• 한국통신학회논문지
• /
• 제22권3호
• /
• pp.423-431
• /
• 1997

A new decision tree generator MEC is proposed in this paper, which uses the difference of multi-base entropy as a consistent criterion for discretization and selection of attributes. To evaluate the performance of the proposed generator, it is compared to other generators which use criteria based on entropy and adopt different discretization styles. As an experimental result, it is shown that the proposed generator produces the most efficient classifiers, which have the least number of leaves at the same error rate, regardless of whether attribute values constituting the training set are discrete or continuous.

• 한국수자원학회논문집
• /
• 제57권7호
• /
• pp.437-449
• /
• 2024

딥러닝을 활용하여 유역 특성을 반영한 유량 예측 및 비교 연구가 주목받고 있다. 본 연구는 셀프 어텐션 메커니즘을 통해 대용량 데이터 훈련에 적합한 Transformer와 인코더-디코더(Encoder-Decoder) 구조를 가지는 LSTM-based multi-state-vector sequence-to-sequence (LSTM-MSV-S2S) 모형을 선정하여 유역정보(catchment attributes)를 고려할 수 있는 모형을 구축하였고 이를 토대로 국내 10개 다목적댐 유역의 유입량을 예측하였다. 본 연구에서 설계한 실험 구성은 단일유역-단일훈련(Single-basin Training, ST), 다수유역-단일훈련(Pretraining, PT), 사전학습-파인튜닝(Pretraining-Finetuning, PT-FT)의 세 가지 훈련 방법을 사용하였다. 모형의 입력 자료는 선정된 10가지 유역정보와 함께 기상 자료를 사용하였으며, 훈련 방법에 따른 유입량 예측 성능을 비교하였다. 그 결과, Transformer 모형은 PT와 PT-FT 방법에서 LSTM-MSV-S2S보다 우수한 성능을 보였으며, 특히 PT-FT 기법 적용 시 가장 높은 성능을 나타냈다. LSTM-MSV-S2S는 ST 방법에서는 Transformer보다 높은 성능을 보였으나, PT 및 PT-FT 방법에서는 낮은 성능을 보였다. 또한, 임베딩 레이어 활성화 값과 원본 유역정보를 군집화하여 모형의 유역 간 유사성 학습 여부를 분석하였다. Transformer는 활성화 벡터가 유사한 유역들에서 성능이 향상되었으며, 이는 사전에 학습된 다른 유역의 정보를 활용해 성능이 개선됨을 입증하였다. 본 연구는 다목적댐별 적합한 모형 및 훈련 방법을 비교하고, 국내 유역에 PT 및 PT-FT 방법을 적용한 딥러닝 모형 구축의 필요성을 제시하였다. 또한, PT 및 PT-FT 방법 적용 시 Transformer가 LSTM-MSV-S2S보다 성능이 더 우수하였다.

• 한국주거학회논문집
• /
• 제1권2호
• /
• pp.49-66
• /
• 1990

This study is a case study to grasp residents` trade-off preference and opinions for selected interior environmental attributes of muilti-family housing. Interiew with structured questionnaire was carried out through pilot and main survey. On the basis of the result of pilot survey, interior environmental attributes for the main survey were selected. Selected attributes were the size of each residential room, the degree of openness between two rooms and interior facilities. Among them, trade-off approach was applied to the size of each residential room and interior facilities. For the main survey. 45 housewives living in 31 pyung apartment of a selected construction company to grasp the residents` trade-off preference and opinions on the selected attributes. In terms of the size of each room, subjects wanted the room to be lager, whereas master bedroom smaller, and family bathroom larger, wheareas toilet near master bedroom smaller. In terms of the degree of openness between two rooms, the present degree of openness between private and service area such as living room and balcony, and second bedroom and adjacent balcony need to be more open, whereas the present degree of openness between living room and dining room and between living room and kitchen need to be more closed. The comparative orders of important intems were the ventilation facility in the bathroom, drying poles for clothes in the balcony, interior landscape, and workable for hand washing clothes. In conclusion, measurement of preference using trade-off approach about selected interior environmental attributes in post-occupancy evaluation was regarded as a promising evaluation method to grasp the practical and comparative preference under constraints comparing to the typical existing methods.

