• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.3050-3063
• /
• 2023

Recommendation systems provide personalized products or services to online users by mining their past preferences. Collaborative filtering is a popular recommendation technique because it is easy to implement. However, with the rapid growth of the number of users in recommendation systems, collaborative filtering suffers from serious scalability and sparsity problems. To address these problems, a novel collaborative filtering recommendation algorithm is proposed. The proposed algorithm partitions the users using affinity propagation clustering, and searches for k nearest neighbors in the partition where active user belongs, which can reduce the range of searching and improve real-time performance. When predicting the ratings of active user's unrated items, mean deviation method is used to impute values for neighbors' missing ratings, thus the sparsity can be decreased and the recommendation quality can be ensured. Experiments based on two different datasets show that the proposed algorithm is excellent both in terms of real-time performance and recommendation quality.

• Communications for Statistical Applications and Methods
• /
• 제4권1호
• /
• pp.229-241
• /
• 1997

We consider discrimination curve and minimum dwell time for Poisson distribution and Poisson-power function distribution. Let the random variable X has Poisson distribution with mean .lambda.. For the hypothesis testing H$\_$0/:.lambda. = t vs. H$\_$1/:.lambda. = d (d$\_$0/ if X.leq.c. Since a critical value c can not be determined to satisfy both types of errors .alpha. and .beta., we considered discrimination curve that gives the maximum d such that it can be discriminated from t for a given .alpha. and .beta.. We also considered an algorithm to compute the minimum dwell time which is needed to discriminate at the given .alpha. and .beta. for the Poisson counts and proved its convergence property. For the Poisson-power function distribution, we reject H$\_$0/ if X.leq..'{c}.. Since a critical value .'{c}. can not be determined to satisfy both .alpha. and .beta., similar to the Poisson case we considered discrimination curve and computation algorithm to find the minimum dwell time for the Poisson-power function distribution. We prosent this algorithm and an example of computation. It is found that the minimum dwell time algorithm fails for the Poisson-power function distribution if the aiming error variance .sigma.$\^$2/$\_$2/ is too large relative to the variance .sigma.$\^$2/$\_$1/ of the Gaussian distribution of intensity. In other words, if .ell. is too small, we can not find the minimum dwell time for a given .alpha. and .beta..

• The Journal of the Acoustical Society of Korea
• /
• 제19권1E호
• /
• pp.22-26
• /
• 2000

In this paper, the DS/CDMA PN code acquisition system with nonlinear transmitter power amplifier based on digital matched filter (DMF) which has the rapid acquisition time is presented and the performance is evaluated in terms of mean acquisition time, detection probability, and signal to interference under multiuser environment. The performance is presented with respect to the output backoff of the nonlinear amplifier and the correlation window.

• 한국경영과학회지
• /
• 제17권3호
• /
• pp.181-193
• /
• 1992

This paper shows the model of a consecutive-k-out-of-n :G system with common-cause outages. The objective is to analytically derive the mean operating time between failures for a non-repairable component system. The average failure time of a system and the system availability are also considered. Then, the model is extended to a system with repairable components and unrestricted repair, in which service times are exponentially distributed.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(1)
• /
• pp.209-212
• /
• 2000

In this paper, effect of imperfect power control on performance of a pseudonoise (PN) code tracking loop is analyzed and simulated for a direct-sequence/code-division multiple access (DS/CDMA) system. The multipath fading channel is modeled as a two-ray Rayleigh fading model. Power control error is modeled as a log-normally distributed random variable. The tracking performance of DLL (delay-locked-loop) is evaluated in terms of tracking jitter and mean-time-to-lose-lock (MTLL). From the simulation results, it is shown that the PN tracking performance is very sensitive to the power control error.

