• Journal of Communications and Networks
• /
• v.8 no.3
• /
• pp.330-338
• /
• 2006

Many web cache systems and policies concerning them have been proposed. These studies, however, consider large objects less useful than small objects in terms of performance, and evict them as soon as possible. Even if this approach increases the hit rate, the byte hit rate decreases and the connections occurring over congested links to outside networks waste more bandwidth in obtaining large objects. This paper puts forth a client-cluster approach for improving the web cache system. The client-cluster is composed of the residual resources of clients and utilizes them as exclusive storage for large objects. This proposed system achieves not only a high hit rate but also a high byte hit rate, while reducing outgoing traffic. The distributed hash table (DHT) based peer-to-peer lookup protocol is utilized to manage the client-cluster. With the natural characteristics of this protocol, the proposed system with the client-cluster is self-organizing, fault-tolerant, well-balanced, and scalable. Additionally, the large objects are managed with an index based allocation method, which balances the loads of all clients well. The performance of the cache system is examined via a trace driven simulation and an effective enhancement of the proxy cache performance is demonstrated.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.4
• /
• pp.768-774
• /
• 2007

This paper proposes how to reduce the amount of data transmitted in each sensor and cluster head in order to lengthen the lifetime of sensor network. This study proposes hierarchical filtering for reducing the sensor's energy dissipation. Hierarchical filtering is to divide sensor network by two tiers when filtering it. First tier performs filtering when transmitting the data from cluster member to cluster head, and second tier performs filtering when transmitting the data from cluster head to base station. This should increase the efficiency of filtering and decrease the inaccuracy of the data compared to the methods which enlarge the filter width to do more filtering.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.447-449
• /
• 2021

Various wireless sensor network protocols have been proposed to maintain the network for a long time by minimizing energy consumption. Using the K-means clustering algorithm takes longer to cluster than traditional hierarchical algorithms because the center point must be moved repeatedly until the final cluster is established. For K-means clustering-based protocols, only the residual energy of nodes or nodes near the center point of the cluster is considered when the cluster head is elected. In this paper, we propose a new wireless sensor network protocol based on K-means clustering to improve the energy efficiency while improving the aforementioned problems.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1507-1510
• /
• 2003

We propose UPGMA(Unweighted Pair Group Method using Average distance) as hierarchical clustering to detect abrupt shot changes using multiple features such as pixel-by-pixel difference, global and local histogram difference. Conventional $\kappa$-means algorithm which is a method of the partitional clustering, has to select an efficient initial cluster center adaptively UPGMA that we propose, does not need initial cluster center because of agglomerative algorithm that it starts from each sample for clusters. And UPGMA results in stable performance. Experiment results show that the proposed algorithm works not only well but also stably.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.601-605
• /
• 1991

In this paper an approximate solution method for the large-scale Traveling Salesman Problem(TSP) is presented. The method start with the subdivision of the problem domain into a number of clusters by considering their geometries. The clusters have limited number of nodes so as to get local solutions. They are linked to give the least path which covers the whole domain and become TSPs with start- and end-node. The approximate local solutions in each cluster are obtained by using geometrical property of the cluster, and combined to give an overall-approximate solution for the large-scale TSP.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.159-166
• /
• 2003

To reduce the high dimensionality required for training of feature vectors in speaker identification, we propose an efficient GMM based on local PCA with Fuzzy clustering. The proposed method firstly partitions the data space into several disjoint clusters by fuzzy clustering, and then performs PCA using the fuzzy covariance matrix in each cluster. Finally, the GMM for speaker is obtained from the transformed feature vectors with reduced dimension in each cluster. Compared to the conventional GMM with diagonal covariance matrix, the proposed method needs less storage and shows faster result, under the same performance.

• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.517-524
• /
• 2006

In cluster computers, it is essential to Implement the single I/O space(SIOS) supporting integrated I/O substructure to efficiently process I/O intensive applications. SIOS service provides with global I/O address space to directly access peripherals and hard disks in its own or remote nodes from any node in the cluster computer In this thesis, we propose the implementation method of SIOS in Linux clusters by using only freewares. This method is implemented at device driver level that uses Enhanced Network Block Device(ENBD) and file system level that uses S/W RAID and NFS. The major strengths of this method are easiness of implementation and almost no cost due to using freewares. In addition, since freewares used are open sources, it is possible to apply this method to other platforms with only slight modification. Moreover, experiments show that I/O throughputs are up to 5.5 times higher in write operations and approximately 2.3 times higher in read operations than those of CDD method that uses the device driver developed at kernel level.

• Journal of the Korea Convergence Society
• /
• v.12 no.7
• /
• pp.169-179
• /
• 2021

This study shows that the two-stage k-means clustering method can improve prediction performance by predicting the stock price, To this end, this study introduces the two-stage k-means clustering algorithm and tests the prediction performance through comparison with various machine learning techniques. It selects the cluster close to the prediction target obtained from the k-means clustering, and reapplies the k-means clustering method to the cluster to search for a cluster closer to the actual value. As a result, the predicted value of this method is shown to be closer to the actual stock price than the predicted values of other machine learning techniques. Furthermore, it shows a relatively stable predicted value despite the use of a relatively small cluster. Accordingly, this method can simultaneously improve the accuracy and stability of prediction, and it can be considered as the new clustering method useful for small data. In the future, developing the two-stage k-means clustering is required for the large-scale data application.

• The KIPS Transactions:PartD
• /
• v.10D no.4
• /
• pp.591-602
• /
• 2003

Delay and discontinuance phenomenon of service are cause by sudden increase of the network communication amount and the quantity consumed of resources when Internet users are driven excessively to a conventional single large database sewer. To solve these problems, spatial database cluster consisted of several single nodes on high-speed network to offer high-performance is risen. But, research about spatial join operation that can reduce the performance of whole system in case process at single node is not achieved. So, in this paper, we propose efficient parallel spatial join processing method in a spatial database cluster system that uses data partitions and replications method that considers the characteristics of space data. Since proposed method does not need the creation step and the assignment step of tasks, and does not occur additional message transmission between cluster nodes that appear in existent parallel spatial join method, it shows performance improvement of 23% than the conventional parallel R-tree spatial join for a shared-nothing architecture about expensive spatial join queries. Also, It can minimize the response time to user because it removes redundant refinement operation at each cluster node.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.8
• /
• pp.1191-1199
• /
• 2003

This paper describes to observe the combustion process of only one droplet cluster. In this study, liquid fuel was atomized by ultrasonic wave to form an acoustically levitated droplet cluster. In order to elucidate the detailed structure of burning process of the droplet cluster, laser tomography method was applied. Time-series planar images of fuel droplets were processed and diameter of the each droplet was calculated based on the Mie-scattering theory. Using these data, the modified droplet group combustion number was estimated in time-series. As the result, when the internal droplet group combustion occur, the modified group combustion number dose not decrease monotonically, but show a tow-staged decreasing process. In all case of combustion process, combustion reactions were measured two types that combustion speed was fast and slow. It was casued by difference of concentration degree and droplet size distribution.