• ETRI Journal
• /
• 제30권5호
• /
• pp.663-673
• /
• 2008

The multi-scenario topology of multi-channel hybrid ubiquitous sensor networks (USNs) is studied and a novel link auto-diversity cross-layer cooperative scheduling scheme is proposed in this paper. The proposed scheme integrates the attributes of the new performance evaluation link auto-diversity air-time metric and the topology space in the given multi-scenario. The proposed scheme is compared with other schemes, and its superiority is demonstrated through simulations. The simulation results show that relative energy consumption, link reception probability, and end-to-end blocking probability are improved. The addressing ratio of success with unchanged parameters and external information can be increased. The network can tolerate more hops to support reliable transportation when the proposed scheme is implemented. Moreover, the scheme can make the network stable. Therefore, the proposed scheme can enhance the average rate performance of the hybrid USN and stabilize the outage probability.

• Journal of information and communication convergence engineering
• /
• 제1권2호
• /
• pp.74-81
• /
• 2003

There are many researches on visual languages, but the most of them are difficult to support various collaborative interactions on a distributed multimedia environment. So, this paper suggests a collaborative visual language for interaction between multi-users. The visual language can describe a conceptual model for collaborative interactions between multi-users. Using the visual language, generated visual sentences consist of object icons and interaction operators. An object icon represents a user who is responsible for a collaborative activity, has dynamic attributes of a user, and supports flexible interaction between multi-users. An interaction operator represents an interactive relation between multi-users and supports various collaborative interactions. Merits of the visual language are as follows: supporting of both asynchronous interaction and synchronous interaction, supporting flexible interaction between multi-users according to participation or leave of users, supporting a user oriented modeling, etc. For example, an application to a workflow system for document approval is illustrated. So we could be found that the visual language shows a collaborative interaction.

• 한국컴퓨터정보학회논문지
• /
• 제25권9호
• /
• pp.63-69
• /
• 2020

이미지-이미지 변환은 입력 이미지를 통해서 목적 이미지를 만들어내는 기술로 최근 비지도 학습 구조인 GAN을 활용하여 더 실제와 같은 이미지를 만들어내는 높은 성과를 보였다. 이에 따라 GAN을 활용한 이미지-이미지 변환 연구는 다양하게 진행되고 있다. 이때 일반적으로 이미지-이미지 변환은 하나의 속성 변환을 목표한다. 그러나 실제 생활에서 사용되고 얻을 수 있는 자료들은 한 가지 특징으로 설명하기 힘든 다양한 특징으로 이루어진다. 그래서 다양한 속성을 활용하기 위하여 속성별로 이미지 생성 과정을 나누어 학습할 수 있도록 하는 다중 속성 변화를 목표로 한다면 더 이미지-이미지 변환의 역할을 잘 수행할 수 있을 것이다. 본 논문에서는 GAN을 활용한 이미지-이미지 변환 구조 중 높은 성과를 보인 CycleGAN을 활용해 이중 속성 변환 구조인 Multi CycleGAN을 제안한다. 이 구조는 입력 도메인을 두 가지의 속성에 대하여 학습하기 위하여 3개의 도메인이 양방향 학습을 진행하는 이중 변환 구조를 구현하였다. 새로운 구조를 통해 생성된 이미지와 기존 이미지-이미지 변환 구조들을 통해 생성된 이미지를 비교할 수 있도록 실험을 진행하였다. 실험 결과 새로운 구조를 통한 이미지는 입력 도메인의 속성을 유지하며 목표한 속성이 적용되는 높은 성능을 보였다. 이 구조를 활용한다면 앞으로 더 다양한 이미지를 생성하는 일이 가능지기 때문에 더 다양한 분야에서의 이미지 생성의 활용을 기대할 수 있다.

