• 제목/요약/키워드: AI engine

검색결과 73건 처리시간 0.029초

사물인터넷 기반 소셜로봇 시스템의 분석 및 설계 (Analysis and Design of Social-Robot System based on IoT)

  • 조병호
    • 한국인터넷방송통신학회논문지
    • /
    • 제19권1호
    • /
    • pp.179-185
    • /
    • 2019
  • 소셜로봇의 핵심기술은 음성인식 및 대화엔진인데 이를 개발하는데 많은 비용이 들고 음성인식률 및 대화엔진의 성능의 부족으로 인한 로봇과의 대화기능 구현이 어려웠다. IoT 기반의 클라우드 인공지능 기술의 발전과 여러 기업이 이들 오픈 API 제공으로 로봇과 인간과의 대화 기능 구현이 가능하게 됐다. 본 논문에서는 기존의 지능형 소셜로봇 기술동향을 조사하고 효율적인 IoT 기반 소셜로봇 시스템 구조를 설계한다. 또한 객체지향방법을 이용한 사용자 요구사항 분석, 플로우 차트 및 화면 설계를 보여줌으로 효과적인 소셜로봇 소프트웨어 분석 및 설계 방법을 제시하고자 한다.

기체연료 엔진에서 공연비제어를 위한 흡입공기량 추정 (Estimation of Inlet Air Mass Flow for Air-Fuel Raito Control of Gaseous-Fuel Engines)

  • 심한섭;이강윤;선우명호;송창섭
    • 한국자동차공학회논문집
    • /
    • 제9권5호
    • /
    • pp.131-139
    • /
    • 2001
  • Highly accurate control of the air-fuel ratio is important to reduce exhaust gas emissions of the gaseous-fuel engines. In order to achieve this purpose, inlet air mass flow must be measured exactly, and precise engine models are necessary to design engine control systems. In this paper, the effects of water vapor and gaseous fuel that change the air mass flow are studied. The effective air mass ratio is defined as the air mass flow divided by the mixture mass flow, and also it is applied to the estimation of the inlet air mass flow. The presence of the gaseous fuel and the water vapor in the mixture reduces the air partial pressure and the effective air mass ratio of the gaseous-fuel engines. The Experimental results for an LPG engine show that the estimation of the inlet ai mass flow based upon the effective air mass ratio is more accurate than that of the normal air mass flow.

  • PDF

지식기반 객체지향 군수시뮬레이션 모델에 관한 연구 - 초기군수지원성 분석모델을 중심으로 - (Knowledge Based and Object-Oriented Simulation Model for Logistics Analysis)

  • 마호명;최상영
    • 한국국방경영분석학회지
    • /
    • 제22권1호
    • /
    • pp.67-80
    • /
    • 1996
  • Artificial Intelligence(AI) techniques and Object-Oriented(OO) techniques contribute to the simulation modeling of the complex systems. AI techniques are suitable to model human reasoning in the simulation. While OO techniques have advantages of re-usability, maintainability and extendability of the software. Thus, in this paper, we design a knowledge-based object-oriented simulation model, particularly for the logistics analysis of military armor vehicles. The simulation model consists of three modules i.e., scenario, simulation mechanism, and inference engine. The model is designed within the OO paradigm and implemented by using the C++ language. An example case of using the model for the logistic analysis is included.

  • PDF

Implementation of an Autostereoscopic Virtual 3D Button in Non-contact Manner Using Simple Deep Learning Network

  • You, Sang-Hee;Hwang, Min;Kim, Ki-Hoon;Cho, Chang-Suk
    • Journal of Information Processing Systems
    • /
    • 제17권3호
    • /
    • pp.505-517
    • /
    • 2021
  • This research presented an implementation of autostereoscopic virtual three-dimensional (3D) button device as non-contact style. The proposed device has several characteristics about visible feature, non-contact use and artificial intelligence (AI) engine. The device was designed to be contactless to prevent virus contamination and consists of 3D buttons in a virtual stereoscopic view. To specify the button pressed virtually by fingertip pointing, a simple deep learning network having two stages without convolution filters was designed. As confirmed in the experiment, if the input data composition is clearly designed, the deep learning network does not need to be configured so complexly. As the results of testing and evaluation by the certification institute, the proposed button device shows high reliability and stability.

Unity ML-Agents Toolkit을 활용한 대상 객체 추적 머신러닝 구현 (Implementation of Target Object Tracking Method using Unity ML-Agent Toolkit)

  • 한석호;이용환
    • 반도체디스플레이기술학회지
    • /
    • 제21권3호
    • /
    • pp.110-113
    • /
    • 2022
  • Non-playable game character plays an important role in improving the concentration of the game and the interest of the user, and recently implementation of NPC with reinforcement learning has been in the spotlight. In this paper, we estimate an AI target tracking method via reinforcement learning, and implement an AI-based tracking agency of specific target object with avoiding traps through Unity ML-Agents Toolkit. The implementation is built in Unity game engine, and simulations are conducted through a number of experiments. The experimental results show that outstanding performance of the tracking target with avoiding traps is shown with good enough results.

Data mining and Copyright

  • Kim, Kyungsuk
    • International Journal of Internet, Broadcasting and Communication
    • /
    • 제14권4호
    • /
    • pp.11-19
    • /
    • 2022
  • Data mining has broad applications that reach beyond scholarly and scientific research and provide internet search engine services that are commonly used forms of Text and Data Mining('TDM') of websites. The exceptions and limitations for data mining provide a competitive advantage in the global race for policy innovation because it permits researchers to conduct computational analysis - TDM on any materials to which they have access. For this purpose, Japan and the EU added limitations on copyright to legalize some TDM research through amendments to copyright law, and the U.S. copyright law has allowed data mining by the fair use provision. On the other hand, there are no explicit exceptions and limitations for data mining under the Korean Copyright Act, and there are no cases considering data mining fair use. We review comparatively exceptions and limitations on copyright which will help to encourage AI-related business by using more data smoothly through the mining process and extracting more valuable information.

