• Nuclear Engineering and Technology
• /
• 제53권12호
• /
• pp.3944-3951
• /
• 2021

Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover, some approaches such as using synthetic dataset, in presence of large number of FS techniques, are very tedious and time consuming task. In this study to tackle the issue of dependency of estimation accuracy on the selected FS technique, a methodology based on the heterogeneous ensemble is proposed. The performance of the major learning algorithms of neural network (i.e. the FFNN-BR, the FFNN-LM) in combination with the diverse FS techniques (i.e. the NCA, the F-test, the Kendall's tau, the Pearson, the Spearman, and the Relief) and different combination techniques of the heterogeneous ensemble (i.e. the Min, the Median, the Arithmetic mean, and the Geometric mean) are considered. The target parameters/transients of Bushehr nuclear power plant (BNPP) are examined as the case study. The results show that the Min combination technique gives the more accurate estimation. Therefore, if the number of FS techniques is m and the number of learning algorithms is n, by the heterogeneous ensemble, the search space for acceptable estimation of the target parameters may be reduced from n × m to n × 1. The proposed methodology gives a simple and practical approach for more reliable and more accurate estimation of the target parameters compared to the methods such as the use of synthetic dataset or trial and error methods.

• 한국ITS학회 논문지
• /
• 제11권6호
• /
• pp.81-88
• /
• 2012

다중 입출력(MIMO : Multiple-Input Multiple-Output) 시스템은 공간 다이버시티 이득과 공간 다중화 이득을 얻을 수 있게 한다. 본 논문에서는 MIMO 시스템에서 데이터 정보와 안테나 선택 기법을 이용한 공간 부호화 기법을 제안한다. 이 기법은 부호화 이득과 동시에 공간 다이버시티 이득을 얻을 수 있게 한다. BPSK(Binary Phase-Shift Keying) 변조 방식을 사용한 MIMO 시스템에서 BER 성능을 분석하고, 데이터의 편재율에 따라 달라지는 공간 다이버시티 이득을 실험을 통하여 비교하였다.

• 정보처리학회논문지D
• /
• 제9D권5호
• /
• pp.897-902
• /
• 2002

소프트웨어 기술의 급속한 발전으로 컴포넌트 개발방법론은 많이 연구되었으나 컴포넌트의 품질을 구매자 관점에서 종합적이고 체계적으로 비교 및 평가하는 선정기법에 대한 연구가 미약한 상황이다. 지금까지 대부분의 컴포넌트 품질평가 방법은 객체지향의 척도를 기반으로 한 개발자 관점의 평가 방법이었으나 본 논문에서는 구매자 관점에서 최적의 상용컴포넌트를 선정하기 위한 기법으로 MCDM(Multiple Criteria Decision Making)기법을 활용한 4단계 선정 절차와 평가기준을 제시하였다. 상용컴포넌트의 품질은 국제표준(IS0/IEC 9126)에서 규정하고 있는 6가지 중요한 품질 특성 중에서 기능성, 효율성, 사용성을 고려하였으며 현재 인터넷상에서 판매하고 있는 상용 EJB 컴포넌트들에 대한 실증적 분석을 통하여 본 논문에서 제시한 상용컴포넌트 선정기법이 최적의 상용컴포넌트를 선택하는데 적용 가능한 것임을 보여준다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 학술대회지
• /
• pp.712-716
• /
• 2004

Because of rapid development of software technology, a number of software professionals have been concerned with component-based development methodologies. Up to date, the evaluation of component quality has been focused on object-oriented metric based methodology. But this paper presents the selection process and evaluation criteria based on an MCDM(Multiple Criteria Decision Making) technique for the selection of optimal COTS component from consumers' viewpoints. We considered functionality, efficiency and usability based on ISO/IEC 9126 for quality measurement and conducted practical analysis into commercial EJB component in internet. This paper shows that the proposed selection technique is applicable for the selection of the optimal COTS component.

• Journal of Communications and Networks
• /
• 제12권6호
• /
• pp.616-623
• /
• 2010

In this paper, exact closed-form expressions for outage probability and bit error probability (BEP) are presented for multi-hop decode-and-forward (DF) relaying schemes in conjunction with cooperative diversity, in which selection combining technique is employed at each node. We have shown that the proposed protocol offers remarkable diversity advantage over direct transmission as well as the conventional DF relaying schemes with the same combining technique. We then investigate the system performance when different diversity schemes are employed. It has been observed that the system performance loss due to selection combining relative to maximal ratio combining is not significant. Simulations are performed to confirm our theoretical analysis.

• International Journal of Computer Science & Network Security
• /
• 제21권5호
• /
• pp.129-132
• /
• 2021

Two feature selection approaches are analyzed in this study. First Approach used in this paper is Filter Approach which comprises of correlation technique. It provides two reduced feature sets using positive and negative correlation. Secondly Approach used in this paper is the wrapper approach which comprises of Sequential Forward Selection technique. The reduced feature set obtained by positive correlation results comprises of Rate of Acceleration, Intensity and Formant. The reduced feature set obtained by positive correlation results comprises of Rasta PLP, Log energy, Log power and Zero Crossing Rate. Pitch, Rate of Acceleration, Log Power, MFCC, LPCC is the reduced feature set yield as a result of Sequential Forwarding Selection.

