KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Subject: search.filters.subject.K-means algorithm

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Track Misregistration Estimation Technique Based on Hybrid K-Means and EM Algorithm in Bit-Patterned Media Recording Systems
    (2025-01-01)
    Kochcha, Pijit
    ;
    Kankhunthod, Kittipon
    ;
    Warisarn, Chanon
    Track misregistration (TMR) in ultrahigh density bit-patterned media recording (BPMR) is a significant issue, severely degrading system performance. Although TMR can be managed by a servo control loop, this article proposes a hybrid TMR mitigation method based on K-means and expectation-maximization (EM) algorithms to enhance TMR prediction accuracy and improve bit-error-rate (BER) in multihead/multitrack BPMR systems. This method utilizes 2-D equalizer and 1-D generalized partial response (GPR) target coefficients for the soft-output Viterbi algorithm (SOVA) detector according to the estimated TMR level to mitigate this effect. Simulation results demonstrate that the proposed system significantly outperforms conventional systems, especially under high TMR conditions. The hybrid approach achieves high TMR estimation accuracy and delivers BER performance close to an ideal system with perfect TMR estimation, showing up to a 1.25 dB improvement in BER over systems without TMR mitigation. These findings underscore the effectiveness of the hybrid K-means-EM-based TMR estimator in enhancing system performance under various conditions.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An improvement of extreme learning machine using subclass clustering
    (2018-07-02)
    Watchareeruetai, Ukrit
    ;
    Jiramaneepinit, Boonnithi
    Extreme learning machine (ELM) is an extremely fast learning algorithm proposed for a single-hidden-layer feed-forward neural network (SLFN). ELM projects a set of training instances into a random feature space, and then analytically calculates the weight matrix connecting between the hidden layer and the output layer, leading to a very fast learning speed. This paper proposes an improved version of ELM, named clustering-ELM, that assigns a subclass to each training instances and learns for a weight matrix that projects random features into subclass. In the prediction step, the responses from output nodes of the same class are integrated into one using maximum function. Experimental results conducted on various benchmark datasets reveal a promising performance of the proposed clustering-ELM, compared to the standard ELM.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Enhancing K-means algorithm for solving classification problems
    (2013-11-25)
    Thammano, Arit
    ;
    Kesisung, Pannee
    K-means is the most popular clustering algorithm because of its efficiency and superior performance. However, the performance of K-means algorithm depends heavily on the selection of initial centroids. This paper proposes an extension to the original K-means algorithm enabling it to solve classification problems. First, the entropy concept is employed to adapt the traditional K-means algorithm to be used as a classification technique. Then, to improve the performance of K-means algorithm, a new scheme to select the initial cluster centers is proposed. The proposed models are tested on seven benchmark data sets from the UCI machine learning repository. Experimental results have shown that the proposed models outperform the learning vector quantization network in most of the tested data sets. © 2013 IEEE.