• Journal of Appropriate Technology
• /
• v.7 no.1
• /
• pp.33-40
• /
• 2021

The government of Uganda, which belongs to East Africa, approved the National Vison Statement, "A transformed Ugandan society from a Peasant to a Modern and Prosperous Country within 30 years". However, the Uganda is facing the problem of unbalanced development between urban and rural area in spite of the government's efforts. In particular, the urban-rural education gap is emerging as a problem that could negatively affect national development plans. In this paper, we explain the reasons why Uganda's urban-rural educational imbalance is accelerating. In addition, we would like to introduce a way to reduce the educational imbalance by using appropriate technology of ICT such as the electronic library system.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.251-256
• /
• 2022

범주 불균형은 분류 모델이 다수 범주에 편향되게 학습되어 소수 범주에 대한 분류 성능을 떨어뜨리는 문제를 야기한다. 언더 샘플링 기법은 다수 범주 데이터의 수를 줄여 소수 범주와 균형을 이루게하는 대표적인 불균형 해결 방법으로, 텍스트 도메인에서의 기존 언더 샘플링 연구에서는 단어 임베딩과 랜덤 샘플링과 같은 비교적 간단한 기법만이 적용되었다. 본 논문에서는 트랜스포머 기반 문장 임베딩과 군집화 기반 샘플링 방법을 통해 텍스트 데이터의 정보 손실을 최소화하는 언더샘플링 방법을 제안한다. 제안 방법의 검증을 위해, 감성 분석 실험에서 제안 방법과 랜덤 샘플링으로 추출한 훈련 세트로 모델을 학습하고 성능을 비교 평가하였다. 제안 방법을 활용한 모델이 랜덤 샘플링을 활용한 모델에 비해 적게는 0.2%, 많게는 2.0% 높은 분류 정확도를 보였고, 이를 통해 제안하는 군집화 기반 언더 샘플링 기법의 효과를 확인하였다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.507-511
• /
• 2020

오픈 도메인 대화에서 텍스트에 나타난 태도나 성향과 같은 화자의 주관적인 감정정보를 분석하는 것은 사용자들에게서 풍부한 응답을 이끌어 내고 동시에 제공하는 목적으로 사용될 수 있다. 하지만 한국어 감성분석에서 기존의 대부분의 연구들은 긍정과 부정 두개의 클래스 분류만을 다루고 있고 이는 현실 화자의 감정 정보를 정확하게 분석하기에는 어려움이 있다. 또한 최근에 오픈한 다중클래스로된 한국어 대화 감성분석 데이터셋은 중립 클래스가 전체 데이터셋의 절반을 차지하고 일부 클래스는 사용하기에 매우 적은, 다시 말해 클래스 간의 데이터 불균형 문제가 있어 다루기 굉장히 까다롭다. 이 논문에서 우리는 일곱개의 클래스가 존재하는 한국어 대화에서 세션들을 효율적으로 분류하는 기법들에 대해 논의한다. 우리는 극심한 클래스 불균형에도 불구하고 76.56 micro F1을 기록하였다.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.9-15
• /
• 2024

In this paper, a Diffusion Multi-step Classifier (DMC) is proposed to address the imbalance issue in credit prediction. DMC utilizes a Diffusion Model to generate continuous numerical data from credit prediction data and creates categorical data through a Multi-step Classifier. Compared to other algorithms generating synthetic data, DMC produces data with a distribution more similar to real data. Using DMC, data that closely resemble actual data can be generated, outperforming other algorithms for data generation. When experiments were conducted using the generated data, the probability of predicting delinquencies increased by over 20%, and overall predictive accuracy improved by approximately 4%. These research findings are anticipated to significantly contribute to reducing delinquency rates and increasing profits when applied in actual financial institutions.

• The KIPS Transactions:PartC
• /
• v.16C no.6
• /
• pp.783-790
• /
• 2009

The necessity of wireless sensor networks is increasing in the recent years. So many researches are studied in wireless sensor networks. The clustering algorithm provides an effective way to prolong the lifetime of the wireless sensor networks. The one-hop routing of LEACH algorithm is an inefficient way in the energy consumption of cluster-head, because it transmits a data to the BS(Base Station) with one-hop. On the other hand, other clustering algorithms transmit data to the BS with multi-hop, because the multi-hop transmission is an effective way. But the multi-hop routing of other clustering algorithms which transmits data to BS with multi-hop have a data bottleneck state problem. The unequal clustering algorithm solved a data bottleneck state problem by increasing the routing path. Most of the unequal clustering algorithms partition the nodes into clusters of unequal size, and clusters closer to the BS have small-size the those farther away from the BS. However, the energy consumption of cluster-head in unequal clustering algorithm is more increased than other clustering algorithms. In the thesis, I propose an energy efficient unequal clustering algorithm which decreases the energy consumption of cluster-head and solves the data bottleneck state problem. The basic idea is divided a three part. First of all I provide that the election of appropriate cluster-head. Next, I offer that the decision of cluster-size which consider the distance from the BS, the energy state of node and the number of neighborhood node. Finally, I provide that the election of assistant node which the transmit function substituted for cluster-head. As a result, the energy consumption of cluster-head is minimized, and the energy consumption of total network is minimized.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.20 no.1
• /
• pp.21-28
• /
• 2009

