• Journal of Korea Multimedia Society
• /
• v.17 no.4
• /
• pp.441-457
• /
• 2014

Observed from the recent performance evaluation of clustering schemes in wireless sensor networks, we found that most of them did not consider various sensor characteristics and its application environment. Without considering these, the performance evaluation results are difficult to be trusted because these networks are application-specific. In this paper, for the fair evaluation, we measured several clustering scheme's performance variations in accordance with sensor data pattern, number of sensors per node, density of points of interest (data density) and sensor coverage. According to the experiment result, we can conclude that clustering methods are easily influenced by POI variation. Network lifetime and data accuracy are also slightly influenced by sensor coverage and number of sensors. Therefore, in the case of the clustering scheme that did not consider various conditions, fair evaluation cannot be expected.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2005.04a
• /
• pp.296-299
• /
• 2005

Time series of spring discharge data in Jeju island can provide abundant information on the spatial groundwater system. In this study, the classification based on time series of spring discharge was performed with clustering analysis: discharge rate and EC. Peak discharges are mainly observed in august or september. However, double peaks and late peaks of discharge are also observed at a plenty of springs. Based on results of clustering analysis, it can be deduced that GH model is not appropriate for the conceptual model of Groundwater system in Jeju island. EC distributions in dry season are also support the conclusion.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.9
• /
• pp.859-872
• /
• 2004

With the rapid advance of computer and communication techonology, the recent trend of education environment is edveloping in the ubiquitous learning (u-learning) direction that learners select and organize the contents, time and order of learning by themselves. Since the amount of education information through the internet is increasing rapidly and it is managed in document in an effective way is necessary. The document clustering is integrated documents to subject by classifying a set of documents through their similarity among them. Accordingly, the document clustering can be used in exploring and searching a document and it can increased accuracy of search. This paper proposes an efficient incremental clustering method for a set of documents increase gradually. The incremental document clustering algorithm assigns a set of new documents to the legacy clusters which have been identified in advance. In addition, to improve the correctness of the clustering, removing the stop words can be proposed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.189-196
• /
• 2014

Recently, the need for retrieving documents is growing in SNS environment such as twitter. For supporting the twitter search, a clustering technique classifying the massively retrieved documents in terms of topics is required. However, due to the nature of twitter, there is a limit in applying previous simple techniques to clustering the twitter documents. To overcome such problem, we propose in this paper a new clustering technique suitable to twitter environment. In proposed method, we augment new terms to feature vectors representing the twitter documents, and recalculate the weights of features using Korean Wikipedia. In addition, we performed the experiments with Korean twitter documents, and proved the usability of proposed method through performance comparison with the previous techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1213-1237
• /
• 2019

Vehicular Ad-hoc Network (VANET) facilities envision future Intelligent Transporting Systems (ITSs) by providing inter-vehicle communication for metrics such as road surveillance, traffic information, and road condition. In recent years, vehicle manufacturers, researchers and academicians have devoted significant attention to vehicular communication technology because of its highly dynamic connectivity and self-organized, decentralized networking characteristics. However, due to VANET's high mobility, dynamic network topology and low communication coverage, dissemination of large data packets (e.g. multimedia content) is challenging. Clustering enhances network performance by maintaining communication link stability, sharing network resources and efficiently using bandwidth among nodes. This paper proposes a mobility-based, multi-hop clustering algorithm, (MBCA) for multimedia content broadcasting over an IEEE 802.11p-LTE-enabled hybrid VANET architecture. The OMNeT++ network simulator and a SUMO traffic generator are used to simulate a network scenario. The simulation results indicate that the proposed clustering algorithm over a hybrid VANET architecture improves the overall network stability and performance, resulting in an overall 20% increased cluster head duration, 20% increased cluster member duration, lower cluster overhead, 15% improved data packet delivery ratio and lower network delay from the referenced schemes [46], [47] and [50] during multimedia content dissemination over VANET.

