Skip to main content

13 Result(s)

within Tae Hyung Kim Remove this filter Computer Science Remove this filter

and

  1. No Access

    Chapter and Conference Paper

    Enhancing Robustness of Prototype with Attentive Information Guided Alignment in Few-Shot Classification

    In this paper, we carefully revisit the issues of conventional few-shot learning: i) gaps in highlighted features between objects in support and query samples, and ii) losing the explicit local properties due ...

    Tae-Hyung Kim, Woo-Jeoung Nam… in Advances in Knowledge Discovery and Data M… (2023)

  2. Article

    Open Access

    Min-max exclusive virtual machine placement in cloud computing for scientific data environment

    In cloud computing, there is a trade-off between SLAV (Service Level Agreement Violation) and system operating cost. Violation rates can be decreased when using more hosts, which increases system operating cos...

    Moon-Hyun Kim, Jun-Yeong Lee, Syed Asif Raza Shah… in Journal of Cloud Computing (2021)

    Download PDF (3152 KB) View Article

  3. No Access

    Article

    Multiscale Bayesian texture segmentation using neural networks and Markov random fields

    This paper presents a wavelet-based texture segmentation method using multilayer perceptron (MLP) networks and Markov random fields (MRF) in a multi-scale Bayesian framework. Inputs and outputs of MLP networks...

    Tae Hyung Kim, Il Kyu Eom, Yoo Shin Kim in Neural Computing and Applications (2009)

  4. Chapter and Conference Paper

    Human-Aided Cleaning Algorithm for Low-Cost Robot Architecture

    This paper presents a human-aided cleaning algorithm that can be implemented on low-cost robot architecture while the cleaning performance far exceeds the conventional random style cleaning. We clarify the adv...

    Seungyong Kim, Kiduck Kim, Tae-Hyung Kim in Human-Computer Interaction. HCI Intelligen… (2007)

    Download PDF (270 KB)

  5. No Access

    Chapter and Conference Paper

    Neural Network Based Texture Segmentation Using a Markov Random Field Model

    This paper presents a novel texture segmentation method using neural networks and a Markov random field (MRF) model. Multi-scale wavelet coefficients are used as input for the neural networks. The output of th...

    Tae Hyung Kim, Hyun Min Kang, Il Kyu Eom… in Advances in Neural Networks - ISNN 2006 (2006)

  6. No Access

    Chapter and Conference Paper

    Enabling Agent Oriented Programming Using CORBA-Based Object Interconnection Technology for Ubiquitous Computing

    This paper presents a real-time agent service layer (RT-ASL) that is built on CORBA, in order to use a high-level abstraction of software agents for ubiquitous computing. There are four important characteristi...

    Hyongeun Choi, Tae-Hyung Kim in AI 2006: Advances in Artificial Intelligence (2006)

  7. No Access

    Chapter and Conference Paper

    Texture Segmentation Using SOM and Multi-scale Bayesian Estimation

    This paper presents a likelihood estimation method from SOM (self organizing feature map), and texture segmentation is performed by using Bayesian estimation and SOM. Multi-scale wavelet coefficients are used ...

    Tae Hyung Kim, Il Kyu Eom, Yoo Shin Kim in Advances in Neural Networks - ISNN 2006 (2006)

  8. No Access

    Chapter and Conference Paper

    Return Address Randomization Scheme for Annuling Data-Injection Buffer Overflow Attacks

    Buffer overflow(BOF) has been the most common form of vulnerability in software systems today, and many methods exist to defend software systems against BOF attacks. Among them, the instruction set randomizati...

    Deok ** Kim, Tae Hyung Kim, Jong Kim, Sung Je Hong in Information Security and Cryptology (2006)

  9. No Access

    Chapter and Conference Paper

    Load and Performance Balancing Scheme for Heterogeneous Parallel Processing

    Dynamic loop scheduling methods are suitable for balancing parallel loops on shared-memory multiprocessor machines. However, their centralized nature causes a bottleneck for relatively small number of processo...

    Tae-Hyung Kim in Computational and Information Science (2005)

  10. No Access

    Chapter and Conference Paper

    An Interface Agent for Wrapper-Based Information Extraction

    This paper proposes a new method of building information extraction rules for Web documents by exploiting a user interface agent that combines the manual and automatic approaches of rule generation. We adopt t...

    Jaeyoung Yang, Tae-Hyung Kim, Joongmin Choi in Intelligent Agents and Multi-Agent Systems (2005)

  11. No Access

    Chapter and Conference Paper

    Texture Segmentation Using Neural Networks and Multi-scale Wavelet Features

    This paper presents a novel texture segmentation method using Bayesian estimation and neural networks. Multi-scale wavelet coefficients and the context information extracted from neighboring wavelet coefficien...

    Tae Hyung Kim, Il Kyu Eom, Yoo Shin Kim in Advances in Natural Computation (2005)

  12. No Access

    Chapter and Conference Paper

    State Machine Based Operating System Architecture for Wireless Sensor Networks

    A wireless sensor network is characterized as a massively distributed and deeply embedded system. Such a system requires concurrent and asynchronous event handling as a distributed system and resource-consciou...

    Tae-Hyung Kim, Seongsoo Hong in Parallel and Distributed Computing: Applic… (2005)

  13. No Access

    Chapter and Conference Paper

    A Fault Tolerance Extension to the Embedded CORBA for the CAN Bus Systems

    This paper presents a fault tolerant extension to our CAN-CORBA design. The CAN-CORBA is an environment specific CORBA we designed for distributed embedded control systems built on the CAN bus. We extend it fo...

    Gwangil Jeon, Tae-Hyung Kim, Seongsoo Hong… in Languages, Compilers, and Tools for Embedd… (2001)