• 로봇학회논문지
• /
• 제19권2호
• /
• pp.196-202
• /
• 2024

The ability to understand given environments and plan a sequence of actions leading to goal state is crucial for personal service robots. With recent advancements in deep learning, numerous studies have proposed methods for state representation in planning. However, previous works lack explicit information about relationships between objects when the state observation is converted to a single visual embedding containing all state information. In this paper, we introduce graph-based state representation that incorporates both object and relationship features. To leverage these advantages in addressing the task planning problem, we propose a Graph Neural Network (GNN)-based subgoal prediction model. This model can extract rich information about object and their interconnected relationships from given state graph. Moreover, a search-based algorithm is integrated with pre-trained subgoal prediction model and state transition module to explore diverse states and find proper sequence of subgoals. The proposed method is trained with synthetic task dataset collected in simulation environment, demonstrating a higher success rate with fewer additional searches compared to baseline methods.

• 산업경영시스템학회지
• /
• 제20권42호
• /
• pp.39-47
• /
• 1997

There are four parameters (i.e. overall density, local density, grouping, layout complexity) to consider in designing screen of a visual display terminal. Among these, only the optimum level of overall density is known to be about 25~30% by some studies. Therefore, the present experiment is conducted to define the optimum levels of the other parameters to achieve the user's best performance in visual search task. The results are as follows; (1) The function related to the levels of local density and user's search times is shown to be U -shaped. When the level of local density is about 40%, the search time is shorter than those of any other levels. (2) In the experiment of grouping, user's performance is best when the number of group is 5, and the size of group does not exceed visual angle $5^{\circ}$ (0,088rad). (3) The user performance is improved as the layout becomes less complex.

• ETRI Journal
• /
• 제44권5호
• /
• pp.746-758
• /
• 2022

This paper focuses on a mobile edge-computing-enabled heterogeneous network. A battery level-aware task-scheduling framework is proposed to improve the energy efficiency and prolong the operating hours of battery-powered mobile devices. The formulated optimization problem is a typical mixed-integer nonlinear programming problem. To solve this nondeterministic polynomial (NP)-hard problem, a decomposition-based task-scheduling algorithm is proposed. Using an alternating optimization technology, the original problem is divided into three subproblems. In the outer loop, task offloading decisions are yielded using a pruning search algorithm for the task offloading subproblem. In the inner loop, closed-form solutions for computational resource allocation subproblems are derived using the Lagrangian multiplier method. Then, it is proven that the transmitted power-allocation subproblem is a unimodal problem; this subproblem is solved using a gradient-based bisection search algorithm. The simulation results demonstrate that the proposed framework achieves better energy efficiency than other frameworks. Additionally, the impact of the battery level-aware scheme on the operating hours of battery-powered mobile devices is also investigated.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2011년도 춘계학술대회
• /
• pp.81-82
• /
• 2011

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2436-2457
• /
• 2023

The elderly population is rapidly increasing worldwide, but many face challenges in using digital tools like the Internet due to health and incapacity issues. Existing online search user interfaces (UIs) often overlook the specific usability needs of the elderly. This study proposes an adaptable web search UI model for the elderly, based on their perspectives, to enhance search performance and usability. The proposed UI model is evaluated through comparative usability testing with 20 participants, comparing it to the Google search UI. Effectiveness, efficiency, and satisfaction are measured using task completion time, error rate, and subjective preferences. The results show significant differences (p > 0.05) between the proposed web search UI model and the Google search UI. The proposed UI model achieves higher subjective satisfaction levels, indicating better alignment with the needs and preferences of elderly users. It also reduces task completion time, indicating improved efficiency, and decreases the error rate, suggesting enhanced effectiveness. These findings emphasize the importance of considering the unique usability needs of the elderly when designing search UIs. The proposed adaptable web search UI model offers a promising approach to enhance the digital experiences of elderly users. This study lays the groundwork for further development and refinement of adaptable web search UI models that cater to the specific needs of elderly users, enabling designers to create more inclusive and user-friendly search interfaces for the growing elderly population.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권4호
• /
• pp.300-307
• /
• 2012

When the volume of data grows big, some simple tasks could become a significant concern. Nearest neighbor search is such a task which finds from a data set the k nearest data points to queries. Locality-sensitive hashing techniques have been developed for approximate but fast nearest neighbor search. This paper introduces the notion of locality-sensitive hashing and surveys the locality-sensitive hashing techniques. It categories them based on several criteria, presents their characteristics, and compares their performance.

