• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.393-400
• /
• 2016

Recently, there have been various researches on efficient and automatic analysis on urban environment methods that utilize the computer vision and machine learning technology. Among many new analyses, urban safety analysis has received a major attention. In order to predict more accurately on safety score and reflect the human visual perception, it is necessary to consider the generic and local information that are most important to human perception. In this paper, we use Double-column Convolutional Neural network consisting of generic and local columns for the prediction of urban safety. The input of generic and local column used re-sized and random cropped images from original images, respectively. In addition, a new learning method is proposed to solve the problem of over-fitting in a particular column in the learning process. For the performance comparison of our Double-column Convolutional Neural Network, we compare two Support Vector Regression and three Convolutional Neural Network models using Root Mean Square Error and correlation analysis. Our experimental results demonstrate that our Double-column Convolutional Neural Network model show the best performance with Root Mean Square Error of 0.7432 and Pearson/Spearman correlation coefficient of 0.853/0.840.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.6
• /
• pp.177-186
• /
• 2020

Recent advances in deep learning technology have improved image recognition performance in the field of computer vision, and serverless computing is emerging as the next generation cloud computing technology for event-based cloud application development and services. Attempts to use deep learning and serverless computing technology to increase the number of real-world image recognition services are increasing. Therefore, this paper describes how to develop an efficient deep learning based image recognition service system using serverless computing technology. The proposed system suggests a method that can serve large neural network model to users at low cost by using AWS Lambda Server based on serverless computing. We also show that we can effectively build a serverless computing system that uses a large neural network model by addressing the shortcomings of AWS Lambda Server, cold start time and capacity limitation. Through experiments, we confirmed that the proposed system, using AWS Lambda Serverless Computing technology, is efficient for servicing large neural network models by solving processing time and capacity limitations as well as cost reduction.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.39 no.1
• /
• pp.51-65
• /
• 2002

This paper presents a design method of the neural network-based controller using an indirect adaptive control method to deal with an intelligent control for chaotic nonlinear systems. The proposed control method includes the identification and control Process for chaotic nonlinear systems. The identification process for chaotic nonlinear systems is an off-line process which utilizes the serial-parallel structure of multilayer neural networks and simple state space neural networks. The control process is an on-line process which uses the trained neural networks as the system model. An error back-propagation method was used for training of identification and control for chaotic nonlinear systems. The performance of the proposed neural network controller was evaluated by application to the Duffing equation and the Lorenz equation, and the proposed controller was compared with other neural network-based controllers by computer simulations.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.1
• /
• pp.24-31
• /
• 2015

A differential codebook using M-ary phase shift keying (M-PSK) constellation as its codeword elements, is proposed for Long term evolution (LTE), LTE-Advanced (LTE-A), and/or WiMAX systems. Due to the temporal correlation of the adjacent channel, the consecutive precoding matrices are likely to be similar. This approach quantize only the differential information of the channel instead of the whole channel subspace, which virtually increase the codebook size to realize more accurate quantization of the channel. Especially, the proposed codebook has the same properties of LTE release-8 codebook that is, constant modulus, complexity reduction, and nested property. The mobile station can be designed by using a less expensive non-linear amplifier utilizing the constant modulus property. Computer simulations show that the capacity of the proposed codebook performs better than LTE release-8 codebook with the same amount of feedback information.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.3
• /
• pp.90-98
• /
• 2011

The recognition and classification of paddy rice disease are of major importance to the technical and economical aspect of agricultural industry over the world. Computer vision techniques are used to diagnose rice diseases and to efficiently manage crops. Segmentation of lesions is the most important technique to detect paddy rice disease early and accurately. A new Gaussian Mean (GM) method was proposed to segment paddy rice diseases in various color spaces. Different color spaces produced different results in segmenting paddy diseases. Thus, this empirical study was conducted with the motivation to determine which color space is best for segmentation of rice disease. It included five color spaces; NTSC, CIE, YCbCr, HSV and the normalized RGB(NRGB). The results showed that YCbCr was the best color space for optimal segmentation of the disease lesions with 98.0% of accuracy. Furthermore, the proposed method demonstrated that diseases lesions of paddy rice can be segmented automatically and robustly.