DFT-spread OFDM(Discrete Fourier Transform-Spread Orthogonal Frequency Division Multiplexing) is very effective for solving the PAPR(Peak-to-Average Power Ratio) problem. Therefore, the SC-FDMA(Single Carrier-Frequency Division Multiple Access) which is basically same to the DFT spread OFDM was adopted as the uplink standard of the 3GPP LTE ($3^{rd}$ Generation Partnership Project Long Term Evolution). Unlike the ordinary OFDM system, the SC-FDMA using DFT spreading method is vulnerable to the ICI(Inter-Carrier Interference) problem caused by the phase noise and IQ(In-phase/Quadrature) imbalance and effected FDE(Frequency Domain Equalizer). In this paper, the ICI effects from the phase noise and IQ imbalance which can be problems in uplink transmission are analyzed according the back-off level of HPA. Next, we propose the equalizer algorithm to remove the ICI effects. This proposed equalizer based on the FDE can be considered as up-graded and improved version of PNS(Phase Noise Suppression) algorithm. This proposed equalizer effectively compensates the ICI resulting from the phase noise and IQ imbalance. Finally, through the computer simulation, it can be shown that about SNR=14 dB is required for the $BER=10^{-4}$ after ICI compensation when the back-off is 4.5 dB, $\varepsilon=0.005$, $\phi=5^{\circ}$, and $pn=0.06\;rad^2$.

• Information Systems Review
• /
• v.9 no.1
• /
• pp.45-65
• /
• 2007

In medical industry, health insurance bill audit is unique and essential process in general hospitals. The health insurance bill audit process is very important because not only for hospital's profit but also hospital's reputation. Particularly, at the large general hospitals many related workers including analysts, nurses, and etc. have engaged in the health insurance bill audit process. This paper introduces a case of health insurance bill audit for finding reducible health insurance bill cases using decision tree induction techniques at a large general hospital in Korea. When supervised learning methods had been tried to be applied, one of major problems was data imbalance problem in the health insurance bill audit data. In other words, there were many normal(passing) cases and relatively small number of reduction cases in a bill audit dataset. To resolve the problem, in this study, well-known methods for imbalanced data sets including over sampling of rare cases, under sampling of major cases, and adjusting the misclassification cost are combined in several ways to find appropriate decision trees that satisfy required conditions in health insurance bill audit situation.

• Information Systems Review
• /
• v.18 no.2
• /
• pp.23-38
• /
• 2016

Previous studies on information systems (IS) and finance suggest that information on stock message boards influence the investment decisions of individual investors. However, how information on online stock message boards influences an individual investor's buy or sell decisions is unclear. To address this research question, we investigate the relationship between a number of posts on stock message boards and order imbalance in stock markets. Order imbalance is defined as the difference between the daily sum of buy-side shares traded and the daily sum of sell-side shares traded. Therefore, order imbalance can suggest the direction of trades and the strength of the direction with trading volumes. In this regard, this study examines how the number of posts (information on stock message boards) influences order imbalance (stock trading behavior). We collected about 46,077 messages of 40 companies on the Korea Composite Stock Price Index from Paxnet, the most popular Korean online stock message board. The messages we collected were divided based on in-trading and after-trading hours to examine the relationship between the numbers of posts and trading volumes. We also collected order imbalance data on individual investors. We then integrated the balanced panel data sets and analyzed them through vector regression. We found that the number of posts on online stock message boards is positively related to prior order imbalance. We believe that our findings contribute to knowledge in IS and finance. Furthermore, this study suggests that investors should carefully monitor information on stock message boards to understand stock market sentiments.

• Korea journal of population studies
• /
• v.20 no.1
• /
• pp.65-96
• /
• 1997

The main purpose of this study is to explore the determinants of sex ratio imbalance at birth in Taegu which has experienced the extremely imbalanced sex ratio at birth since mid-1980s. This paper attempts to compare the determinants of sex ratio imbalance at birth, such as sex discrimination against women, son preference, prenatal sex identification followes by sex-selective induced abortions, among married women aged 25 to 44 in Taegu with those in Bay area, California in USA. The research is based on the survey data which were conducted in Taegu, Repulic of Korea and Bay area, California in USA. The findings of this analysis suggest that married women in Taegu are more likely to feel sex discrimination against women than married women in Bay area. Furthermore, the percentage of married women's effort for son bearing before pregnancy is much higher than that of married women in Bay area. We also have found that the percentage of sex-selective induced abortion in Taegu is six times higher than that of married women in Bay area. According to the logistic regression analysis, the determinants of sex-selective induced abortion among married women in Taegu are discrimination against women, son preference, prenatal sex identification. On the other hand, age is the only variable which has an important impact on sex-selective induced abortion among married women in Bay area. From the findings of this study, we can conclude that son preference based on Cofucianism is the most important impact on sex ratio imbalance at birth in Taegu where son preference is much stronger than other regions in Korea. The phenomenon of extremely imbalanced sex ratio at birth in Taegu is the result of combination of these factors, such as strong son preference, seeking to have at least one son within small family size, and prenatal sex identification followed by sex-selective induced abortion.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.3-10
• /
• 2014

Direct conversion receiver(DCR) gets noticed for integration and cost reduction of wireless communication systems instead of the heterodyne receiver which uses complex filter. But DCR has several factors in performance degradation. One of them is I/Q imbalance phenomenon, that is amplitude and phase mismatch between real and imaginary part of receiver. Accordingly, researches are being carried to improve the I/Q imbalance problem. However, the tendency of the broaden bandwidth of communication systems, low pass filter(LPF) mismatch problem affects severely in I/Q mismatch phenomenon at the DCR. To study this problem, we generated 10MHz broadband signal and shifted it ${\pm}8MHz$ from the center frequency. The signal is affected by LPF mismatch and it appears as frequency selective distortion. Thus, LPF mismatch model is added to I/Q imbalance model which conventionally dealt with amplitude and phase mismatches. In addition, we proposed the compensation method for each factors of mismatch. As the simulation results, the proposed I/Q mismatch compensator resolves the frequency selective distortion which occurred by the existing LPF mismatch.