The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Enhancement of the k-Means Clustering Speed by Emulation of Birds' Motion in Flock

새떼 이동의 모방에 의한 k-평균 군집 속도의 향상

  • Received : 2014.07.08
  • Accepted : 2014.09.19
  • Published : 2014.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In an effort to improve the convergence speed in k-means clustering, we introduce the notion of the birds' movement in a flock. Their motion is characterized by the observation that each bird runs after his nearest neighbor. We utilize this feature in clustering procedure. Once the class of a vector is determined, then a number of vectors in the vicinity of it are assigned to the same class. Experiments have shown that the required number of iterations for termination is significantly lower in the proposed method than in the conventional one. Furthermore, the time of calculation per iteration is more than 5% shorter in the proposed case. The quality of the clustering, as determined from the total accumulated distance between the vector and its centroid vector, was found to be practically the same. It might be phrased that we may acquire practically the same clustering result with shorter computational time.

K-평균 군집에서 수렴 속도를 향상시키기 위한 노력으로서, 우리는 새떼 이동의 개념을 도입한다. 그들 운동의 특징은 각 새가 그의 가장 가까운 이웃을 쫓아간다는 것이다. 우리는 군집 과정에 이 특징을 활용한다. 일단 한 벡터의 클래스가 결정되면, 그 근처의 몇 벡터들에게 동일한 클래스가 부여된다. 실험 결과 군집 종결에 필요한 계산 반복 횟수가 종전 방법에 비해 유의미하게 작은 것으로 나타났다. 게다가 단일 반복 계산에 소요되는 시간이 5% 이상 짧았다. 벡터와 센트로이드 사이의 거리를 누적한 값으로 군집의 품질을 평가한 바, 본 논문에서 제안한 방법과 종전 방법과의 차이는 거의 없었다. 결론적으로, 본 논문에서 제안한 방법에 의해, 보다 짧은 계산 시간으로 질적 하락 없는 군집을 수행할 수 있었다.

Keywords

References

  1. N. Krishnan and S. N. N. Sujatha, "Segmentation of cervical cancer images using active contour models," IEEE Int. Conf. on Computational Intelligence and Computing Research, Tamilnadu, India, Dec. 2010, pp. 1-8.
  2. T. Zhicun and L. Ruihua, "Application of Improved Genetic K-Means Clustering Algorithm in Image Segmentation," First Int. Workshop on Education Technology and Computer Science, vol. 2, Hubei, China, Mar. 2009, pp. 625-628.
  3. W. Zhang and H.-J. Suh, "Analysis and Simulation of Signal Acquisition of GPS Software Receiver," J. of the Korea Institute of Electronic Communication Sciences, vol. 6, no. 1, 2011, pp. 27-33.
  4. C.-K. Ryu and C.-B. Park, "A Novel Clustering Method with Time Interval for Context Inference based on the Multi-sensor Data Fusion," J. of the Korea Institute of Electronic Communication Sciences, vol. 8, no. 3, 2013, pp. 397-402. https://doi.org/10.13067/JKIECS.2013.8.3.397
  5. J.-H. Cho, "Psychology Analysis using Color Histogram Clustering," J. of the Korea Institute of Electronic Communication Sciences, vol. 8, no. 3, 2013, pp. 415-420. https://doi.org/10.13067/JKIECS.2013.8.3.415
  6. Z. Zhu, Y. Tian, J. Xu, X. Deng, and X. Ren, "An Improved Partitioning-Based Web Documents Clustering Method Combining GA with ISODATA," Fourth Int. Conf. on Fuzzy Systems & Knowledge Discovery, vol. 2, 2007, pp. 208-213.
  7. Y.-G. Liu, K.-F. Chen, and X.-M. Li, "A hybrid genetic based clustering algorithm," Proc. of 2004 Int. Conf. on Machine Learning and Cybernetics, vol. 3, 2004, pp. 1677-1682.
  8. W. Zhang, C. Chang, H. Yang, and H. Jiang, "A Hybrid Approach to Data Clustering Analysis with K-Means and Enhanced Ant-Based Template Mechanism," Int. Conf. on Web Intelligence and Intelligent Agent Technology, vol. 1, Toronto, Canada, 2010, pp. 390-397.
  9. S. Wang and S. Fan, "Hybrid of k-means and Chevyshev neural network," Int. Conf. on Automatic Control and Artificial Intelligence, Changsa, China, Mar. 2012, pp. 1596-1600.
  10. M. Dorigo, "Optimization, Learning and Natural Algorithms," Ph.D thesis, Milano : Italy, 1992.
  11. T. Rui, S. Fong, X. Yang, and S. Deb, "Integrating nature-inspired optimization algorithms to K-means clustering," 7th Int. Conf. on Digital Information Management, Macau, China, Aug. 2012, pp. 116-123.
  12. E. Saka and O. Nasraoui, "Simultaneous Clustering and Visualization of Web Usage Data Using Swarm-Based Intelligence," 20th IEEE Int. Conf. on Tools with Artificial Intelligence, vol. 1, Dayton, OH, Nov. 2008, pp. 539-546.
  13. V. Krishnaveni and G. Arumugam, "A novel enhanced bio-inspired harmony search algorithm for clustering," Int. Conf. on Recent Advances in Computing and Software Systems, Chennai, India, Apr. 2012, pp. 7-12.
  14. Y. Zhao, G. Tang, D. Wei, X. Zhou, and G. Zhang, "A Clustering Algorithm Based on Probabilistic Crowding and K-means," The 6th World Congress on Intelligent Control and Automation, vol. 2, Dalian, China, June 2006, pp. 5892-5895.
  15. R. Salman and V. Kecman, "The effect of cluster location and dataset size on 2-stage k-means algorithm," 10th Int. Workshop on Electronics, Control, Measurement and Signals, Liberec, Czech Republic, June 2011, pp. 1-5.
  16. B. J. Frey and D. Dueck, "Clustering by passing messages between data points," Science Magazine, vol. 315, 2007, pp. 972-976.
  17. Y. Zhu, J. Yu, and C. Jia, "Initializing K-means Clustering Using Affinity Propagation," Ninth Int. Conf. on Hybrid Intelligent Systems, vol. 1, Shenyang, China, Aug. 2009, pp. 338-343.
  18. W. C. Reynolds, "Flocks, herds and schools : A distributed behavioral model," ACM SIGGRAPH Computer Graphics, vol. 21, no. 4, 1987, pp. 25-34. https://doi.org/10.1145/37402.37406
  19. C. Delgado-Mata, J. Ibanez, S. Bee, R. Ruiz, and R. Aylett, "On the use of Virtual Animals with Artificial Fear in Virtual Environments," New Generation Computing, vol. 25, no. 2, 2007, pp. 145-169. https://doi.org/10.1007/s00354-007-0009-5
  20. J. Kennedy, Swarm Intelligence. Eberhart : Morgan Kaufmann, 2001.
  21. M. K. Pakhira, "A Modified k-means Algorithm to Avoid Empty Clusters," Int. J. of Recent Trends in Engineering, vol. 1, no. 1, 2009, pp. 220-226.