• Title/Summary/Keyword: Optimal threshold

검색결과 538건 처리시간 0.029초

비정규 혼합분포에서의 최적분류점 (Optimal Thresholds from Non-Normal Mixture)

  • 홍종선;주재선
    • 응용통계연구
    • /
    • 제23권5호
    • /
    • pp.943-953
    • /
    • 2010
  • 신용평가연구에서 확률변수 스코어와 정상과 부도상태의 모수공간으로 정의된 혼합분포에서 확률밀도함수의 관계식으로 최적분류점을 추정하고 이에 대응하는 오류합의 크기를 비교하는 연구가 정규분포의 가정하에 이루어져있는데 본 연구에서는 비정규분포인 와이블, 로지스틱 그리고 감마분포로 확장하여 가설검정을 이용하는 방법과 전체정확도와 진실율을 최대화하는 방법에 의한 최적분류점을 각각 구하고 최적분류점에 대응하는 제I종과 제II종 오류합의 크기를 비교하여 효율성을 비교 토론한다.

Optimal Control Of Two-Hop Routing In Dtns With Time-Varying Selfish Behavior

  • Wu, Yahui;Deng, Su;Huang, Hongbin
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제6권9호
    • /
    • pp.2202-2217
    • /
    • 2012
  • The transmission opportunities between nodes in Delay Tolerant Network (DTNs) are uncertain, and routing algorithms in DTNs often need nodes serving as relays for others to carry and forward messages. Due to selfishness, nodes may ask the source to pay a certain reward, and the reward may be varying with time. Moreover, the reward that the source obtains from the destination may also be varying with time. For example, the sooner the destination gets the message, the more rewards the source may obtain. The goal of this paper is to explore efficient ways for the source to maximize its total reward in such complex applications when it uses the probabilistic two-hop routing policy. We first propose a theoretical framework, which can be used to evaluate the total reward that the source can obtain. Then based on the model, we prove that the optimal forwarding policy confirms to the threshold form by the Pontryagin's Maximum Principle. Simulations based on both synthetic and real motion traces show the accuracy of our theoretical framework. Furthermore, we demonstrate that the performance of the optimal forwarding policy with threshold form is better through extensive numerical results, which conforms to the result obtained by the Maximum Principle.

Optimal Strategies for Cooperative Spectrum Sensing in Multiple Cross-over Cognitive Radio Networks

  • Hu, Hang;Xu, Youyun;Liu, Zhiwen;Li, Ning;Zhang, Hang
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제6권12호
    • /
    • pp.3061-3080
    • /
    • 2012
  • To improve the sensing performance, cooperation among secondary users can be utilized to collect space diversity. In this paper, we focus on the optimization of cooperative spectrum sensing in which multiple cognitive users efficiently cooperate to achieve superior detection accuracy with minimum sensing error probability in multiple cross-over cognitive radio networks. The analysis focuses on two fusion strategies: soft information fusion and hard information fusion. Under soft information fusion, the optimal threshold of the energy detector is derived in both noncooperative single-user and cooperative multiuser sensing scenarios. Under hard information fusion, the optimal randomized rule and the optimal decision threshold are derived according to the rule of minimum sensing error (MSE). MSE rule shows better performance on improving the final false alarm and detection probability simultaneously. By simulations, our proposed strategy optimizes the sensing performance for each cognitive user which is randomly distributed in the multiple cross-over cognitive radio networks.

Improved Single-Tone Frequency Estimation by Averaging and Weighted Linear Prediction

  • So, Hing Cheung;Liu, Hongqing
    • ETRI Journal
    • /
    • 제33권1호
    • /
    • pp.27-31
    • /
    • 2011
  • This paper addresses estimating the frequency of a cisoid in the presence of white Gaussian noise, which has numerous applications in communications, radar, sonar, and instrumentation and measurement. Due to the nonlinear nature of the frequency estimation problem, there is threshold effect, that is, large error estimates or outliers will occur at sufficiently low signal-to-noise ratio (SNR) conditions. Utilizing the ideas of averaging to increase SNR and weighted linear prediction, an optimal frequency estimator with smaller threshold SNR is developed. Computer simulations are included to compare its mean square error performance with that of the maximum likelihood (ML) estimator, improved weighted phase averager, generalized weighted linear predictor, and single weighted sample correlator as well as Cramer-Rao lower bound. In particular, with smaller computational requirement, the proposed estimator can achieve the same threshold and estimation performance of the ML method.

동적 임계값을 이용한 메모리 소거 (Dynamic Threshold based Even-wear Leveling Policies)

  • 박제호
    • 반도체디스플레이기술학회지
    • /
    • 제6권2호
    • /
    • pp.5-10
    • /
    • 2007
  • According to the advantageous features of flash memory, its exploitation and application in mobile and ubiquitous related devices as well as voluminous storage devices is being increased rapidly. The inherent properties that are determined by configuration of flash memory unit might restrict the promising expansion in its utilization. In this paper, we study policies based on threshold values, instead of using global search, in order to satisfy our objective that is to decrease the necessary processing cost or penalty for recycling of flash memory space at the same time minimizing the potential degradation of performance. The proposed cleaning methods create partitions of candidate memory regions, to be reclaimed as free, by utilizing global or dynamic threshold values. The impact of the proposed policies is evaluated through a number of experiments, the composition of the optimal configuration featuring the methods is tested through experiments as well.