• Journal of the Korean Statistical Society
• /
• 제34권3호
• /
• pp.173-183
• /
• 2005

The Box-Cox power transformation is generally used for variance stabilization. Recently, Shin and Kang (2001) showed, under the Box-Cox transformation, invariant properties to the original model under the large mean and relatively small variance assumptions in time series analysis. In this paper we obtain some invariant properties in spatial statistics. Spatial statistics, Invariant Property, Variogram, Box-Cox power Transformation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3630-3656
• /
• 2018

Degree distribution can provide basic information for structural characteristics and internal relationship in social network. It is a critical procedure for social network topology analysis. In this paper, based on the mean-field theory, we study a special type of social network with exponential distribution of time intervals. First of all, in order to improve the accuracy of analysis, we propose a spreading coefficient algorithm based on intimate relationship, which determines the number of the joined members through the intimacy among members. Then, simulation show that the degree distribution of follows the power-law distribution and has small-world characteristics. Finally, we compare the performance of our algorithm with the existing algorithms, and find that our algorithm improves the accuracy of degree distribution as well as reducing the time complexity significantly, which can complete 29.04% higher precision and 40.94% lower implementation time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.4099-4113
• /
• 2022

In this paper, we propose improved maximum access delay time, noise variance, and power delay profile (PDP) estimation schemes for orthogonal frequency division multiplexing (OFDM) system in multipath fading channels. To this end, we adopt the approximate maximum likelihood (ML) estimation strategy. For the first step, the log-likelihood function (LLF) of the received OFDM symbols is derived by utilizing only the cyclic redundancy induced by cyclic prefix (CP) without additional information. Then, the set of the initial path powers is sub-optimally obtained to maximize the derived LLF. In the second step, we can select a subset of the initial path power set, i.e. the maximum access delay time, so as to maximize the modified LLF. Through numerical simulations, the benefit of the proposed method is verified by comparison with the existing methods in terms of normalized mean square error, erroneous detection, and good detection probabilities.

• 응용통계연구
• /
• 제29권7호
• /
• pp.1373-1383
• /
• 2016

풍력에너지 산업이 발전하고 풍력발전에 대한 의존율이 높아짐에 따라 안정적인 공급이 중요해지고 있다. 원활한 전력수급계획을 세우기 위해서 풍력발전량을 정확히 예측하는 것이 중요하다. 본 논문에서는 강원도 평창 횡계리에 설치된 대관령 2풍력(2MW 1기)의 시간별 풍력발전 데이터와 강원도 대관령 기상대에서 관측되는 시간별 풍속과 풍향 데이터를 기상청 지상관측자료에서 수집하여 연구하였다. 풍력발전량 예측을 위하여 신경망 모형과 시계열 모형인 ARMA, ARMAX, ARMA-GARCH, Holt Winters 모형을 비교하였다. 모형 간 예측력을 비교하기 위해 mean absolute error(MAE)를 사용하였다. 모형의 예측 성능 비교 결과 1시간에서 3시간의 단기 예측에 있어서 ARMA-GARCH 모형이 우수한 예측력을 보였다. 6시간 이후 예측에서는 신경망 모형이 우수한 예측을 보였다.

• 한국컴퓨터정보학회논문지
• /
• 제19권4호
• /
• pp.25-33
• /
• 2014

본 논문에서는 멀티코어 프로세서 상에서 실시간 작업들의 데드라인들을 만족하면서 전력 소모량의 확률적 기대값을 최소화하는 문제를 해결하는 스케쥴링 기법을 제시하였다. 제시된 기법에서는 주어진 작업들의 불확실한 계산량을 과거의 계산량 분포에 기반하여 확률적 계산량으로 변환하고, 한정된 개수의 이산적 클락 주파수 값들을 이용하여 변환된 확률적 계산량의 전력 소모 기대 값을 최소화한다. 또한 시스템의 부하량이 적을 때에는 누수 전력을 고려하여 전체 코어들 중에서 일부의 코어들만을 사용하고 나머지 코어들의 전원을 소등시켜서 전력 소모량을 줄인다. 성능평가 실험에서 제시된 기법이 기존 방법의 전력 소모량을 최대 69%까지 감소시킴을 확인하였다.