• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.29-30
• /
• 2022

Curriculum learning은 딥러닝의 성능을 향상시키기 위해 사람의 학습 과정과 유사하게 일종의 'curriculum'을 도입해 모델을 학습시키는 방법이다. 대부분의 연구는 학습 데이터 중 개별 샘플의 난이도를 기반으로 점진적으로 모델을 학습시키는 방안에 중점을 두고 있다. 그러나, coarse-to-fine 메카니즘은 데이터의 난이도보다 학습에 사용되는 class의 유사도가 더욱 중요하다고 주장하며, 여러 난이도의 auxiliary task를 차례로 학습하는 방법을 제안했다. 그러나, 이 방법은 혼동행렬 기반으로 class의 유사성을 판단해 auxiliary task를 생성함으로 다중 레이블 분류에는 적용하기 어렵다는 한계점이 있다. 따라서, 본 논문에서는 multi-label 환경에서 multi-class와 binary task를 생성하는 방법을 제안해 coarse-to-fine 메카니즘 적용을 위한 방안을 제시하고, 그 결과를 분석한다.

• 한국공작기계학회논문집
• /
• 제12권3호
• /
• pp.31-37
• /
• 2003

With the paradigm shifting from the principal of manufacturing efficiency to business globalism and rapid adaptation to its environments, more and more enterprises are being virtually organized as manufacturing network of different units in web. The formation of these enterprise called as Virtual Enterprise(VE) is becoming a growing trend as enterprises concentrating on core competence and economic benefit. 13us paper proposes multi-agent based task assignment system for VE, which attempts to address the selection of individually managed partners and the task assignment to them A case example is presented to illustrate how the proposed system can assign the task to partners.

• 대한인간공학회지
• /
• 제25권3호
• /
• pp.7-16
• /
• 2006

Although several theories and models have been proposed to explain the effects of cultural differences in team decision making, many aspects of team decision-making in multi-cultural contexts such as team performance, team communication, and team cognition still remain unclear. In particular, little attention has paid to the empirical studies on team processes multi-cultural team members use to interact with each other to accomplish the task in different task environments. To investigate the effects of culture and task characteristics on team decision making behavior in multi-cultural contexts, this study compared culturally homogenous and heterogeneous groups in the context of logistics decision making. Results of the study showed that cultural difference and task complexity may affect team performance as well as team interaction process to varying degree.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3638-3657
• /
• 2022

In urban vehicular edge computing (VEC) environments, one edge server always serves many task requests in its coverage which results in the resource-constrained problem. To resolve the problem and improve system utilization, we first design a general hierarchical resource management framework based on typical VEC network structures. Following the framework, a specific interacting protocol is also designed for our decision algorithm. Secondly, a greedy bidding-based multi-hop task scheduling decision algorithm is proposed to realize effective task scheduling in resource-constrained VEC environments. In this algorithm, the goal of maximizing system utility is modeled as an optimization problem with the constraints of task deadlines and available computing resources. Then, an auction mechanism named greedy bidding is used to match task requests to edge servers in the case of multiple hops to maximize the system utility. Simulation results show that our proposal can maximize the number of tasks served in resource constrained VEC networks and improve the system utility.

• 한국자동차공학회논문집
• /
• 제24권2호
• /
• pp.127-136
• /
• 2016

The camera based object detection systems should satisfy the recognition performance as well as real-time constraints. Particularly, in safety-critical systems such as Autonomous Emergency Braking (AEB), the real-time constraints significantly affects the system performance. Recently, multi-core processors and system-on-chip technologies are widely used to accelerate the object detection algorithm by distributing computational loads. However, due to the advanced hardware, the complexity of system architecture is increased even though additional hardwares improve the real-time performance. The increased complexity also cause difficulty in migration of existing algorithms and development of new algorithms. In this paper, to improve real-time performance and design complexity, a task scheduling strategy is proposed for visual object tracking systems. The real-time performance of the vision algorithm is increased by applying pipelining to task scheduling in a multi-core processor. Finally, the proposed task scheduling algorithm is applied to crosswalk detection and tracking system to prove the effectiveness of the proposed strategy.

