• ETRI Journal
• /
• 제31권4호
• /
• pp.419-428
• /
• 2009

A question answering (QA) system can be built using multiple QA modules that can individually serve as a QA system in and of themselves. This paper proposes a learnable, strategy-driven QA model that aims at enhancing both efficiency and effectiveness. A strategy is learned using a learning-based classification algorithm that determines the sequence of QA modules to be invoked and decides when to stop invoking additional modules. The learned strategy invokes the most suitable QA module for a given question and attempts to verify the answer by consulting other modules until the level of confidence reaches a threshold. In our experiments, our strategy learning approach obtained improvement over a simple routing approach by 10.5% in effectiveness and 27.2% in efficiency.

• 통합자연과학논문집
• /
• 제14권2호
• /
• pp.50-56
• /
• 2021

Due to the recent increase in the mobile streaming market, mobile traffic is increasing exponentially. IMT-2020, named as the next generation mobile communication standard by ITU, is called the 5th generation mobile communication (5G), and is a technology that satisfies the data traffic capacity, low latency, high energy efficiency, and economic efficiency compared to the existing LTE (Long Term Evolution) system. 5G implements this technology by utilizing a high frequency band, but there is a problem of path loss due to the use of a high frequency band, which is greatly affected by system performance. In this paper, small cell technology was presented as a solution to the high frequency utilization of 5G mobile communication system, and furthermore, the system performance was improved by applying machine learning technology to macro communication and small cell communication method decision. It was found that the system performance was improved due to the technical application and the application of machine learning techniques.

• International journal of advanced smart convergence
• /
• 제9권4호
• /
• pp.156-166
• /
• 2020

In this paper, to improve spectral efficiency and mitigate interference in coordinated millimeter-wave systems, we proposes an optimal user group and beam selection scheme. The proposed scheme improves spectral efficiency by mitigating intra- and inter-cell interferences (ICI). By examining the effective channel capacity for all possible user combinations, user combinations and beams with minimized ICI can be selected. However, implementing this in a dense environment of cells and users requires highly complex computational abilities, which we have investigated applying multiclass classifiers based on machine learning. Compared with the conventional scheme, the numerical results show that our proposed scheme can achieve near-optimal performance, making it an attractive option for these systems.

• ETRI Journal
• /
• 제46권3호
• /
• pp.379-391
• /
• 2024

To meet increasing traffic requirements in mobile networks, small base stations (SBSs) are densely deployed, overlapping existing network architecture and increasing system capacity. However, densely deployed SBSs increase energy consumption and interference. Although these problems already exist because of densely deployed SBSs, even more SBSs are needed to meet increasing traffic demands. Hence, base station (BS) switching operations have been used to minimize energy consumption while guaranteeing quality-of-service (QoS) for users. In this study, to optimize energy efficiency, we propose the use of deep reinforcement learning (DRL) to create a BS switching operation strategy with a traffic prediction model. First, a federated long short-term memory (LSTM) model is introduced to predict user traffic demands from user trajectory information. Next, the DRL-based BS switching operation scheme determines the switching operations for the SBSs using the predicted traffic demand. Experimental results confirm that the proposed scheme outperforms existing approaches in terms of energy efficiency, signal-to-interference noise ratio, handover metrics, and prediction performance.

• 정보교육학회논문지
• /
• 제13권1호
• /
• pp.1-8
• /
• 2009

본 연구는 탐구교수학습 모형에 기반한 체육과 ICT교수 학습 과정안을 개발하고 현장에 적용하여 교수 학습에서의 효율성을 입증하는 것이다. 최근, 체육 교육에도 ICT를 활용이 다양해지고 있다. 본 연구는 기존의 ICT 단순 활용방식에서 벗어나 교수 학습의 구체적 절차와 방법인 '학습모형'에 기반한 ICT 활용을 연구함으로써 학습 목표와 효과를 높이도록 하였다. 체육과의 육상, 체조 단원에 적용되는 탐구교수학습모형을 ICT 활용 수업에 적합하도록 재구성하여 절차적 모형으로 각 단계를 정의하고, 이를 실현하기 위한 ICT 교수 학습 과정안을 개발하였다. 그리고 초등학교 5학년 수업에 적용하였다. 적용 결과 교수 학습 목표 달성의 효율성을 높이고 학습의 흥미유발과 학습 만족도를 높이고 멀리뛰기의 기능적인 면에서 효과가 있었다.