  • PDF

추계적 페트리 네트를 이용한 대기시스템의 제어모형 (Control Models for Queueing Systems Using Stochastic Petri Nets)

  • 이광식;이효성
    • 산업공학
    • /
    • 제8권2호
    • /
    • pp.161-169
    • /
    • 1995
  • In this paper, a threshold policy is considered for the Markovian queueing system with server vacations. The threshold policy considered in this paper has the following form: "when the number of customers present in the system increases to N, the server is turned on and serves customers until the system becomes empty". In this paper, we show how the finite capacity or finite population queueing system under a threshold policy can be modeled by the stochastic Petri net. The performance evaluation of the model is carried out using the software called "SPNP". Some examples are also presented in which it is shown that how the optimal threshold policies can be obtained under a linear cost structure.

  • PDF

이중 재고한계점에 반응하는 고객이탈행위를 고려한 강건한 뉴스벤더 모델 (Robust Newsvendor Model with Customer Balking by the Bi-levels of Inventory Threshold)

  • 정욱;이세원
    • 산업경영시스템학회지
    • /
    • 제36권1호
    • /
    • pp.36-43
    • /
    • 2013
  • Many retailer store managers are experiencing the situation where some customers balk at purchasing products if the stock is low. In this paper, we extend the single period newsvendor model in an environment of customer balking behavior occurring at double threshold inventory levels assuming the chance of sales during balking is a discrete function of inventory level. Our analysis is based on the assumption that only the mean and the variance of demand are known, without assuming any specific distributional form. We derive the explicit general expression of optimal order quantity with unknown distribution of demand with double threshold inventory levels of customer balking. Then, we illustrate the concepts developed here through simple numerical examples and conclude the future research topics under balking situation.

동영상 컷 검출을 위한 가변형 동적 임계값 기법 (Variable Dynamic Threshold Method for Video Cut Detection)

  • 염성주;김우생
    • 한국통신학회논문지
    • /
    • 제27권4A호
    • /
    • pp.356-363
    • /
    • 2002
  • 컷 검출은 내용기반 검색에 필요한 인덱싱을 위해 수행되어야 하는 기초 작업으로 이를 위한 매우 다양한 기법들이 제안된바 있다. 그러나 기존의 연구에서는 대부분 고정된 하나의 임계값을 사용하기 때문에 통영상의 종류나 내용에 따라 최적의 임계값을 정해야만 하는 문제점을 갖는다. 본 논문에서는 컷 검출 간격의 확률적인 분포에 따라 임계값을 조절하며 컷이 발생하면 이전 컷과의 간격과 특징값 차이를 다음 컷 검출을 위한 임계값 설정에 반영하는 가변형 동적 임계값 방법을 제안한다. 이를 위해 임계값 조절에 필요한 인자 값들을 실행시간에 구하는 방법과 이를 사용한 컷 검출 알고리즘을 제시한다. 또한 실험을 통해 제안하는 방법이 기존의 방법에 비해 오 검출율을 줄일 수 있어 효율적임을 보인다.

차영상에서의 히스토그램을 이용한 적응적 임계값 결정 (Decision of Adaptive Threshold Value Using Histogram in Differential Image)

  • 오명관;김태익;최동진;전병민
    • 한국콘텐츠학회논문지
    • /
    • 제4권3호
    • /
    • pp.91-97
    • /
    • 2004
  • 이동 객체 추적 시스템을 위한 한 연구 분야로 차영상을 이용하여 움직임을 추정하는 기법이 있다. 움직임 추정을 위해 차영상을 이용하는 경우 임계값을 적용하여 배경 영역과 이동 객체 영역을 구분할 수 있도록 이진화를 수행하는 과정이 필수적이다. 본 논문에서는 차영상에서 배경과 객체의 특성 변화에 적응적인 임계값 결정 기법을 제안하였다. 제안 기법은 차영상의 히스토그램 모양을 분석하여 적절한 임계값을 결정하도록 하였다. 그레이 스케일 영상의 이진화에 사용되는 일반적인 임계값 기법들과 성능을 비교 평가하였다. 60개의 실험 영상에 대해 평가한 결과 제안 기법이 수작업으로 확인한 최적의 임계값과 평균 오차 2.8로 성능의 우수성을 확인하였다.

  • PDF

근막이완술이 유착성 관절낭염 환자의 통증 역치와 교감신경계 과활동에 미치는 효과: 사례연구 (The Effects of Myofascial Release on Pain Threshold and Sympathetic Hyperactivity in Patients with Adhesive Capsulitis: Case Study)

  • 정성관;이호준
    • 대한정형도수물리치료학회지
    • /
    • 제27권2호
    • /
    • pp.87-92
    • /
    • 2021
  • Purpose: This study aimed to investigate the effects of myofascial release technique on pain threshold and hormonal changes in patients with adhesive capsulitis of the shoulder. Methods: Eight patients with adhesive capsulitis were treated with the myofascial release technique. Myofascial release is a form of manual therapy that involves the application of a low load, long duration stretch to the myofascial complex, intended to restore optimal length, decrease pain, and improve function. Blood tests and pressure pain threshold (PPT) examinations were performed on their first visit. On their second visit, the myofascial release technique was applied to the shoulder for 20 min. Then, blood tests and PPT were re-evaluated to determine the effects of the myofascial release technique on pain threshold and hormonal changes. Results: Pain threshold increased from 2.92 to 24.13 lb after treatment. Epinephrine decreased from .13 to .08 ng/mL whereas norepinephrine increased from .25 to .41ng/㎖ after treatment. Conclusion: Myofascial release technique in patients with adhesive capsulitis increased pain thresholds, norepinephrine and decreased epinephrine levels.