• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.103-107
• /
• 2017

한국어 형태소 분석 및 구구조 구문 분석은 한국어 자연어처리에서 난이도가 높은 작업들로서 최근에는 해당 문제들을 출력열 생성 문제로 바꾸어 sequence-to-sequence 모델을 이용한 end-to-end 방식의 접근법들이 연구되었다. 한국어 형태소 분석 및 구구조 구문 분석을 출력열 생성 문제로 바꿀 시 해당 출력 결과는 하나의 열로서 합쳐질 수가 있다. 본 논문에서는 sequence-to-sequence 모델을 이용하여 한국어 형태소 분석 및 구구조 구문 분석을 동시에 처리하는 모델을 제안한다. 실험 결과 한국어 형태소 분석과 구구조 구문 분석을 동시에 처리할 시 형태소 분석이 구구조 구문 분석에 영향을 주는 것을 확인 하였으며, 구구조 구문 분석 또한 형태소 분석에 영향을 주어 서로 영향을 줄 수 있음을 확인하였다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.1
• /
• pp.148-154
• /
• 2012

For a successful checkpointing strategy, we should place checkpoints so as to optimize fault-tolerance capability of real-time systems. This paper presents a novel scheme of checkpoint placement for real-time systems with periodic multi-tasks. Under the influence of transient faults, multi-tasks are scheduled by the Rate Monotonic (RM) algorithm. The optimal checkpoint intervals are derived to maximize the probability of task completion. In particular, this paper is concerned about the general case that the deadline of a task is longer than the period. Compared with the special condition that the deadline is equal to or less than the period, this general case causes a more complicate test procedure for schedulability of the RM algorithm with respect to a given set of checkpoint re-execution vectors. The probability of task completion is also derived in a more complex form. A case study is given to show the applicability of the proposed scheme.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.472-474
• /
• 2019

Because of the difference in network structure and loss function, Verification and identification models have their respective advantages and limitations for person reidentification (re-ID). In this work, we propose a multi-task network simultaneously computes the identification loss and verification loss for person reidentification. Given a pair of images as network input, the multi-task network simultaneously outputs the identities of the two images and whether the images belong to the same identity. In experiments, we analyze the major factors affect the accuracy of person reidentification. To address the occlusion problem and improve the generalization ability of reID models, we use the Random Erasing Augmentation (REA) method to preprocess the images. The method can be easily applied to different pre-trained networks, such as ResNet and VGG. The experimental results on the Market1501 datasets show significant and consistent improvements over the state-of-the-art methods.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1149-1159
• /
• 2019

We present a novel deep learning architecture for obtaining a latent image from a single blurry image, which contains dynamic motion blurs through object/camera movements. The proposed architecture consists of two sub-modules: blur image restoration and optical flow estimation. The tasks are highly related in that object/camera movements make cause blurry artifacts, whereas they are estimated through optical flow. The ablation study demonstrates that training multi-task architecture simultaneously improves both tasks compared to handling them separately. Objective and subjective evaluations show that our method outperforms the state-of-the-arts deep learning based techniques.

• Journal of Aerospace System Engineering
• /
• v.17 no.2
• /
• pp.78-85
• /
• 2023

For Multi-UAV systems, a task allocation could be a key factor to determine the capability to perform a task. In this paper, we proposed a task allocation method based on genetic algorithm for minimizing makespan and satisfying various constraints. To obtain the optimal solution of the task allocation problem, a huge calculation effort is necessary. Therefore, a genetic algorithm-based method could be an alternative to get the answer. Many types of UAVs, tasks, and constraints in real worlds are introduced and considered when tasks are assigned. The proposed method can build the task sequence of each UAV and calculate waiting time before beginning tasks related to constraints. After initial task allocation with a genetic algorithm, waiting time is added to satisfy constraints. Multiple numerical simulation results validated the performance of this mission planning method with minimized makespan.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.896-902
• /
• 2004

The purpose of the study of multi-robot system is to realize multi-robot system easy for the control of robot system in case robot is adapted in the complicated environment of task structure. The purpose of the study of multi-robot system is to realize multi-robot system easy for the control of robot system in case robot is adapted in the complicated environment of task structure. To make real time control possible by making effective use of recognized information in this dynamic environment, suitable distribution of tasks should be made in consideration of function and role of each performing robots. In this paper, IHMA (Intelligent Hybrid Modular Architecture) of Intelligent combined control architecture which utilizes the merits of deliberative and reactive controllers will be suggested and its efficiency will be evaluated through the adaptation of control architecture to representative multi-robot system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.149.3-149
• /
• 2001

Task allocation is a key problem in multiagent systems. The importance of automated negotiation protocols for solving the task allocation problem is increasing as a consequence of increased multi-agent applications. In this paper, we introduce the multiagent Traveling Salesman Problem(TSP) as an example of task reallocation problem, and suggest Vickery auction as an inter-agent coordination mechanism for solving this problem. In order to apply this market-based coordination mechanism into multiagent TSPs, we define the profit of each agent, the ultimate goal of negotiation, cities to be traded out through auctions, the bidding strategy, and the order of auctions. The primary advantage of such approach is that it can find an optimal task allocation ...

• Korean Journal of Cognitive Science
• /
• v.24 no.1
• /
• pp.71-93
• /
• 2013

Multitasking has become part of our life. Self-interruption and switching to another task become easier and more frequent. According to previous studies, however, most of the task-switching incurs a cognitive cost. This study investigated the benefit from task switching. In Study 1, participants performed two tasks were similar, and negative correlation between the number of task switching and performance were confirmed, this result is similar to previous studies. Study 2 has shown that, made a comparison of two conditions, between possible and impossible conditions in terms of task switching. Depending on switching preference, the result of task performance has differentiated and the emotion that participants had before the task has changed. Depending on participants' switching preference, there were different amount of switching cost. Moreover, for participants who preferred task switching highly than others, task switching occurred more benefit than cost.

• Journal of Convergence for Information Technology
• /
• v.10 no.12
• /
• pp.216-225
• /
• 2020

This study was conducted to qualitatively analyze the selected research through a systematic review to find out application method, outcome measures, and intervention effects of dual task. We searched for published studies from January 2010 to December 2019. Electrical database were PubMed and ProQuest. Search terms were 'dual task' OR 'multi modal' AND 'mild cognitive impairment' OR 'dementia' OR 'Alzheimer's disease'AND 'intervention' OR 'rehabilitation. There were 8 studies selected finally. The dual task was applied not as a single intervention but as a combined intervention with other exercises. The contents of dual task were consisted of motor and cognitive tasks to be independent each other. The outcome measures included general cognitive function such as MMSE and CERAD, executive function, and memory. Additionally the dual task cost was also used to identify the direct improvement of the dual task. This study could provide informations of dual task application on elderly with cognitive impairment.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.37-45
• /
• 2022

In this paper, a multi agent-multi task assignment problem, which is a representative problem of combinatorial optimization, is presented. The objective of the problem is to determine the coordinated agent-task assignment that maximizes the sum of the achievement rates of each task. The achievement rate is represented as a concave down increasing function according to the number of agents assigned to the task. The problem is expressed as an NP-hard problem with a non-linear objective function. In this paper, to solve the assignment problem, we propose a hybrid cross-entropy algorithm as an effective and efficient solution methodology. In fact, the general cross-entropy algorithm might have drawbacks (e.g., slow update of parameters and premature convergence) according to problem situations. Compared to the general cross-entropy algorithm, the proposed method is designed to be less likely to have the two drawbacks. We show that the performances of the proposed methods are better than those of the general cross-entropy algorithm through numerical experiments.