• Asia Marketing Journal
• /
• 제17권1호
• /
• pp.27-53
• /
• 2015

Learning organization has been an important issue in both management and marketing areas. Also learning capability is a key construct of innovation process in a firm. Especially, in marketing context, several researchers have studied market-based learning and its relation with performance. Previous studies have shown that market-based learning has a positive impact on overall firm performance. However, there has been inconsistency in the concept of market-based learning itself and its relationships with antecedents and consequences. Given this conflicting and inconsistent results of previous research, this study has two main objectives. First, this paper proposed a conceptual framework that marketbased learning has two types of processes and each types of market-based learning will generate different types of performance. Second, the mediating role of marketing capability in learning-performance link is proposed. The proposed conceptual framework shows that organizations which have marketbased learning for innovation management can enjoy ambidextrous firm performance on both side of effectiveness and efficiency via marketing capability. Moreover our research model proposes key drivers of market based organizational learning.

• 지능정보연구
• /
• 제7권1호
• /
• pp.63-79
• /
• 2001

비모수적인 효율성 분석기법인 자료봉합분석(Data Envelopment Analysis) 은 현재 학교, 은행, 병원 등 여러 분야에서 각 조직의 효율성을 평가하는데 응용되고 있다. 그러나, 방법론 적용에 있어 상대적으로 비효율적인 의사결정단위의 참조집합이 1개 이상의 효율적인 의사결정단위로 구성되어 있어, 어느 방향으로 개선해야 할지 가이드라인을 제공하지 못하고 또한 효율성 크기에 따라, 비효율적인 의사결정단위의 단계적인 개선 방향을 제공하지 못한다는 불편한 점이 있다. 따라서, 본 연구에서는 이와 같은 불편한 점을 보완하기 위한 자료봉합분석과 기계학습을 이용한 하이브리드 방법론을 개발하고, 이를 국내 29개 생명보험사에 적용하여 타당성을 검증하였다.

• ETRI Journal
• /
• 제42권5호
• /
• pp.686-699
• /
• 2020

In this paper, we propose a supervised-learning-based spatial performance prediction (SLPP) framework for next-generation heterogeneous communication networks (HCNs). Adaptive asset placement, dynamic resource allocation, and load balancing are critical network functions in an HCN to ensure seamless network management and enhance service quality. Although many existing systems use measurement data to react to network performance changes, it is highly beneficial to perform accurate performance prediction for different systems to support various network functions. Recent advancements in complex statistical algorithms and computational efficiency have made machine-learning ubiquitous for accurate data-based prediction. A robust network performance prediction framework for optimizing performance and resource utilization through a linear discriminant analysis-based prediction approach has been proposed in this paper. Comparison results with different machine-learning techniques on real-world data demonstrate that SLPP provides superior accuracy and computational efficiency for both stationary and mobile user conditions.

• Structural Engineering and Mechanics
• /
• 제83권2호
• /
• pp.167-178
• /
• 2022

Surrogate models aim to approximate the performance function with an active-learning design of experiments (DoE) to obtain a sufficiently accurate prediction of the performance function's sign for an inexpensive computational demand in reliability analysis. Nevertheless, many existing active-learning methods are limited to the Kriging model, while the uncertainties of the Kriging itself affect the reliability analysis results. Moreover, the existing general active-learning methods may not achieve a fully satisfactory balance between accuracy and efficiency. Therefore, a novel active-learning method GLM-CM is constructed to yield the issues, which conciliates several merits of existing methods. To demonstrate the performance of the proposed method, four examples, concerning both mathematical and engineering problems, were selected. By benchmarking obtained results with literature findings, various surrogate models combined with the proposed method not only provide an accurate reliability evaluation while highly alleviating the computational burden, but also provides a satisfactory balance between accuracy and efficiency compared to the other reliability methods.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.