• 한국국방경영분석학회지
• /
• 제29권1호
• /
• pp.57-75
• /
• 2003

Policy-based networking offers a network manager the ability to manage the network in a holistic and dynamic fashion rather than force a network manager to manage the network by dealing with each device individually. Policy-based networking is focusing on users and applications instead of emphasizing devices and interfaces. An important part of the policy-based networking is to simplify the task of administration and management for different disciplines. The Defense Information System(DIS) of today are complex and heterogeneous systems. Operational needs are not a trivial task and Quality of Service(QoS) is not generally guaranteed. So, important data may be missed or congested by trivial data. Policy-based networking provide a way to support QoS and simplify the management of multiple devices deploying complex technologies. This paper suggest implementation of policy-based networking in DIS to improvement of performance, and implementation is progressed step by step. Especially this paper is focusing on the providing QoS with policy-based networking using Lightweight Directory Access Protocol(LDAP) Server.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.163-165
• /
• 2019

The task of image denoising is gaining popularity in the computer vision research field. Its main objective of restoring the sharp image from given noisy input is demanded in all image processing procedure. In this work, we treat the process of residual hair removal on faces images similar to the task of image denoising. In particular, our method removes the residual hair that presents on the frontal or profile face images and in-paints it with the relevant skin color. To achieve this objective, we employ a deep neural network that able to perform both tasks in one time. Furthermore, simple technic of residual hair color augmentation is introduced to increase the number of training data. This approach is beneficial for improving the robustness of the network. Finally, we show that the experimental results demonstrate the superiority of our network in both quantitative and qualitative performances.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제27권8호
• /
• pp.834-845
• /
• 2000

대부분의 에이전트는 그들이 생성될 때 자신이 수행하는 작업에 대한 계획을 갖고 있다. 이러한 에이전트들이 모여 멀티 에이전트 시스템을 이룰 경우 하나의 복잡한 작업을 수행하기 위해 미리 정의된 각 에이전트의 계획을 그대로 사용하게 되면 각 계획 규칙 사이의 연관성 등을 고려하지 못하기 때문에 시스템의 작업 처리 효율성이 떨어진다. 이를 해결하기 위해서는 에이전트가 갖고 있는 독자적인 계획을 통합하는 것이 요구된다. 이러한 계획의 통합은 미리 정의된 각 에이전트의 계획 사이의 관계를 파악하여 병렬적인 작업 수행을 가능하게 한다. 본 논문에서는 멀티 에이전트 시스템을 이루는 에이전트들이 자신의 작업 수행을 위한 계획을 갖고 있다는 가정 하에 하나의 큰 작업을 효율적으로 처리하기 위해 에이전트들의 계획을 네트워크 형태로 표현하고 이를 통합하여 작업을 수행하는 방법을 제시한다. 이 방법은 기존의 연구들이 다루고 있는 계획 순서 등과 관련된 에이전트 조정 문제를 자연스럽게 해결할 뿐만 아니라 다른 계획에 영향을 미치지 않는 각 에이전트의 독자적인 계획을 병렬로 수행시켜 작업 처리 시간을 단축시키는 효과를 낸다.

• 한국음향학회지
• /
• 제42권5호
• /
• pp.395-401
• /
• 2023

음향 이벤트 검출(Sound Event Detection, SED)은 음향 신호에서 관심 있는 음향의 종류와 발생 구간을 검출하는 기술로, 음향 감시 시스템 및 모니터링 시스템 등 다양한 분야에서 활용되고 있다. 최근 음향 신호 분석에 관한 국제 경연 대회(Detection and Classification of Acoustic Scenes and Events, DCASE) Task 4를 통해 다양한 방법이 소개되고 있다. 본 연구는 다양한 영역에서 성능 향상을 이끌고 있는 Dense Convolutional Networks(DenseNet)을 음향 이벤트 검출에 적용하기 위해 설계 변수에 따른 성능 변화를 비교 및 분석한다. 실험에서는 DenseNet with Bottleneck and Compression(DenseNet-BC)와 순환신경망(Recurrent Neural Network, RNN)의 한 종류인 양방향 게이트 순환 유닛(Bidirectional Gated Recurrent Unit, Bi-GRU)을 결합한 DenseRNN 모델을 설계하고, 평균 교사 모델(Mean Teacher Model)을 통해 모델을 학습한다. DCASE task4의 성능 평가 기준에 따라 이벤트 기반 f-score를 바탕으로 설계 변수에 따른 DenseRNN의 성능 변화를 분석한다. 실험 결과에서 DenseRNN의 복잡도가 높을수록 성능이 향상되지만 일정 수준에 도달하면 유사한 성능을 보임을 확인할 수 있다. 또한, 학습과정에서 중도탈락을 적용하지 않는 경우, 모델이 효과적으로 학습됨을 확인할 수 있다.

