• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• 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.

• ETRI Journal
• /
• v.38 no.4
• /
• pp.714-723
• /
• 2016

Considerable attention has been given to processing graph data in recent years. An efficient method for computing the node proximity is one of the most challenging problems for many applications such as recommendation systems and social networks. Regarding large-scale, mutable datasets and user queries, top-k query processing has gained significant interest. This paper presents a novel method to find top-k answers in a node proximity search based on the well-known measure, Personalized PageRank (PPR). First, we introduce a distribution state transition graph (DSTG) to depict iterative steps for solving the PPR equation. Second, we propose a weight distribution model of a DSTG to capture the states of intermediate PPR scores and their distribution. Using a DSTG, we can selectively follow and compare multiple random paths with different lengths to find the most promising nodes. Moreover, we prove that the results of our method are equivalent to the PPR results. Comparative performance studies using two real datasets clearly show that our method is practical and accurate.

• Journal of Multimedia Information System
• /
• v.2 no.3
• /
• pp.263-274
• /
• 2015

The subject of this work is the complex discrete systems simulation special features with the aid of dynamic graph models. The proposed simulation technique allows to determine the ways for tasks solutions in terms of discrete systems analysis and synthesis of various complication: one-dimensional and multidimensional, steady and unstable, with the pulse elements abnormal operating mode and others. Often complex control systems analysis and synthesis task solutions, via classical approach comes out to be insolvent, because of the computational problems. The application of graph models allows to perform clear and strict characterization and computer procedures automation. The optimal controls synthesis algorithm presented in this paper, transferring the discrete system from target initial state to target final state within the minimum time, allows to consider the zero initial conditions systems, with the initial potential energy, with the control actions limitations and complex pulse elements operating mode.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1254-1271
• /
• 2018

Keyphrase extraction is one of fundamental natural language processing (NLP) tools to improve many text-mining applications such as document summarization and clustering. In this paper, we propose to use two novel techniques on the top of the state-of-the-art keyphrase extraction methods. First is the anti-patterns that aim to recognize non-keyphrase candidates. The state-of-the-art methods often used the rich feature set to identify keyphrases while those rich feature set cover only some of all keyphrases because keyphrases share very few similar patterns and stylistic features while non-keyphrase candidates often share many similar patterns and stylistic features. Second one is to use the dependency graph instead of the word co-occurrence graph that could not connect two words that are syntactically related and placed far from each other in a sentence while the dependency graph can do so. In experiments, we have compared the performances with different settings of the graphs (co-occurrence and dependency), and with the existing method results. Finally, we discovered that the combination method of dependency graph and anti-patterns outperform the state-of-the-art performances.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.213-217
• /
• 2007

소프트웨어 테스팅은 소프트웨어의 개발 과정에 있어서 가장 중요하고 많은 비용이 드는 부분이다. 소프트웨어 테스팅을 수동으로 행하는 것은 많은 문제를 발생시킬 수 있다. 소프트웨어 자동 테스팅을 하기 위해서 최근 활발히 연구되고 있는 부분이 모델 기반 소프트웨어 자동 테스팅 기법이다. 본 논문에서는 UML 모델 기반 테스트 케이스 자동 생성 기법을 제안한다. UML state chart 로 모델링 된 테스트 대상 소프트웨어를 제안된 자료구조에 저장 한 후, 이를 flow graph 로 변환한다. 최종적으로 변환된 flow graph 에서 테스트 케이스를 생성한다.

• Journal of Advanced Navigation Technology
• /
• v.14 no.6
• /
• pp.975-983
• /
• 2010

In this paper, we introduce extended problems of Tower of Hanoi (ToH) and propose a novel visualization method to express a state space of ToH. As for the extended problems, we introduce multi-peg ToH, multi-stack ToH, and regular state ToH. The novel visualization method in this paper is a natural extension of Hanoi graph visualization. In the proposed method, we assign one Cartesian coordinate point per each disk to provide an unified visualization that the marks on a link and the changes of a state should correspond with a peg position of a disk. Compared with Hanoi graph, the generated graph by the proposed method is isomorphic if we remove links of forbidden move, which indicates that our method is a generalization of Hanoi graph and thus is more expressive. To help the understanding of the readers, we show the generated graphs by our method when the number of disks is 2 and 3.

• Journal of the Korean Institute of Navigation
• /
• v.22 no.2
• /
• pp.81-87
• /
• 1998

On this paper, the methods of optimization research of the fishing navigation using the graph theory are substantiated on the basis of the proposed probable model of the fishing vessel navigator's activity. The graph theory is concered about the transitionform the top graph to the rib one. And the definition of the additional system elements (quasi elements) necessary to provide the effectiveness during the fishing navigation are also substantiated herein. This approach helps to optimize the structure of any fishing vessel monitoring system.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.425-430
• /
• 2002

An automatic transmission model using the bond graph techniques is developed for analyzing shift characteristics of vehicles. Bond graph models can be systemically manipulated to yield state space equations of standard form. Bond graph techniques are applied for modeling overall automatic transmission systems and shift models. A fuzzy controller is synthesized for the verification of a shifting model in the ${1^st} gear to the {2^nd}$ gear. Simulation results show the fitness of models by the bond graph techniques.

• Journal of Electrical Engineering and information Science
• /
• v.2 no.6
• /
• pp.43-47
• /
• 1997

A procedure presented in this paper generates test sequences to check the conformity of an implementation with a protocol specification, which is modeled as a deterministic finite state machine (FSM). Given a FSM, a common procedure of test sequence generation, first, constructs a directed graph which edges include the state check after each transition, and produces a symmetric graph G* from and, finally, finds a Euler tour of G*. We propose a technique to determine a minimum-cost tour of the transition graph of the FSM. The proposed technique using Multiple Unique State Signature (MUSS) solves an open issue that one MUIO sequence assignment may lead to two more edges of unit cost being replicated to from G* while an optimal assignment may lead to the replication of a single edge of high cost. In this paper, randomly generated FSMs have been studied as test cases. The result shows that the proposed technique saves the cost 4∼28% and 2∼21% over the previous approach using MUIO and MUSP, respectively.

• Proceedings of the KIEE Conference
• /
• 1990.11a
• /
• pp.450-456
• /
• 1990

In this paper, production system is implemented with the inferential neural network model using semantic network and directed graph. Production system can be implemented with the transform of knowledge representation in production system into semantic network and of semantic network into directed graph, because directed graphs can be expressed by neural matrices. A concept node should be defined by the state vector to calculated the concepts expressed by matrices. The expressional ability of neunal network depends on how the state vector is defined. In this study, state vector is overlapped and each overlapping part acts as a inheritant of concept.