• 한국CDE학회논문집
• /
• 제2권2호
• /
• pp.77-84
• /
• 1997

This paper is concerning the development of multiple neural networks system of problem domains where the complete input space can be decomposed into several different regions, and these are known prior to training neural networks. We will adopt oblique decision tree to represent the divided input space and sel ect an appropriate subnetworks, each of which is trained over a different region of input space. The overall architecture of multiple neural networks system, called the federated architecture, consists of a facilitator, normal subnetworks, and tile networks. The role of a facilitator is to choose the subnetwork that is suitable for the given input data using information obtained from decision tree. However, if input data is close enough to the boundaries of regions, there is a large possibility of selecting the invalid subnetwork due to the incorrect prediction of decision tree. When such a situation is encountered, the facilitator selects a tile network that is trained closely to the boundaries of partitioned input space, instead of a normal subnetwork. In this way, it is possible to reduce the large error of neural networks at zones close to borders of regions. The validation of our approach is examined and verified by applying the federated neural networks system to the configuration design of a midship structure.

• 한국통신학회논문지
• /
• 제37A권9호
• /
• pp.738-745
• /
• 2012

본 논문에서는 부호화된 4+12+16 APSK에 대하여 낮은 복잡도를 갖는 근사화된 연판정 디매핑 알고리즘을 제안한다. 제안된 알고리즘을 도출하기 위해 4+12+16 APSK의 결정 경계를 근사화하고, 그 근사화된 결정 경계로부터 각 비트에 대한 LLR 값을 계산한다. 새롭게 제안된 알고리즘은 기존의 max-log 알고리즘보다 곱셈 계산 수를 상당히 줄여 수신기 복잡도를 크게 낮출 수 있으며, 낮은 복잡도로 인한 BER 성능 열화를 약 1.1dB 이하로 줄일 수 있다.

• 디지털융복합연구
• /
• 제13권1호
• /
• pp.243-248
• /
• 2015

인식 모델을 구성할 때 정의되지 않은 모델, 인식 모델 구성 후에 추가되어진 모델, 모델이 부족하여 하나의 모델 클러스터링으로 모델링하여 생성된 인식 모델들은 인식률 저하의 원인이 된다. 이러한 원인을 개선하기 위하여 Bayesian 기법의 모수 추정을 이용한 결정트리 상태 공유 모델링 방법을 제안하였다. 제안 방법은 Bayesian 기법의 파라미터 추정을 통하여 탐색된 결과로부터 결정트리 기반 상태 공유 모델링의 최대 확률 기법에 따라 인식모델을 결정한다. 본 논문에서 제안하여 시뮬레이션 데이터를 이용한 실험 결과에서 제안한 군집화 방식을 비교하여 1.29%의 음성인식 오류감소율을 보였으며, 기존 군집화 방식에 비해 개선된 성능을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.2925-2948
• /
• 2019

In order to improve the utilization of irrigation water resources of greenhouse tomatoes, a water-saving irrigation decision-making model based on genetic optimization T-S fuzzy neural network is proposed in this paper. The main work are as follows: Firstly, the traditional genetic algorithm is optimized by introducing the constraint operator and update operator of the Krill herd (KH) algorithm. Secondly, the weights and thresholds of T-S fuzzy neural network are optimized by using the improved genetic algorithm. Finally, on the basis of the real data set, the genetic optimization T-S fuzzy neural network is used to simulate and predict the irrigation volume for greenhouse tomatoes. The performance of the genetic algorithm improved T-S fuzzy neural network (GA-TSFNN), the traditional T-S fuzzy neural network algorithm (TSFNN), BP neural network algorithm(BPNN) and the genetic algorithm improved BP neural network algorithm (GA-BPNN) is compared by simulation. The simulation experiment results show that compared with the TSFNN, BPNN and the GA-BPNN, the error of the GA-TSFNN between the predicted value and the actual value of the irrigation volume is smaller, and the proposed method has a better prediction effect. This paper provides new ideas for the water-saving irrigation decision in greenhouse tomatoes.

• Journal of applied mathematics & informatics
• /
• 제41권5호
• /
• pp.1129-1143
• /
• 2023

Social media platforms have become an integral part of our daily lives, and they generate vast amounts of data that can be analyzed for various purposes. However, the quality of the data obtained from social media is often questionable due to factors such as noise, bias, and incompleteness. Enhancing data quality is crucial to ensure the reliability and validity of the results obtained from such data. This paper proposes an enhanced decision-making framework based on Business Decision Management Systems (BDMS) that addresses these challenges by incorporating a data quality enhancement component. The framework includes a backtracking method to improve plan failures and risk-taking abilities and a steep optimized strategy to enhance training plan and resource management, all of which contribute to improving the quality of the data. We examine the efficacy of the proposed framework through research data, which provides evidence of its ability to increase the level of effectiveness and performance by enhancing data quality. Additionally, we demonstrate the reliability of the proposed framework through simulation analysis, which includes true positive analysis, performance analysis, error analysis, and accuracy analysis. This research contributes to the field of business intelligence by providing a framework that addresses critical data quality challenges faced by organizations in decision-making environments.

