• Korean Journal of Cognitive Science
• /
• v.12 no.1_2
• /
• pp.35-42
• /
• 2001

In this paper. a document is represented as a weighted graph called a text relationship map. In the graph. a node represents a vector of nouns in a sentence, an edge completely connects other nodes. and a weight on the edge is a value of the similarity between two nodes. The similarity is based on the word overlap between the corresponding nodes. The importance of a node. called an aggregate similarity in this paper. is defined as the sum of weights on the links connecting it to other nodes on the map. In this paper. we present a Korean text summarization system using the aggregate similarity. To evaluate our system, we used two test collection, one collection (PAPER-InCon) consists of 100 papers in the field of computer science: the other collection (NEWS) is composed of 105 articles in the newspapers and had built by KOROlC. Under the compression rate of 20%. we achieved the recall of 46.6% (PAPER-InCon) and 30.5% (NEWS) and the precision of 76.9% (PAPER-InCon) and 42.3% (NEWS).

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.37-42
• /
• 2021

NOMA (Non-orthogonal multiple Access) system has been focused on the next generation cellular system for higher spectral efficiency. However, this requires user scheduling as the NOMA system is a multi-user system which accesses simultaneously. There are two representative scheduling schemes, proportionate scheduling (FP) and cumulative distribution function (CFD) scheduling. The PF scheduling is applied, the cell edge user is hard to obtain a transmit opportunity. Recently, CDF scheduling is obviously noted that it offers the same possibility of transmission for a user regardless of the location in a cell. We consider an uplink NOMA system with CDF scheduling, and obtain the channel access probabilities, the outage probabilities of the system with different number of users and different kinds of weights through simulation. The results indicate that the likelihood of each user accessing the channel is the same and the probability of failure decreases as the number of users increases. We found that the effect of the probability of failure is negligible as the weight of the cell edge user increases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.16-37
• /
• 2022

Accurate liver segment segmentation based on radiological images is indispensable for the preoperative analysis of liver tumor resection surgery. However, most of the existing segmentation methods are not feasible to be used directly for this task due to the challenge of exact edge prediction with some tiny and slender vessels as its clinical segmentation criterion. To address this problem, we propose a novel deep learning based segmentation model, called Boundary-Aware Dual Attention Liver Segment Segmentation Model (BADA). This model can improve the segmentation accuracy of liver segments with enhancing the edges including the vessels serving as segment boundaries. In our model, the dual gated attention is proposed, which composes of a spatial attention module and a semantic attention module. The spatial attention module enhances the weights of key edge regions by concerning about the salient intensity changes, while the semantic attention amplifies the contribution of filters that can extract more discriminative feature information by weighting the significant convolution channels. Simultaneously, we build a dataset of liver segments including 59 clinic cases with dynamically contrast enhanced MRI(Magnetic Resonance Imaging) of portal vein stage, which annotated by several professional radiologists. Comparing with several state-of-the-art methods and baseline segmentation methods, we achieve the best results on this clinic liver segment segmentation dataset, where Mean Dice, Mean Sensitivity and Mean Positive Predicted Value reach 89.01%, 87.71% and 90.67%, respectively.

• Transactions on Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.17-20
• /
• 2024

This paper presents a novel lightweight object detection model tailored for low-powered edge devices, addressing the limitations of traditional resource-intensive computer vision models. Our proposed detector, inspired by the Single Shot Detector (SSD), employs a compact yet robust network design. Crucially, it integrates an 'enhancer block' that significantly boosts its efficiency in detecting smaller objects. The model comprises two primary components: the Light_Block for efficient feature extraction using Depth-wise and Pointwise Convolution layers, and the Enhancer_Block for enhanced detection of tiny objects. Trained from scratch on the Udacity Annotated Dataset with image dimensions of 300x480, our model eschews the need for pre-trained classification weights. Weighing only 5.5MB with approximately 0.43M parameters, our detector achieved a mean average precision (mAP) of 27.7% and processed at 140 FPS, outperforming conventional models in both precision and efficiency. This research underscores the potential of lightweight designs in advancing object detection for edge devices without compromising accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.7A
• /
• pp.710-716
• /
• 2007

In this paper, a new scheme of downlink co-channel interference (CCI) cancellation in OFDM cellular networks is introduced for users at the cell-edge. Coordinated symbol transmission between base stations (BS) is operated where the same symbol is transmitted from different BS on different sub-carriers. At the mobile station (MS) receiver, we introduce a soft decision maximum likelihood CCI canceler and a modified maximum ratio combining (M-MRC) to obtain an estimate of the transmitted symbols. Weights used in the combining method are derived from the channels coefficients between the cooperated BSs and the MS. Simulations show that the proposed scheme works well under frequency-selective channels and frequency non-selective channels. A gain of 9 dB and 6 dB in SIR is obtained under multipath fading and flat-fading channels, respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5A
• /
• pp.409-416
• /
• 2007