• 산업기술연구
• /
• 제20권B호
• /
• pp.201-206
• /
• 2000

A priori information of object is needed to control in some well known control methods. But we can't always know a priori information of object in real world. In this paper, the inverted pendulum is simulated as a control task with the goal of learning to balance the pendulum with no a priori information using neural network controller. In contrast to other applications of neural networks to the inverted pendulum task, the performance feedback is unavailable on each training step, appearing only as a failure signal when the pendulum falls or reaches the bound of track. To solve this task, the delayed performance evaluation and the learning of nonlinear of nonlinear functions must be dealt. Reinforcement learning method is used for those issues.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.19-27
• /
• 2021

Tasks scheduling have been gaining attention in both industry and research. The scheduling that ensures independent task execution is critical in real-time systems. While task scheduling has gained a lot of attention in recent years, there have been few works that have been implemented into real-time architecture. The efficiency of the classical scheduling strategy in real-time systems, in particular, is still understudied. To reduce total waiting time, we apply three scheduling approaches in this paper: First In/First Out (FIFO), Shortest Execution Time (SET), and Shortest-Longest Execution Time (SLET). Experimental results have demonstrated the efficacy of the SLET in comparison with the others in most cases in a wide range of configurations.

• 지능정보연구
• /
• 제18권2호
• /
• pp.61-83
• /
• 2012

지식지도는 관련된 지식의 현황을 네트워크 형식으로 보여주는 일종의 도식으로, 지식 간의 상호참조적 네비게이션 관계를 기초로 하는 지식 분류 및 저장 체계 역할을 한다. 이러한 이유로 인하여 지식 및 이들 지식이 또 다른 지식과 갖는 관계를 네트워크 형식으로 형식적이고 객관적으로 묘사하기 위한 온톨로지 기반 지식지도의 필요성이 대두되어왔다. 본 논문은 지식 간의 상호참조적 네비게이션이 가능한 온톨로지 기반 지식지도를 구현하기 위한 방법론을 제시한다. 제시된 방법론에 의해 구현되는 온톨로지 기반 지식지도는 지식 간의 상호참조적 네비게이션을 가능하게 할 뿐만 아니라 이러한 지식 간 네트워크 관계에 의해 추가적인 지식 간의 관계를 추론할 수 있다. 제시된 개념의 타당성을 검증하기 위하여 두 가지의 실제 비즈니스 프로세스를 기반으로 지식지도를 구현하였고, 구현된 지식지도에 나타나는 지식 간 네트워크 구성의 유효성을 검토하였다.

• Educational Technology International
• /
• 제14권2호
• /
• pp.189-213
• /
• 2013

The study was conducted to find out the interaction between learning styles, and types of task on satisfaction and achievement in Chinese learning on Facebook. 44 students from D University in Seoul, Korea finished the questionnaires. To measure the participants' learning styles and satisfaction, the learning style instrument and satisfaction instrument were used. The data received were analyzed to find out the interaction between learning styles, and types of task on satisfaction and achievement. Through the analysis, the study suggests that, in the SNS environment for learning, instructors should focus on more on types of tasks than learning styles. Learning styles are important, however, for new pedagogy for one new learning environment, types of task are definitely more important than learning styles. Depending on the study results, the instructors should pay more attention to types of task, and they should also use different strategies to facilitate the contents of tasks to improve achievement and satisfaction in an SNS environment.

• Asia pacific journal of information systems
• /
• 제33권3호
• /
• pp.652-676
• /
• 2023

The objective of this study is to provide a deeper understanding of the factors that lead to the development and adoption of AI-based chatbots. We analyze the structural relationship between the organizational (externalities), systematic (fit), and the consumer-related (psychological) factors and their role in the adoption of AI-based chatbots. Founded on the theories of task-technology fit and network externalities, we present a conceptual model overlooking common perception-based theories (e.g., Technology Acceptance Model). We collected 380 responses from Indian banking consumers to test the model using the PLS-SEM method. Interestingly, the findings present a positive impact of all factors on consumers' intention to adopt AI-based chatbots. However, the interplays between these factors provide a mixed perspective for literature. Apart from employing a combination of factors that have been used to study technology adoption, our study explores the importance of externalities and their relationship with fit factors, a unique outlook often overlooked by prior research. Moreover, we offer a clear understanding of latent variables such as trust, and the intricacies of their interplays in a novel context. Thereby, the study offers implications for literature and practice, followed by future research directions.

• 대한인간공학회지
• /
• 제19권2호
• /
• pp.87-99
• /
• 2000

This study aims to examine a fuzzy logic-based human expert EMG prediction model (FLHEPM) for predicting electromyographic responses of trunk muscles due to manual lifting based on two task (control) variables. The FLHEPM utilizes two variables as inputs and ten muscle activities as outputs. As the results, the lifting task variables could be represented with the fuzzy membership functions. This provides flexibility to combine different scales of model variables in order to design the EMG prediction system. In model development, it was possible to generate the initial fuzzy rules using the neural network, but not all the rules were appropriate (87% correct ratio). With regard to the model precision, the EMG signals could be predicted with reasonable accuracy that the model shows mean absolute error of 8.43% ranging from 4.97% to 13.16% and mean absolute difference of 6.4% ranging from 2.88% to 11.59%. However, the model prediction accuracy is limited by use of only two task variables which were available for this study (out of five proposed task variables). Ultimately, the neuro-fuzzy approach utilizing all five variables to predict either the EMG activities or the spinal loading due to dynamic lifting tasks should be developed.