuring the UHF sensor, and by relocating the proper position is calculated in accordance with the sensor signal decay rate and minimize the error of omission in detecting a partial discharge signal was optimized.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.6
• /
• pp.922-934
• /
• 2015

In this paper, The classification between precipitation echo(PRE) and non-precipitation echo(N-PRE) (including ground echo and clear echo) is carried out from weather radar data using neuro-fuzzy algorithm. In order to classify between PRE and N-PRE, Input variables are built up through characteristic analysis of radar data. First, the event classifier as the first classification step is designed to classify precipitation event and non-precipitation event using input variables of RBFNNs such as DZ, DZ of Frequency(DZ_FR), SDZ, SDZ of Frequency(SDZ_FR), VGZ, VGZ of Frequency(VGZ_FR). After the event classification, in the precipitation event including non-precipitation echo, the non-precipitation echo is completely removed by the echo classifier of the second classifier step that is built as Type-2 FCM based RBFNNs. Also, parameters of classification system are acquired for effective performance using PSO(Particle Swarm Optimization). The performance results of the proposed echo classifier are compared with CZ. In the sequel, the proposed model architectures which use event classifier as well as the echo classifier of Interval Type-2 FCM based RBFNN show the superiority of output performance when compared with the conventional echo classifier based on RBFNN.