• 한국문헌정보학회지
• /
• 제49권2호
• /
• pp.51-73
• /
• 2015

인터넷은 20-30년 전에는 상상할 수 없었던 엄청난 양의 정보에 대한 즉각적인 접근을 가능하게 하고 있다. 하지만 정보를 표현한 언어가 다양한 국가의 언어로 제공됨으로 이용자는 인터넷상에서 제공되는 컨텐츠를 온전히 사용하기 위해 반드시 외국어에 대한 이해를 수반해야 한다. 2015년 한 통계에 따르면 전 세계 웹사이트의 약 55%가 영어로 제작되어 있다고 한다. 따라서 정보탐색에 있어 웹 컨텐츠의 절반 이상에서 사용되고 있는 영어의 중요성을 간과할 수 없는 것이다. 본 연구는 인터넷을 활용한 정보문제 해결에 있어 검색 질의의 언어와 질의문의 복잡성이 검색 성과에 어떤 영향을 미치는지 살펴보고자 하였다. 실험은 서울 시내 종합사립대학교에 재학 중인 30명의 학생들을 대상으로 실시하였다. 연구자는 피험자들에게 각각 총 8개의 검색과제를 무선방식으로 제공하였다. 이들 과제는 각각 4개씩의 한글과 영어로 된 질의로, 이는 다시 같은 수의 단순 질의와 복합 질의로 나누어진다. 실험 결과 단순 질의와 복합 질의 간 검색에 소요된 시간, 검색 횟수, 정답률에 있어 통계적으로 유의미한 차이를 보였다. 하지만 질의 언어가 검색 성과 지표에는 영향을 미치지 않는 것으로 나타났다. 또 학생들의 영어구사수준 역시 검색성과에 영향을 미치지 않았다. 그러나 검색과 관련된 다른 지표(검색 언어의 사용 및 검색엔진 선택)에 있어서는 검색 언어와 검색 복잡성이 영향을 미치는 것으로 나타났다.

• 전자공학회논문지B
• /
• 제29B권3호
• /
• pp.6-15
• /
• 1992

This paper proposes a method for the global optimization of redundancy over the whole task period for a kinematically redundant robot. The necessary conditions based on the calculus of variations for an integral type cost criterion result in a second-order differential equation. For a cyclic task, the periodic boundary conditions due to conservativity requirements are discussed. We refine the two-point boundary value problem to an initial value adjustment problem and suggest a numerical search method for providing the conservative global optimal solution using the gradient projection method. Since the initial joint velocity is parameterized with the number of the redundancy, we only search the parameter value in the space of as many dimensions as the number of degrees of redundancy. We show through numerical examples that multiple nonhomotopic extremal solutions and the generality of the proposed method by considering the dynamics of a robot.

• International journal of advanced smart convergence
• /
• 제11권3호
• /
• pp.64-71
• /
• 2022

Various types of attendance management systems are being introduced in a remote working environment and research on using face recognition is in progress. To ensure accurate worker's attendance, a face recognition-based attendance management system must analyze every frame of video, but face recognition is a heavy task, the number of the task should be minimized without affecting accuracy. In this paper, we proposed a search model using time interval variation to minimize the number of face recognition task of recorded videos for attendance management system. The proposed model performs face recognition by changing the interval of the frame identification time when there is no change in the attendance status for a certain period. When a change in the face recognition status occurs, it moves in the reverse direction and performs frame checks to more accurate attendance time checking. The implementation of proposed model performed at least 4.5 times faster than all frame identification and showed at least 97% accuracy.

• 한국멀티미디어학회논문지
• /
• 제20권7호
• /
• pp.986-993
• /
• 2017

Object Tracking is a technique for tracking moving objects over time in a video image. Using object tracking technique, many research are conducted such a detecting dangerous situation and recognizing the movement of nearby objects in a smart car. However, it still remains a challenging task such as occlusion, deformation, background clutter, illumination variation, etc. In this paper, we propose a novel deep visual object tracking method that can be operated in robust to many challenging task. For the robust visual object tracking, we proposed a Convolutional Neural Network(CNN) which shares weight of the convolutional layers. Input of the CNN is a three; first frame object image, object image in a previous frame, and current search frame containing the object movement. Also we propose a method to consider the motion of the object when determining the current search area to search for the location of the object. Extensive experimental results on a authorized resource database showed that the proposed method outperformed than the conventional methods.