• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.1058-1070
• /
• 1999

In this paper, we propose a control model which can control the burst input messages of the BSC(Base Station controller) in mobile communication systems more efficiently and reliably, by dividing the input messages characteristically and using multiprocessor system. Using M/M/c/K queueing model, we briefly analyze proposed model to get characteristic parameters which are required to performance improvement. On the base of the results, we compare our proposed model with the conventional one by using SLAM II with regard to the following factors : the call blocking rate of the input message, the distribution of average queue length, the utilization of process controller(server), and the distribution of average waiting time in queue. In addition, we modified our model which has overload control function for burst input messages, and analyzed its performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.19-28
• /
• 2022

Recently, cryptocurrency has attracted much attention, and price prediction studies of cryptocurrency have been actively conducted. Especially, efforts to improve the prediction performance by applying the deep learning model are continuing. LSTM (Long Short-Term Memory) model, which shows high performance in time series data among deep learning models, is applied in various views. However, it shows low performance in cryptocurrency price data with high volatility. Although, to solve this problem, new input features were found and study was conducted using them, there is a lack of study on input features that drop predictive performance. Thus, in this paper, we collect the recent trends of six cryptocurrencies including Bitcoin and Ethereum and analyze effects of input features on the cryptocurrency price predictive performance through statistics and deep learning. The results of the experiment showed that cryptocurrency price predictive performance the best when open price, high price, low price, volume and price were combined except for rate of closing price fluctuation.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.1
• /
• pp.18-23
• /
• 2008

In this paper, we propose the input image selection-method to improve the reconstructed high-resolution (HR) image quality. To obtain ideal super-resolution (SR) reconstruction image, all input images are well-registered. However, the registration is not ideal in practice. Due to this reason, the selection of input images with low registration error (RE) is more important than the number of input images in order to obtain good quality of a HR image. The suitability of a candidate input image can be determined by using statistical and restricted registration properties. Therefore, we propose the proper candidate input Low Resolution(LR) image selection-method as a pre-processing for the SR reconstruction in automatic manner. In video sequences, all input images in specified region are allowed to use SR reconstruction as low-resolution input image and/or the reference image. The candidacy of an input LR image is decided by the threshold value and this threshold is calculated by using the maximum motion compensation error (MMCE) of the reference image. If the motion compensation error (MCE) of LR input image is in the range of 0 < MCE < MMCE then this LR input image is selected for SR reconstruction, else then LR input image are neglected. The optimal reference LR (ORLR) image is decided by comparing the number of the selected LR input (SLRI) images with each reference LR input (RLRI) image. Finally, we generate a HR image by using optimal reference LR image and selected LR images and by using the Hardie's interpolation method. This proposed algorithm is expected to improve the quality of SR without any user intervention.

• The KIPS Transactions:PartD
• /
• v.18D no.4
• /
• pp.225-236
• /
• 2011

Various applications of LBS (Location Based Services) are being developed to provide the customized service depending on user's location with progress of wireless communication technology and miniaturization of personalized device. To effectively process an amount of vehicles' location data, LBS requires the techniques such as vehicle observation, data communication, data insertion and search, and user query processing. In this paper, we propose the historical location index, GIP-FB (Group Insertion tree with Flexible Buffer Node) and the flexible buffer node technique to adjust the cost of data insertion and search. the designed GIP+ based index employs the buffer node and the projection storage to cut the cost of insertion and search. Besides, it adjusts the cost of insertion and search by changing the number of line segments of the buffer node with user defined time interval. In the experiment, the buffer node size influences the performance of GIP-FB by changing the number of non-leaf node of the index. the proposed flexible buffer node is used to adjust the performance of the historical location index depending on the applications of LBS.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.7
• /
• pp.1113-1119
• /
• 2002

In this paper, it was presented that broadly delivered scanner devices can also used in finger print recognition process and then modified existing steps of fingerprint image Processing. First, using the adaptive binary method, that effect was certified already, increased the effect of the results. And then, applying table mapping methods that looks for elements from look-up table, decreased the processing time, too. Finally, it was presented that ridge-direction characteristics extracted from these processes can used effectively In the area of fingerprint recognition system.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.1120-1128
• /
• 1999

The model-based object recognition is defined as a graph matching process between model images and an input image. In this paper, a graph matching problem is modeled as a n optimization problems and a genetic algorithm is proposed to solve the problems. For this work, fitness function, data structured and genetic operators are developed The simulation results are shown that the proposed genetic algorithm can match feature points between model image and input image for recognition of partially occluded two-dimensional objects. The performance fo the proposed technique is compare with that of a neural network technique.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.2
• /
• pp.148-155
• /
• 1995

When we analize many amount of patterns, it is necessary for these patterns are to be clustering into several groups according to a certain evaluation function. This process, in case that there are lots of input patterns, needs a considerable amount of computations and is reqired parallel algorithm for these. To solve this problem, this paper propose parallel clustering algorithm which parallelized k-means algorithm and implemented it under the MIMD parallel computer based message passing. The result is through the experiment and performance analysis, that this parallel algorithm is appropriate in case these are many input patterns.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.2
• /
• pp.15-22
• /
• 2002

In this paper, we proposed the face recognition algorithm which can be used for a security system. The distance and angle of the face features are used in the conventional method, but the proposed method used the genetic algorithm which selects image to best fit the input image in the database images. The performance of proposed algorithm is verified through the simulation. The results of proposed method show good performance.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.2
• /
• pp.82-87
• /
• 2003

In this paper, the color matching algorithm is Proposed for stitching machine. The matched embroidery color threads are selected by using the proposed algorithm from a computer files which is designed on the computer or scanned from the drawings designed by an artist. The proposed algorithm finds the best matching nearest colors from the given embroidery color threads . The multiple candidates owing to have the equal distance in the CIE color space are further processed to find nearest dominant color. The color dithering method will be useful for reproducing original design with high fidelity.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.12
• /
• pp.3265-3274
• /
• 1998

본 논문에서는 인간의 칼랄 인식 특성인 명도, 채도 및 색조의 관계를 학습시킨 신경회로망을 이용하여 열화된 영상의 채도 부분을 향상하는 칼라영상향상법으 제안하였다. 제안한 방법은 우선 표준영상으로부터 여러 단계 열화된 영상들로부터 얻은 다양한 명도, 채도 및 색조의 관계를 신경회로망의 입력으로 하고 표준영상의 채도를 목표차로 해서 신경회로망을 학습시킨다. 그리고 이렇게 학습된 신경회로망에 열화된 영상의 명도, 채도, 색조 그리고 향상시킨 명도를 입력하면 향상된 채도를 얻을 수 있는 칼라영상향상방법이다. 본 논문에서는 제안한 방법이 기존의 칼라영상향상법에서 가장 문제가 되었던 영상 향상 시 칼라범위를 초과하는 문제와 채도 향상비의 인위적 선택문제를 해결하고 채도의 대비를 향상시켜 선명한 영상을 얻을 수 있는 방법임을 밝혔다.