• Title/Summary/Keyword: intelligent behavior

Search Result 683, Processing Time 0.024 seconds

An Intelligent Emotion Recognition Model Using Facial and Bodily Expressions

  • Jae Kyeong Kim;Won Kuk Park;Il Young Choi
    • Asia pacific journal of information systems
    • /
    • v.27 no.1
    • /
    • pp.38-53
    • /
    • 2017
  • As sensor technologies and image processing technologies make collecting information on users' behavior easy, many researchers have examined automatic emotion recognition based on facial expressions, body expressions, and tone of voice, among others. Specifically, many studies have used normal cameras in the multimodal case using facial and body expressions. Thus, previous studies used a limited number of information because normal cameras generally produce only two-dimensional images. In the present research, we propose an artificial neural network-based model using a high-definition webcam and Kinect to recognize users' emotions from facial and bodily expressions when watching a movie trailer. We validate the proposed model in a naturally occurring field environment rather than in an artificially controlled laboratory environment. The result of this research will be helpful in the wide use of emotion recognition models in advertisements, exhibitions, and interactive shows.

Effect of Microstructure and Unit Cell's Geometry on the Compressive Mechanical Response of Additively Manufactured Co-Cr-Mo Sheet I-WP Lattice

  • So-Yeon Park;Kyu-Sik Kim;Bandar Almangour;Kee-Ahn Lee
    • Archives of Metallurgy and Materials
    • /
    • v.67 no.4
    • /
    • pp.1525-1529
    • /
    • 2022
  • Co-Cr-Mo based sheet I-WP lattice was fabricated via laser powder bed fusion. The effect of microstructure and the I-WP shape on compressive mechanical response was investigated. Results of compression test showed that yield strength of the sheet I-WP was 176.3 MPa and that of bulk Co-Cr-Mo (reference material) was 810.4 MPa. By applying Gibson-Ashby analytical model, the yield strength of the lattice was reversely estimated from that of the bulk specimen. The calculated strength of the lattice obtained was 150.7 MPa. The shape of deformed lattice showed collective failure mode, and its microstructure showed that strain-induced martensitic transformation occurred in the overall lattice. The deformation behavior of additively manufactured sheet I-WP lattice was also discussed.

Assessment of flexural and splitting strength of steel fiber reinforced concrete using automated neural network search

  • Zhang, Zhenhao;Paul, Suvash C.;Panda, Biranchi;Huang, Yuhao;Garg, Ankit;Zhang, Yi;Garg, Akhil;Zhang, Wengang
    • Advances in concrete construction
    • /
    • v.10 no.1
    • /
    • pp.81-92
    • /
    • 2020
  • Flexural and splitting strength behavior of conventional concrete can significantly be improved by incorporating the fibers in it. A significant number of research studies have been conducted on various types of fibers and their influence on the tensile capacity of concrete. However, as an important property, tensile capacity of fiber reinforced concrete (FRC) is not modelled properly. Therefore, this paper intends to formulate a model based on experiments that show the relationship between the fiber properties such as the aspect ratio (length/diameter), fiber content, compressive strength, flexural strength and splitting strength of FRC. For the purpose of modeling, various FRC mixes only with steel fiber are adopted from the existing research papers. Automated neural network search (ANS) is then developed and used to investigate the effect of input parameters such as fiber content, aspect ratio and compressive strength to the output parameters of flexural and splitting strength of FRC. It is found that the ANS model can be used to predict the flexural and splitting strength of FRC in a sensible precision.