• 한국항공우주학회지
• /
• 제42권3호
• /
• pp.254-262
• /
• 2014

레이더 임무 스케줄링은 제한된 자원 환경에서 레이더의 성능을 향상시키기 위해 효과적으로 임무 배치를 하는 것이다. 본 논문에서는 다기능 레이더의 복수 운용 시의 스케줄링 성능 평가를 위해 총 지연 시간의 합을 목적함수로 정의하고, 실시간성을 고려한 휴리스틱 접근법을 제시한다. 제안된 스케줄링 기법들을 일반적인 임무 시뮬레이션 환경에서 비교 분석하였으며, 특히, 다기능 레이더의 복수 운용에서의 스케줄링 성능을 분석한다.

• 한국멀티미디어학회논문지
• /
• 제22권9호
• /
• pp.1000-1010
• /
• 2019

Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2004년도 추계학술대회
• /
• pp.166-169
• /
• 2004

In this paper show how to design a redundant robot which is suitable for the multiple task without any constraints on the workspace. The implementation is possible by the rigid connection of a mobile robot and a task robot. Use a five joint articulated robot as the task robot; designed the 3 joint mobile robot for this usage. For a task execution assigned to the redundant robot, not only the task robot but the mobile robot should work in the coordinated way. therefore, a kinematic connection of the two robots should be cleary represented in a frame. And, also the dynamic interaction between the two robots needs to be analyzed. Clarified these issues considering the control of the redundant robot. Finally, demonstrate away of utilization of the redundancy as the cooperation between the mobile robot and the task robot to execute a common task.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (A)
• /
• pp.832-834
• /
• 2005

임베디드 시스템은 범용 컴퓨팅 시스템과 달리 자신을 포함하고 있는 기기에 부과된 특정 목적의 컴퓨팅 작업만을 수행한다. 이 시스템을 제어하기 위해서 운영체제가 필요로 하며, 임베디드 환경에서는 신뢰성과 정확성을 요하는 부분이 많기 때문에 실시간 운영체제를 필요로 한다. Real-Time kernel을 기반으로 하는 MicroC/OS-II는 수많은 용도로 사용되고 있지만 task 사용에 한계가 있다. 이 논문에서 제안하는 스케줄링은 task의 생성 수를 늘려주지만, 이 경우 task간의 우선순위 설정이 어려워진다. 이 문제 해결을 위해서 task들의 우선순위 결정은 deadline을 이용하여 3레벨로 나눈다. 3레벨로 나누어지면 task의 수가 증가해도 개발자는 task들을 레벨에 맞게 설정하면 task 관리로 인하여 생기는 문제를 줄일 수 있으며, 효율적인 스케줄링을 가능하게 한다.

• 제어로봇시스템학회논문지
• /
• 제3권2호
• /
• pp.187-196
• /
• 1997

This paper presents a semi-automatic methodology to synthesize executable digital controller saftware in a multi-loop control system. A digital controller is described by a task graph and end-to-end timing requirements. A task graph denotes the software structure of the controller, and the end-to-end requirements establish timing relationships between external inputs and outputs. Our approach translates the end-to-end requirements into a set of task attributes such as task periods and deadlines using nonlinear optimization techniques. Such attributes are essential for control engineers to implement control programs and schedule them in a control system with limited resources. In current engineering practice, human programmers manually derive those attributes in an ad hoc manner: they often resort to radical over-sampling to safely guarantee the given timing requirements, and thus render the resultant system poorly utilized. After task-specific attributes are derived, the tasks are scheduled on a single CPU and the compiled kernel is synthesized. We illustrate this process with a non-trivial servo motor control system.