In cellular orthogonal frequency division multiplexing (OFDM) networks, co-channel interference (CCI) leads to severe degradation in the BER performance. To solve this problem, maximum-likelihood estimation (MLE) CCI cancellation scheme has been proposed in the literature. MLE CCI cancellation scheme generates weighted replicas of the transmitted signals where weights represent the estimated channel transfer functions. The replica with the smallest Euclidean distance from the received signal is selected and data are detected. When the received power of the desired and interference signals are nearly the same, the BER performance is degraded. In this paper, we propose a closed-loop power control (PC) scheme capable of detecting the equal received power situation at the mobile station (MS) receiver by using the newly introduced parameter power ratio (PR). When this situation is detected, the MS sends a feedback to the desired base station (BS) which boosts the transmission power in the next frame. At cell edge where signal to interferer ratio (SIR) is considered to have average value between -5 dB and 10 dB, computer simulations show that the proposed CCI cancellation scheme has a gain of 7 dB at 28 Km/h.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.6 s.324
• /
• pp.9-15
• /
• 2004

In MIMO-OFDM systems, conventional channel estimation techniques using comb type training symbols give relatively large mean squared errors(MSEs) at the edge subcarriers. To reduce the MSEs at these subcarriers, a cyclic comb type training structure is proposed. In the proposed cyclic training structure, all types of training symbols are transmitted cyclically at each antenna. At the receiver, the channel frequency responses that are estimated using each training symbol are averaged with weights obtained from the corresponding MSEs. Computer simulations showed that the proposed cyclic training structure gives more SNR gain than the conventional training structure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1043-1064
• /
• 2020

A kind of Subjective Imaging Effect Assessment (SIEA) method and its applications on intelligent imaging terminal design in engineering site are presented. First, some visual assessment indices are used to characterize the imaging effect: the image brightness, the image brightness uniformity, the color image contrast, the image edge blur, the image color difference, the image saturation, the image noise, and the integrated imaging effect index. A linear weighted function is employed to carry out the SIEA computation and the Analytic Hierarchy Process (AHP) technique is used to estimate its weights. Second, a SIEA software is developed. It can play images after the settings of assessment index or assessment reaction time, etc. Third, two cases are used to illustrate the application effects of proposed method: the image enhancement system design for surveillance camera and the imaging environment perception system design for intelligent lighting terminal. A Prior Sequential Stimulus (PSS) experiment is proposed to improve the evaluation stability of SIEA method. Many experiment results have shown the proposed method can realize a stable system design or parameters setting for the intelligent imaging terminal in engineering site.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.10
• /
• pp.1-9
• /
• 2003

In GRID environments, an efficient load balancing algorithm should be adopted since the system performances of GRID system are not homogeneous. In this work, a new two-step mesh-partitioning scheme based on the graph-partitioning scheme was introduced to consider the difference of system performance. In the two-step mesh-partitioning scheme, the system performance weights were calculated to reflect the effect of heterogeneous system performances and WEVM(Weighted Edge and vertex Method) was adopted to minimize the increase' of communications. Numerical experiments were carried out in multi-cluster environment and WAN (Wide Area Network) environment to investigate the effectiveness of the two-step mesh-partitioning scheme.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.8
• /
• pp.74-86
• /
• 1994

In this paper a hierarchical stereo matching algorithm to obtain the disparity in wavelet transformed domain by using locally adaptive window and weights is proposed. The pyramidal structure obtained by wavelet transform is used to solve the loss of information which the conventional Gaussian or Laplacian pyramid have. The wavelet transformed images are decomposed into the blurred image the horizontal edges the vertical edges and the diagonal edges. The similarity between each wavelet channel of left and right image determines the relative importance of each primitive and make the algorithm perform the area-based and feature-based matching adaptively. The wavelet transform can extract the features that have the dense resolution as well as can avoid the duplication or loss of information. Meanwhile the variable window that needs to obtain precise and stable estimation of correspondense is decided adaptively from the disparities estimated in coarse resolution and LL(low-low) channel of wavelet transformed stereo image. Also a new relaxation algorithm that can reduce the false match without the blurring of the disparity edge is proposed. The experimental results for various images show that the proposed algorithm has good perfpormance even if the images used in experiments have the unfavorable conditions.