Frequency Estimation Method using Recursive Discrete Wavelet Transform for Fault Disturbance Recorder (FDR를 위한 RDWT에 의한 주파수 추정 기법)

  • Park, Chul-Won;Ban, Yu-Hyeon
    • The Transactions of The Korean Institute of Electrical Engineers
    • /
    • v.60 no.8
    • /
    • pp.1492-1501
    • /
    • 2011
  • A wide-area protection intelligent technique has been used to improve a reliability in power systems and to prevent a blackout. Nowadays, voltage and current phasor estimation has been executed by GPS-based synchronized PMU, which has become an important way of wide-area blackout protection for the prevention of expending faults in power systems. As this technique has the difficulties in collecting and sharing of information, there have been used a FNET method for the wide-area intelligent protection. This technique is very useful for the prediction of the inception fault and for the prevention of fault propagation with accurate monitoring frequency and frequency deviation. It consists of FDRs and IMS. It is well known that FNET can detect the dynamic behavior of system and obtain the real-time frequency information. Therefore, FDRs must adopt a optimal frequency estimation method that is robust to noise and fault. In this paper, we present comparative studies for the frequency estimation method using IRDWT(improved recursive discrete wavelet transform), for the frequency estimation method using FRDWT(fast recursive discrete wavelet transform). we used the Republic of Korea 345kV power system modeling data by EMTP-RV. The user-defined arbitrary waveforms were used in order to evaluate the performance of the proposed two kinds of RDWT. Also, the frequency variation data in various range, both large range and small range, were used for simulation. The simulation results showed that the proposed frequency estimation technique using FRDWT can be the optimal frequency measurement method applied to FDRs.

A Study on Swarm Robot-Based Invader-Enclosing Technique on Multiple Distributed Object Environments

  • Ko, Kwang-Eun;Park, Seung-Min;Park, Jun-Heong;Sim, Kwee-Bo
    • Journal of Electrical Engineering and Technology
    • /
    • v.6 no.6
    • /
    • pp.806-816
    • /
    • 2011
  • Interest about social security has recently increased in favor of safety for infrastructure. In addition, advances in computer vision and pattern recognition research are leading to video-based surveillance systems with improved scene analysis capabilities. However, such video surveillance systems, which are controlled by human operators, cannot actively cope with dynamic and anomalous events, such as having an invader in the corporate, commercial, or public sectors. For this reason, intelligent surveillance systems are increasingly needed to provide active social security services. In this study, we propose a core technique for intelligent surveillance system that is based on swarm robot technology. We present techniques for invader enclosing using swarm robots based on multiple distributed object environment. The proposed methods are composed of three main stages: location estimation of the object, specified object tracking, and decision of the cooperative behavior of the swarm robots. By using particle filter, object tracking and location estimation procedures are performed and a specified enclosing point for the swarm robots is located on the interactive positions in their coordinate system. Furthermore, the cooperative behaviors of the swarm robots are determined via the result of path navigation based on the combination of potential field and wall-following methods. The results of each stage are combined into the swarm robot-based invader-enclosing technique on multiple distributed object environments. Finally, several simulation results are provided to further discuss and verify the accuracy and effectiveness of the proposed techniques.

The study on the current status of the intelligent agent with "added characteristic" and its development scheme (캐릭터성을 추가한 지능형 에이전트의 국내 사례와 발전방안 연구)

  • Maeng, Jae-Hee;Park, Jin-Wan
    • Proceedings of the Korea Contents Association Conference
    • /
    • 2006.05a
    • /
    • pp.64-67
    • /
    • 2006
  • Computer performance and the development of computer appliances of today have adopted a new shape of concept, "ubiquitous computing." Thus, users can readily obtain access to abundant information as they can utilize the wireless network taking advantage of the ubiquitous concept, which allows usage inhibited by neither time nor location. In this process, the supply and feedback of information tends to be made real in the form of "interactive agent". This interactive agent with the application of artificial intelligence can enhance the reliability of information using friendly characters, and is used as a tool to grasp the intention! and behavior patterns of the users. This paper will take a look at the concept and the definition of the intelligent agent with "added characteristic", and furthermore investigate the potential and the scope of its development analyzing its features and comparing the examples of the domestic market that pursues to generate profits with it.