모션 트래킹을 이용한 가상현실 복싱 게임 개발 (Development of virtual reality boxing game contents using motion tracking)

  • 김영권;권기재;윤나리;김종인;윤태진
    • 한국컴퓨터정보학회:학술대회논문집
    • /
    • 한국컴퓨터정보학회 2021년도 제64차 하계학술대회논문집 29권2호
    • /
    • pp.517-518
    • /
    • 2021
  • 본 논문에서는 게임 개발 플랫폼인 언리얼 엔진 4을 사용하여 가상현실기술을 활용한 복싱 게임을 개발하였다. 복싱 게임을 더욱 실감나게 즐길 수 있도록 하기 위해 양 손에 부착한 VIVE 트래커로 복싱 동작을 모션 트래킹하여 아바타를 제어하였다. 게임 모드의 경우 연습모드와 스파링모드로 구성하였다. 연습모드에서 튜토리얼을 진행하여 게임플레이를 익힌 후 스파링모드에서 AI와 복싱 대결을 하도록 구현하였다. 스파링모드는 AI와 플레이어가 대결을 하며 먼저 체력을 소모시키면 승리하게 된다. 그리고 AI 캐릭터의 애니메이션 재생 속도에 따라 4가지 난이도를 설정할 수 있다. 가상현실 복싱게임은 VR기술을 이용하여 가정에서 간편하게 복싱 운동을 즐길 수 있으며, 더 많은 VIVE 트래커를 활용하면 정밀한 모션 트래킹이 가능하여 현실감을 높일 수 있다.

  • PDF

추론엔진을 위한 ECBM의 설계 구현 (Design and Implementation of the ECBM for Inference Engine)

  • 신정훈;오명륜;오광진;이양원;류근호;김영훈
    • 한국정보처리학회논문지
    • /
    • 제4권12호
    • /
    • pp.3010-3022
    • /
    • 1997
  • 1970년대 후반에 제안된 전문가 시스템은 인공지능의 한 분야로서, 인간의 사고방식을 모방함으로써 다양한 분야에서 야기되는 문제들을 해결해준다. 대부분의 전문가 시스템은 추론엔진과 지식베이스등과 같은 많은 요소들로 구성 된다. 특히 전문가 시스템의 성능은 추론엔진의 효율성에 의해 좌우된다. 이러한 추론 엔진은 지식 베이스가 구축될 때, 가능한 한 적은 제약성을 가져야 함은 물론, 다양한 추론 방법을 제공해야 한다는 특징을 갖고 있어야 한다. 이 논문에서는 지식 영역과 추론 방식에 대한 범용성을제공하는 추론 엔진을 설계 및 구현하였다. 이를 위해 추론 방식은 사용자에 의해 전향추론과 후향추론 및 직첩추론이 선택적으로 수행된다. 또한 목표 영역에서의 지식 획득을 위한 쉬운 표준화와 모듈화를 가능케하는 생성 규칙을 사용하였을 뿐만 아니라 확장된 CBM을 통해 지식 베이스를 구축하였다. 아울러, Rete 패턴 매칭과 ECBM을 이용한 추론 엔진간의 성능분석을 수행하였다.

  • PDF

CLIPS를 사용한 한글 전문가 시스템을 위한 사용자 인터페이스이 개발(開發) (Development of User-Interfaces for Expert System Using CLIPS)

  • 조성인;김승찬
    • Journal of Biosystems Engineering
    • /
    • 제18권2호
    • /
    • pp.133-143
    • /
    • 1993
  • In developing an Expert System(ES), there are two ways. One is to develop an ES using AI(artificial Intelligence) languages and another using ES-development tools. CLIPS is an ES-development tool and has a powerful inference engine in it. Using the tool like CLIPS, knowledge engineer can concentrate on constructing a knowledge base without wasting time in developing an inference engine. However, CLIPS is lack of user-friendly interfaces for both knowledge enginners and users. Because CLIPS was developed in USA, it can not afford to use Korean language. Therefore, several user-friendly interfaces including hmenu, htille, hpcxdisplay were develpoed and added to CLIPS. CLIPS with the interfaces is called HCLIPS(Hangul CLIPS) in this paper. HCLIPS provides a new I/O device to be utilized for expert systems in Korean. HCLIPS can be efficiently used for developing expert systems in agriculture and consulting farmers interactively who are not familiar with computer programming and ES itself.

  • PDF

공기흡입식 추진기관용 연료조절밸브시스템 개발에 관한 연구 (A Study on the Development of Fuel Metering Unit for Air Breathing Engine)

  • 이도윤;최현영;박종승;구자용
    • 한국군사과학기술학회지
    • /
    • 제8권4호
    • /
    • pp.152-158
    • /
    • 2005
  • In this paper, we have proposed a fuel metering unit of ai breathing engine. The proposed valve system consists of a constant pressure drop valve and a metering valve, which are controlled by servovalve. We carried out nonlinear and linear analysis, computer simulation and experimentation to find effects of some factors on system performance. Analysis and experimental results show a good agreement. It is also shown that the system stability is affected by pressure drop of metering valve and inlet pressure of injectors.