• 지능정보연구
• /
• 제27권3호
• /
• pp.231-252
• /
• 2021

인공지능(Artificial Intelligence)은 미래를 가장 크게 변화시킬 핵심 동력으로 산업 전반과 개인의 일상생활에 다양한 형태로 영향을 미치고 있다. 무엇보다 활용 가능한 데이터가 증가함에 따라 더욱더 많은 기업과 개인들이 인공지능 기술을 이용하여 데이터로부터 유용한 정보를 추출하고 이를 의사결정에 활용하고 있다. 인공지능에 관한 기존 연구는 모방 가능한 업무의 자동화에 초점을 두고 있으나, 인간을 배제한 자동화는 장점 못지않게 알고리즘 편향(Algorithms bias)으로 발생되는 오류나 자율성(Autonomy)의 한계점, 그리고 일자리 대체 등 사회적 부작용을 보여주고 있다. 최근 들어, 인간지능의 강화를 위한 증강 지능 (Augmented intelligence)으로서 인간과 인공지능의 협업에 관한 연구가 주목을 받고 있으며 기업도 관심을 가지기 시작하였다. 본 연구는 의사결정을 위해 조언(Advice)을 제공하는 조언자의 유형을 인간, 인공지능, 그리고 인간과 인공지능 협업의 세 가지로 나누고, 조언자의 유형과 의사결정자의 성격 특성이 의사결정에 미치는 영향을 살펴보았다. 311명의 실험자를 대상으로 사진 속 얼굴을 보고 나이를 예측하는 업무를 진행하였으며, 연구 결과 의사결정자가 조언활용을 하려면 먼저 조언의 유용성을 높게 인지하여하는 것으로 나타났다. 또한 의사결정자의 성격 특성이 조언자 유형별로 조언의 유용성을 인지하고 조언을 활용하는 데에 미치는 영향을 살펴본 결과, 인간과 인공지능의 협업 형태인 경우 의사결정자의 성격 특성에 무관하게 조언의 유용성을 더 높게 인지하고 적극적으로 조언을 활용하는 것으로 나타났다. 인공지능 단독으로 활용될 경우에는 성격 특성 중 성실성과 외향성이 강하고 신경증이 낮은 의사결정자가 조언의 유용성을 더 높게 인지하고 조언을 활용하는 것으로 나타났다. 본 연구는 인공지능의 역할을 의사결정과 판단(Decision Making and Judgment) 연구 분야의 조언자의 역할로 보고 관련 연구를 확장하였다는데 학문적 의의가 있으며, 기업이 인공지능 활용 역량을 제고하기 위해 고려해야 할 점들을 제시하였다는데 실무적 의의가 있다.

• 대한임베디드공학회논문지
• /
• 제9권5호
• /
• pp.285-292
• /
• 2014

The commonly used Newton-Raphson's floating-point number divider algorithm performs two multiplications in one iteration. In this paper, a tentative K'th Newton-Raphson's floating-point number divider algorithm which performs K times multiplications in one iteration is proposed. Since the number of multiplications performed by the proposed algorithm is dependent on the input values, the average number of multiplications per an operation in single precision and double precision divider is derived from many reciprocal tables with varying sizes. In addition, an error correction algorithm, which consists of one multiplication and a decision, to get exact result in divider is proposed. Since the proposed algorithm only performs the multiplications until the error gets smaller than a given value, it can be used to improve the performance of a floating point number divider unit. Also, it can be used to construct optimized approximate reciprocal tables.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권8호
• /
• pp.3772-3790
• /
• 2016

It is well known that the constant modulus algorithm (CMA) presents a large steady-state mean-square error (MSE) for high-order quadrature amplitude modulation (QAM) signals. In this paper, we propose a low-complexity hybrid adaptive blind equalization algorithm, which augments the CMA error function with a novel constellation matched error (CME) term. The most attractive advantage of the proposed algorithm is that it is computationally simpler than concurrent CMA and soft decision-directed (SDD) scheme (CMA+SDD), and modified CMA (MCMA), while the approximation of steady-state MSE of the proposed algorithm is same with CMA+SDD, and lower than MCMA. Extensive simulations demonstrate the performance of the proposed algorithm.

• 음성과학
• /
• 제12권3호
• /
• pp.115-124
• /
• 2005

We investigated on the submission of multiple candidates in speaker-independent speech recognition by VQ/HMM. Submission of fixed number of multiple candidates has first been examined. As the number of candidates increases by two, three, and four, the recognition error rates were found to decrease by 41%, 58%, and 65%, respectively compared to that of a single candidate. We tried another approach that the candidates within a range of Viterbi scores are submitted. The number of candidates showed geometric increase as the admitted range becomes large. For a practical application, a combination of the above two methods was also studied. We chose the candidates within some range of Viterbi scores and limited the maximum number of candidates submitted to five. Experimental results showed that recognition error rates of less than 10% could be achieved with average number of candidates of 3.2 by this method.

• 한국시뮬레이션학회논문지
• /
• 제4권2호
• /
• pp.31-40
• /
• 1995

A hybrid simulation model consists of real physical entities as well as simulated ones. It also contains logical processes for decision making for each operation units, a group of the entities. During the execution of such simulations, the physical and the logical processes consume real clock time while the activity durations of the simulated ones are generated. Due to the inherent chracteristics of the subjects of the communication channels. Since one can not undo an real event already taken place, the traditional central clock approach is used for the synchronization of the events(Kim[6]). However, there are still chances of causality errors due to the randomness in the communication delays. This error is not found in the distributed pure simulations. This paper explains the error in details and proposes a prevention scheme that is simple to implement.