  • PDF

Analysis of Influencing Factors of Traveler Detour Making Behavior for Providing Freeway VMS Information (고속도로 VMS 정보 제공 시 우회율 산출에 관한 연구)

  • Choi, Jai-Sung;Sung, Hyun-Jin;Kim, Sang-Youp;Park, Jun;Kang, Weon-Eui
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.9 no.3
    • /
    • pp.41-50
    • /
    • 2010
  • This paper presents an investigation result that is made to determine dominant influencing factors and their specific impacts on motorist detour makings for VMS placements on freeway. This was necessary to provide engineers with a tool for evaluating VMS cost-effectiveness and its feasibility. This research found that additional travel time delay is the most influential variable in determining motorist detour makings. Also, more than 70% freeway motorists recognize the adjacent national roads as their detour routes, and both AADT and the distance to the entering point of the detour path are found to be dominating factors. Motorist detour ratio model by VMS placement on freeway is developed based on the Stated Preference. In model validation, actual detour making behaviors observed by the Revealed Preference values verify the detour ratio on the Stated Preference. These research findings should be useful for cost-effective placements of VMS on freeway, and it is recommended that the results be tested by practicing engineers in the ITS sector.

Development of a Cause Analysis Program to Risky Driving with Vision System (Vision 시스템을 이용한 위험운전 원인 분석 프로그램 개발에 관한 연구)

  • Oh, Ju-Taek;Lee, Sang-Yong
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.8 no.6
    • /
    • pp.149-161
    • /
    • 2009
  • Electronic control systems of vehicle are rapidly developed to keep balance of a driver`s safety and the legal, social needs. The driver assistance systems are putted into practical use according to the cost drop in hardware and highly efficient sensor, etc. This study has developed a lane and vehicle detection program using CCD camera. The Risky Driving Analysis Program based on vision systems is developed by combining a risky driving detection algorithm formed in previous study with lane and vehicle detection program suggested in this study. Risky driving detection programs developed in this study with information coming from the vehicle moving data and lane data are useful in efficiently analyzing the cause and effect of risky driving behavior.

  • PDF

Analysis of Factors Affecting Travel Time Change Using the Time Use Survey Data in Seoul (서울시 통행시간 변화의 요인분석: 생활시간조사자료를 중심으로)

  • Koo, Ja hun;Choo, Sangho
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.17 no.1
    • /
    • pp.1-16
    • /
    • 2018
  • Changes in the life style might vary trip purposes, ultimately leading to the change in the travel behavior. Therefore, this study analyzed the factors affecting travel time change by using the time use survey data in Seoul, surveyed by the Statistics Korea in 1999~2014. We developed multiple linear regression models for travel time, considering individual, household and time-related variables as independent variables. The models were separately estimated weekday and weekend. the model results show that the household, individual, and time related variables have an significant effect on the travel time. In addition, travel time is more influenced by individual characteristics thn household ones. Each activity time positively affects the travel time, indicating that travel is derived demand. The variable that have the greatest influence on the travel time is the activity time for leisure.

Fault Diagnosis and Tolerance for Asynchronous Counters with Critical Races Caused by Total Ionizing Dose in Space (우주 방사능 누적에 의한 크리티컬 레이스가 존재하는 비동기 카운터를 위한 고장 탐지 및 극복)

  • Kwak, Seong-Woo;Yang, Jung-Min
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.22 no.1
    • /
    • pp.49-55
    • /
    • 2012
  • Asynchronous counters, where the counter value is changed not by a synchronizing clock but by outer inputs, are used in various modern digital systems such as spaceborne electronics. In this paper, we propose a scheme of fault tolerance for asynchronous counters with critical races caused by total ionizing dose (TID) in space. As a typical design flaw of asynchronous digital circuits, critical races cause an asynchronous circuit to show non-deterministic behavior, i.e., the next stable state of a state transition is not a fixed value but may be any value of a state set. Using the corrective control scheme for asynchronous sequential machines, this paper provides an existence condition and design procedure for a state feedback controller that can invalidate the effect of critical races. We implement the proposed control system in VHDL code and conduct experiments to demonstrate that the proposed control system can overcome critical races.