• 전자공학회논문지 IE
• /
• v.44 no.4
• /
• pp.11-18
• /
• 2007

Concept of URC does "with me wherever when, and the robot" which provides necessary service to me can be simply defined. This paper uses URC technology and various robots are implemented with a design. That is, we are going to implement that a user controls a virtual robot by communication between URC server with a design. We used an intelligent robot simulation tool, and a developer was easy, and it was intelligent, and we were connected to active URC server, and modeling did a system for simulation to be able to do an URC robot usefully. It was connected to an URC system and various robots and environments were composed with 3D, and, in this paper, a design and implementation did an intelligent robot simulation system so that it was possible by various contents development through simulation. The URC communication protocol and the URC server were based on a Planet v.1.2 ; Network Protocol, CAMUS(Context-Aware Middleware for URC Systems); URC Server, SAM(Service Agent Manager) v.1.2 ; Service API module developed in Electronics & Telecommunications Research Institute (ETRI).

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.229-237
• /
• 2014

This paper presents a video bitrate converter for baseline profile in H.264/AVC standards to control a selective coding scheme for several applications such as tactical scenes or multimedia area. Transmission channels have various capacities according to the application area, and the bitstream stored in computer should be converted in order not to exceed the capacities of a transmission channel. So the problem is how to convert compressed bitsreams of a given bit-rate into compressed bitsreams of other bit-rates. Such a specific transcoding problem in this paper is referred to as bit-rate conversion. Several researches have been done on bit-rate conversion for the bitstreams compressed by MPEG or H.264/AVC. But the existing schemes are not suitable for selective coding scheme because it needs to recover interest regions better image quality than background. So we propose a new bit-rate converter which considers the importance between interest regions and background.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.1
• /
• pp.9-14
• /
• 2013

In this paper, we propose a low complexity bilateral search SIC for OFDM in fast time-varying channels. Due to the possibility of error propagation in SIC, symbol detection ordering within the block of symbols has a significant effect on the overall performance. In this paper, the first symbol to be detected is determined based on CSEP values, and then the next symbol to be detected is selected according to the updated CSEP while bilaterally searching from the boundary of the detected symbol group. Through computer simulations, we show that the proposed method has performance improvements with almost the same computation complexity over the conventional methods in the high SNR region. It has a performance approaching the MFB, known as the performance upper bound, within 2dB at the BER of $10^{-5}$.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.7
• /
• pp.225-230
• /
• 2013

In a bandpass sampling (BPS), the frequency of the sampler is lower than that of the signal being sampled. In this method, the baseband spectrum directly appears by the sampling operation, so that it is not necessary to use any frequency down-converter, which makes the receiver's hardware simpler. The second-order BPS uses two identical BPS samplers, of which sampling times are offset by each other. By exploiting the relationship between two sampled signals, it can be possible to cancel the aliased signal component or the interference due to the bandpass sampling. In order to cancel the interference, an interpolant filter is used to manipulate the phase characteristics of the BPS sampled signal. In this paper, it is introduced a multiband interpolant filter which can simultaneously cancel multiple interference signals that have been aliased from multiple frequency bands. In case of no need of interference cancellation, another method is suggested to enhance the signal quality by 3dB. A computer simulation has been performed, and the feasibility of the suggested methods has been verified.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.40 no.12
• /
• pp.155-160
• /
• 2003

Owing to the advances in ADC and DSP technologies, signals in If band, which once had to be processed in analog technology, can new be digitally processed. This is referred to as "Digital IF" or "Digital Radio", which is a preliminary stage of SDR. Applying the digital radio technology to a multi-carrier receiver design, a processing gain is generated through an over-sampling of input data. In the digital receiver, decimation is performed for reducing the computational complexity CIC and half band filter is used together with the decimation as an anti-alising filter. The CIC filter, however, should introduce the roll-off phenomenon in the passband, which causes the receiving performance to be considerably degraded due to the distorted Passband flatness of receiving filter. In this paper, we designed a CIC roll-off compensation filter for W-CDMA digital receiver. The performance of the proposed compensation filter is confirmed through computer simulations in such a way that the BER is minimized by compensating the roll-off characteristics.off characteristics.