• 대한음성학회지:말소리
• /
• 제63호
• /
• pp.125-137
• /
• 2007

Recently, many techniques have been proposed to improve the noise robustness for speaker verification. In this paper, we consider the feature recombination technique in multi-band approach. In the conventional feature recombination for speaker verification, to compute the likelihoods of speaker models or universal background model, whole feature components are used. This computation method is not effective in a view point of multi-band approach. To deal with non-effectiveness of the conventional feature recombination technique, we introduce a subband likelihood computation, and propose a modified feature recombination using subband likelihoods. In decision step of speaker verification system in noise environments, a few very low likelihood scores of a speaker model or universal background model cause speaker verification system to make wrong decision. To overcome this problem, a reliable feature selection method is proposed. The low likelihood scores of unreliable feature are substituted by likelihood scores of the adaptive noise model. In here, this adaptive noise model is estimated by maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. The proposed method using subband-based reliable feature selection obtains better performance than conventional feature recombination system. The error reduction rate is more than 31 % compared with the feature recombination-based speaker verification system.

• 대한의용생체공학회:의공학회지
• /
• 제20권3호
• /
• pp.265-274
• /
• 1999

본 논문에서는 3차원 의료 영상에 적합한 interframe 부호화 알고리즘을 제안하였다. 제안된 알고리즘은 움직임 추정/보상과 변환 부호화를 사용하는 동영상 압축 방법에 기초를 두고 있다. 이 알고리즘에서는 움직임 추정을 위해 와핑 방법이 채택되었다. 그리고, 부호화 효율을 향상시키기 위해 적응적 모드 선택을 사용하여 웨이블릿 변환 영역에서 움직임 조상된 오차 영상과 원 영상을 혼합한다. 이렇게 혼합된 영상은 제로트리 부호화 기법에 의해 압축된다. 본 논문은 제안된 방법이 3차원 의료 영상의 부호화에 매우 유용함을 증명하였다. 모의실험결과는 제안된 방법이 슬라이스 간의 간격과 무관하게 항상 좋은 결과를 얻을 수 있도록 하고, 그럼으로써 3차원 의료 영상 압축에 매우 바람직하다는 사실을 보여준다.

• 산업경영시스템학회지
• /
• 제39권1호
• /
• pp.105-115
• /
• 2016

Ensemble classification involves combining individually trained classifiers to yield more accurate prediction, compared with individual models. Ensemble techniques are very useful for improving the generalization ability of classifiers. The random subspace ensemble technique is a simple but effective method for constructing ensemble classifiers; it involves randomly drawing some of the features from each classifier in the ensemble. The instance selection technique involves selecting critical instances while deleting and removing irrelevant and noisy instances from the original dataset. The instance selection and random subspace methods are both well known in the field of data mining and have proven to be very effective in many applications. However, few studies have focused on integrating the instance selection and random subspace methods. Therefore, this study proposed a new hybrid ensemble model that integrates instance selection and random subspace techniques using genetic algorithms (GAs) to improve the performance of a random subspace ensemble model. GAs are used to select optimal (or near optimal) instances, which are used as input data for the random subspace ensemble model. The proposed model was applied to both Kaggle credit data and corporate credit data, and the results were compared with those of other models to investigate performance in terms of classification accuracy, levels of diversity, and average classification rates of base classifiers in the ensemble. The experimental results demonstrated that the proposed model outperformed other models including the single model, the instance selection model, and the original random subspace ensemble model.

• Journal of Communications and Networks
• /
• 제13권3호
• /
• pp.240-249
• /
• 2011

Cooperative diversity protocols have attracted a great deal of attention since they are thought to be capable of providing diversity multiplexing tradeoff among single antenna wireless devices. In the high signal-to-noise ratio (SNR) region, cooperation is rarely required; hence, the spectral efficiency of the cooperative protocol can be improved by applying a proper cooperation selection technique. In this paper, we present a simple "cooperation selection" technique based on instantaneous channel measurement to improve the spectral efficiency of cooperative protocols. We show that the same instantaneous channel measurement can also be used for relay selection. In this paper two protocols are proposed-proactive and reactive; the selection of one of these protocols depends on whether the decision of cooperation selection is made before or after the transmission of the source. These protocols can successfully select cooperation along with the best relay from a set of available M relays. If the instantaneous source-to-destination channel is strong enough to support the system requirements, then the source simply transmits to the destination as a noncooperative direct transmission; otherwise, a cooperative transmission with the help of the selected best relay is chosen by the system. Analysis and simulation results show that these protocols can achieve higher order diversity with improved spectral efficiency, i.e., a higher diversity-multiplexing tradeoff in a slow-fading environment.