• Journal of Sensor Science and Technology
• /
• v.19 no.5
• /
• pp.342-348
• /
• 2010

The wireless sensor networks have been extensively researched. One of the issues in wireless sensor networks is a developing energy-efficient clustering protocol. Clustering algorithm provides an effective way to extend the lifetime of a wireless sensor networks. In this paper, we proposed an energy efficient clustering scheme by adjusting group size. In sensor network, the power consumption in data transmission between sensor nodes is strongly influenced by the distance of two nodes. And cluster size, that is the number of cluster member nodes, is also effected on energy consumption. Therefore we proposed the clustering scheme for high energy efficiency of entire sensor network by controlling cluster size according to the distance between cluster header and sink.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.75-77
• /
• 2008

Nowadays, as the indices of the major search engines grow to a tremendous proportion, vertical search services can help customers to find what they need. Search Engine is one of the reasons for Internet shopping success in today's world. The import one part of search engine is clustering data. The objective of this paper is to explore a k-means++ algorithm to calculate the clustering data which in the Internet shopping environment. The experiment results shows that the k-means++ algorithm is a faster algorithm to achieved a good clustering.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1986-2009
• /
• 2024

The integration of blockchain technology with the rapid growth of Internet of Things (IoT) devices has enabled secure and decentralised data exchange. However, security vulnerabilities and performance limitations remain significant challenges in IoT blockchain networks. This work proposes a novel approach that combines transaction representation and machine learning techniques to address these challenges. Various clustering techniques, including k-means, DBSCAN, Gaussian Mixture Models (GMM), and Hierarchical clustering, were employed to effectively group unlabelled transaction data based on their intrinsic characteristics. Anomaly transaction prediction models based on classifiers were then developed using the labelled data. Performance metrics such as accuracy, precision, recall, and F1-measure were used to identify the minority class representing specious transactions or security threats. The classifiers were also evaluated on their performance using balanced and unbalanced data. Compared to unbalanced data, balanced data resulted in an overall average improvement of approximately 15.85% in accuracy, 88.76% in precision, 60% in recall, and 74.36% in F1-score. This demonstrates the effectiveness of each classifier as a robust classifier with consistently better predictive performance across various evaluation metrics. Moreover, the k-means and GMM clustering techniques outperformed other techniques in identifying security threats, underscoring the importance of appropriate feature selection and clustering methods. The findings have practical implications for reinforcing security and efficiency in real-world IoT blockchain networks, paving the way for future investigations and advancements.

• Phonetics and Speech Sciences
• /
• v.6 no.1
• /
• pp.77-83
• /
• 2014

This paper proposes a speaker and environment clustering method in order to overcome the degradation of the speech recognition performance caused by various noise and speaker characteristics. In this paper, instead of using the distance between Gaussian mixture model (GMM) weight vectors as in the Google's approach, the distance between the adapted mean vectors based on the modified maximum a posteriori (MAP) adaptation is used as a distance measure for vector quantization (VQ) clustering. According to our experiments on the simulation data generated by adding noise to clean speech, the proposed clustering method yields error rate reduction of 10.6% compared with baseline speaker-independent (SI) model, which is slightly better performance than the Google's approach.

• Journal of Computing Science and Engineering
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2016

The fuzzy c-means (FCM) is a frequently utilized algorithm at present. Yet, the clustering quality and convergence rate of FCM are determined by the initial cluster centers, and so an improved FCM algorithm based on canopy cluster concept to quickly analyze the dataset has been proposed. Taking advantage of the canopy algorithm for its rapid acquisition of cluster centers, this algorithm regards the cluster results of canopy as the input. In this way, the convergence rate of the FCM algorithm is accelerated. Meanwhile, the MapReduce scheme of the proposed FCM algorithm is designed in a cloud environment. Experimental results demonstrate the hybrid canopy-FCM clustering algorithm processed by MapReduce be endowed with better clustering quality and higher operation speed.