• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.11
• /
• pp.1464-1471
• /
• 1999

This paper introduces complex-valued competitive learning neural network for spatio-temporal pattern recognition. There have been quite a few neural networks for spatio-temporal pattern recognition. Among them, recurrent neural network, TDNN, and avalanche model are acknowledged as standard neural network paradigms for spatio-temporal pattern recognition. Recurrent neural network has complicated learning rules and does not guarantee convergence to global minima. TDNN requires too many neurons, and can not be regarded to deal with spatio-temporal pattern basically. Grossberg's avalanche model is not able to distinguish long patterns, and has to be indicated which layer is to be used in learning. In order to remedy drawbacks of the above networks, unsupervised competitive learning using complex umber is proposed. Suggested neural network also features simultaneous recognition, time-shift invariant recognition, stable categorizing, and learning rate modulation. The network is evaluated by computer simulation with randomly generated patterns.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.20 no.42
• /
• pp.171-179
• /
• 1997

Genetic Algorithms face an inherent conflict between exploitation and exploration. Exploitation refers to taking advantage of information already obtained in the search. Exploration show that a pattern in bits coupled with another pattern elsewhere in the string is more effective. In this paper shows that the selection method has a major impact on the balance between exploitation and exploration. A more heavy-handed approach seeks to exploit the available information. If decisions must be made quickly, especially those in real-time trading environments, then quicker convergence through exploitation may be more desirable. Also this paper we present some theoretical and empirical the selection method in genetic algorithms for a GA-hard problem.

• Journal of the Korean Society of Industry Convergence
• /
• v.5 no.3
• /
• pp.187-192
• /
• 2002

In-plane ESPI(Electronic Speckle Patten Interferometry)was devised to measure in~plane defamation and rotation of a specimen with laser in this study. The conventional measuring methods of surface deformations such as the strain gauge have many demerits because they are contact and point-to-point measuring ones. But that ESPI is noncontact, nondestructive and whole field measuring method can overcome previous disadvantages. We used ESPI which is sensitive to in-plane displacement for measuring in-plane deformations of a disk. First of all, the system calibration was done due to an in-plane rotation before getting deformations of a disk. Finally we showed good agreement between theexperiment results and those of the FEA(Finit Element Analysis).

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.2
• /
• pp.111-118
• /
• 2001

In this paper, in order to implement the multi-layered perceptron neural network using pure digital logic circuit model, we propose the new logic neuron structure, the digital canonical multi-layered logic neural network structure, and the multi-stage multi-layered logic neural network structure for pattern recognition applications. And we show that the proposed approach provides an incremental additive learning algorithm, which is very simple and effective.

• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.131-135
• /
• 2021

The interference between closely placed co-coverage satellites was analyzed. In general, a satellite network may use different orthogonal polarizations and frequencies to increase the throughput of a satellite. However, when orthogonal linear polarization (horizontal polarization and vertical polarization) or orthogonal circular polarization (left-handed circular polarization and right-handed circular polarization) is used, the signal from one polarization sense to another may be coupled, resulting in cross-polarization interference. This signal-coupling arises due to the finite value of the cross-polarization discrimination of the earth station. In this study, field equations were used to analyze the interference between adjacent satellites using co-frequency. The level of interference was compared to that when two adjacent satellites used the same polarization. The simulation results show that the interference mainly depends on the off-axis co-polar pattern and the cross-polar pattern of the earth station antenna.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.3
• /
• pp.581-590
• /
• 2024

This study aims to extract key topics through text mining of incident records (incident history, post-incident measures, preventive measures) from construction safety accident case data available on the public data portal. It also seeks to provide fundamental insights contributing to the establishment of manuals for disaster prevention by identifying correlations between these topics. After pre-processing the input data, we used the LDA-based topic modeling technique to derive the main topics. Consequently, we obtained five topics related to incident history, and four topics each related to post-incident measures and preventive measures. Although no dominant patterns emerged from the topic pattern analysis, the study holds significance as it provides quantitative information on the follow-up actions related to the incident history, thereby suggesting practical implications for the establishment of a preventive decision-making system through the linkage between accident history and subsequent measures for reccurrence prevention.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.2_2
• /
• pp.319-324
• /
• 2024

In this paper, the Artificial Intelligence Space(AI-Space) for human-robot interface is presented, which can enable human-computer interfacing, networked camera conferencing, industrial monitoring, service and training applications. We present a method for representing, tracking, and objects(human, robot, chair) following by fusing distributed multiple vision systems in AI-Space. The article presents the integration of color distributions into particle filtering. Particle filters provide a robust tracking framework under ambiguous conditions. We propose to track the moving objects(human, robot, chair) by generating hypotheses not in the image plane but on the top-view reconstruction of the scene.

• Journal of the Korea Convergence Society
• /
• v.8 no.12
• /
• pp.23-29
• /
• 2017

This paper introduces the mold technology for the development of ultra-compact package of less than 1mm, and also analyze the error pattern of the results using this mold technology. The existing ultra-small mold structure was one-piece, which caused the surface of EDM to be rough and increase the error rate. This has been an obstacle to further reducing the size of the mold. On the other hand, the proposed mold technology tries to overcome the limitation of the one-piece type by using the prefabricated type method. This paper also classify defect patterns in the results of the proposed mold structure and analyze the occurrence probability of each pattern to use as a basic data to develop a detector.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.7
• /
• pp.769-776
• /
• 2011

In order to cope with the requirements of smaller patterns, larger surfaces and lower costs in the fields of displays, optics and energy, greater attentions is now being paid to the development of micro-pattern machining technology. Compared with flat molds, roll molds have the advantages of short delivery, ease of manufacturing larger surfaces, and continuous molding. This paper presents the state-of-the-art of the micro pattern machining technology on the roll molds and introduces some research results on the machining process technology. The copper and nickel-phosphorous-alloy plating process, machining process technology for uniform micro patterns. micro cutting simulation and the real time monitoring system for micro machining are summarized. The developed technologies have led the complete localization of the prism sheets and will be applied to the direct forming process with succeeding research & development.

• Journal of the Korean Society of Industry Convergence
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2014

This paper describes a new technology to develop the character recognition technology based on pattern recognition for non-contacting inspection optical lens slant or precision parts, and including external form state of lens or electronic parts for the performance verification, this development can achieve badness finding. And, establish to existing reflex data because inputting surface badness degree of scratch's standard specification condition directly, and error designed to distinguish from product more than schedule error to badness product by normalcy product within schedule extent after calculate the error comparing actuality measurement reflex data and standard reflex data mutually. Developed system to smallest 1 pixel unit though measuring is possible 1 pixel as $37{\mu}m{\times}37{\mu}m$ ($0.1369{\times}10-4mm^2$) the accuracy to $1.5{\times}10-4mm$ minutely measuring is possible performance verification and trust ability through an experiment prove.