• 인터넷정보학회논문지
• /
• 제10권3호
• /
• pp.35-49
• /
• 2009

전자전 환경에서 헬기는 헬기생존체계(aircraft survivability equipment: ASE)의 다양한 센서를 통하여 수집한 데이터를 기반으로 헬기에 대한 위협을 식별한다. 헬기의 성공적인 임무 수행 및 생존을 위하여 헬기에 대한 위협을 반복적으로 확인할 수 있는 시뮬레이터의 구현은 필수적이다. 본 논문에서는 (1) 전장 헬기의 센서가 수신하는 위협요소를 정의하는 위협속성 생성기, (2) 전장환경과 유사한 위협을 정규, 균일, 지수 분포로 생성하는 위협자료 생성기 및 (3) 다양한 전장 시나리오에서 센서들이 수집한 데이터를 통합하여 위협의 방향과 정도를 사용자에게 실시간으로 보여주는 위협 분석 및 통합 표시기를 개발한다. 구현한 전장 헬기의 다중센서 위협 시뮬레이터를 이용하여 생성된 다양한 시나리오에서 다수의 위협에 대한 통합정확도를 측정하였다.

• Nuclear Engineering and Technology
• /
• 제54권10호
• /
• pp.3841-3848
• /
• 2022

The effect of modifiers on the optical features and radiation defying ability of the Eu³⁺ ions doped multi constituent glasses was examined. XRD has established the amorphous nature of the specimen. The presence of various functional/fundamental groups in the present glasses was analyzed through FTIR spectra. The physical, structural and elastic traits of the glasses were explored. The variation in the structural compactness of the glass structure according to the incorporated modifier was enlightened to describe their suitability for a better shielding media. For the examined glasses, the metallization criterion value varied in the range 0.613-0.692, indicating the non-metallic character of the glasses with possible nonlinear optical applications. The computed elastic moduli expose the Li-containing glass (BTLi:Eu) to be tightly packed and rigid, which is a requirement for a better shielding channel. Furthermore, the optical bandgap and the Urbach energy values are calculated based on the optical absorption spectra. The evaluated bonding parameters revealed the nature of the fabricated glasses covalent. In addition, we investigated the radiation attenuation attributes of the prepared Eu³⁺ ions doped multi constituent glasses using Phy-X software. We determined the linear attenuation coefficient (LAC) and reported the influence of the five oxides Li₂O₃, CaO, BaO, SrO, and ZnO on the LAC values. The LAC varied between 0.433 and 0.549 cm^-1 at 0.284 MeV. The 39B₂O₃-25TeO₂-15Li₂O₃-10Na₂O-10K₂O-1Eu₂O₃ glass has a much smaller LAC than the other glasses.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2004년도 전력전자학술대회 논문집(2)
• /
• pp.620-624
• /
• 2004

Th is paper presents a systematical approach to study carrier based PWM techniques (CPWM) in diode-clamped and cascade multilevel inverters by using the proposed multi-modulating pattern method. This method is based on the vector correlation between CPWM and space vector PWM (SVPWM) and applicable to both multilevel inverter topologies. The CPWM technique can be described in a general mathematical equation, and obtain the same outputs similarly as of corresponding SVPWM. Control of the fundamental voltage, vector redundancies and phase redundancies in multilevel inverter can be formulated separately in the CPWM equation. The deduced CPWM can obtain a full vector redundancy control, and fully utilize phase redundancy in a cascade inverter. In the paper, CPWM equations and corresponding algorithm for generating multi-modulating signals will be performed, in which SVPWM attributes will be presented by corresponding controllable factors.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.426-439
• /
• 2021

To alleviate the cold-start problem and data sparsity in web service recommendation and meet the personalized needs of users, this paper proposes a personalized web service recommendation method based on a hybrid social network and multi-objective immune optimization. The network adds the element of the service provider, which can provide more real information and help alleviate the cold-start problem. Then, according to the proposed service recommendation framework, multi-objective immune optimization is used to fuse multiple attributes and provide personalized web services for users without adjusting any weight coefficients. Experiments were conducted on real data sets, and the results show that the proposed method has high accuracy and a low recall rate, which is helpful to improving personalized recommendation.