• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.2
• /
• pp.92-98
• /
• 2017

Data clustering determines a group of patterns using similarity measure in a dataset and is one of the most important and difficult technique in data mining. Clustering can be formally considered as a particular kind of NP-hard grouping problem. K-means algorithm which is popular and efficient, is sensitive for initialization and has the possibility to be stuck in local optimum because of hill climbing clustering method. This method is also not computationally feasible in practice, especially for large datasets and large number of clusters. Therefore, we need a robust and efficient clustering algorithm to find the global optimum (not local optimum) especially when much data is collected from many IoT (Internet of Things) devices in these days. The objective of this paper is to propose new Hybrid Simulated Annealing (HSA) which is combined simulated annealing with K-means for non-hierarchical clustering of big data. Simulated annealing (SA) is useful for diversified search in large search space and K-means is useful for converged search in predetermined search space. Our proposed method can balance the intensification and diversification to find the global optimal solution in big data clustering. The performance of HSA is validated using Iris, Wine, Glass, and Vowel UCI machine learning repository datasets comparing to previous studies by experiment and analysis. Our proposed KSAK (K-means+SA+K-means) and SAK (SA+K-means) are better than KSA(K-means+SA), SA, and K-means in our simulations. Our method has significantly improved accuracy and efficiency to find the global optimal data clustering solution for complex, real time, and costly data mining process.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.10
• /
• pp.465-472
• /
• 2017

In the past, researchers mainly used the supervised learning technique of machine learning to analyze power data and investigated the identification of patterns through the data mining technique. Data analysis research, however, faces its limitations with the old data classification and analysis techniques today when the size of electric power data has increased with the possible real-time provision of data. This study thus set out to propose a clustering architecture to analyze large-sized electric power data. The clustering process proposed in the study supplements the K-means algorithm, an unsupervised learning technique, for its problems and is capable of automating the entire process from the collection of electric power data to their analysis. In the present study, power data were categorized and analyzed in total three levels, which include the row data level, clustering level, and user interface level. In addition, the investigator identified K, the ideal number of clusters, based on principal component analysis and normal distribution and proposed an altered K-means algorithm to reduce data that would be categorized as ideal points in order to increase the efficiency of clustering.

• Journal of the Korean Society for Library and Information Science
• /
• v.15
• /
• pp.197-224
• /
• 1988

The kernel technique in game theory is introduced and modified in the notion of super kernel, which creates searching maps through the hierarchic clustering technique. The results show more Improved retrieval efficiency in terms of precision and recall.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.665-672
• /
• 2003

This paper describes a speech synthesis technique by concatenating unit phoneme. At that time, a major problem is that discontinuity is happened from connection part between unit phonemes, especially from connection part between unit phonemes recorded by different persons. To solve the problem, this paper uses clustered diphone, and proposes a spectral smoothing technique, not only using formant trajectory and distribution characteristic of spectrum but also reflecting human's acoustic characteristic. That is, the proposed technique performs unit phoneme clustering using distribution characteristic of spectrum at connection part between unit phonemes and decides a quantity and a scope for the smoothing by considering human's acoustic characteristic at the connection part of unit phonemes, and then performs the spectral smoothing using weights calculated along a time axes at the border of two diphones. The proposed technique removes the discontinuity and minimizes the distortion which can be occurred by spectrum smoothing. For the purpose of the performance evaluation, we test on five hundred diphones which are extracted from twenty sentences recorded by five persons, and show the experimental results.

• The KIPS Transactions:PartD
• /
• v.13D no.7 s.110
• /
• pp.1027-1038
• /
• 2006

There are many technical problems in the recommendation system based on very large database(VLDB). So, it is necessary to study the recommendation system' structure and the data-mining technique suitable for the large scale Internet shopping mail. Thus we design and implement the product recommendation system using k-means clustering algorithm and sequential pattern technique which can be used in large scale Internet shopping mall. This paper processes user information by batch processing, defines the various categories by hierarchical structure, and uses a sequential pattern mining technique for the search engine. For predictive modeling and experiment, we use the real data(user's interest and preference of given category) extracted from log file of the major Internet shopping mall in Korea during 30 days. And we define PRP(Predictive Recommend Precision), PRR(Predictive Recommend Recall), and PF1(Predictive Factor One-measure) for evaluation. In the result of experiments, the best recommendation time and the best learning time of our system are much as O(N) and the values of measures are very excellent.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.744-748
• /
• 2008

In this paper, we propose a novel technique that generate a new song with given example songs. Our system use k-th order Markov chain of which each state represents notes in a measure. Because we have to consider very high-dimensional space if we use notes in a measure as a state of Markov chain directly, we exploit a hierarchical clustering technique for given example songs to use each cluster as a state. Each given examples can be represented as sequences of cluster ID, and we use them for training data of the Markov chain. The resulting Markov chain effectively gives new song similar to given examples.

• Journal of Korean Library and Information Science Society
• /
• v.30 no.3
• /
• pp.427-456
• /
• 1999

This paper deals with the problems of information retrieval through full-test database which arise from both the deficiency of searching strategies or methods by information searcher and the difficulties of query representation, generation, extension, etc. In oder to solve these problems, we should use automatic retrieval instead of manual retrieval in the past. One of the ways to make the gap narrow between the terms by the writers and query by the searchers is that the query should be searched with the terms which the writers use. Thus, the preconditions which should be taken one accorded way to solve the problems are that all areas of information retrieval such as should taken one accorded way to solve the problems are that all areas of information retrieval such as contents analysis, information structure, query formation, query evaluation, etc. should be solved as a coherence way. We need to deal all the ares of automatic information retrieval for the efficiency of retrieval thought this paper is trying to solve the design of thesaurus browser. Thus, this paper shows the theoretical analyses about the form of information retrieval, automatic indexing, clustering technique, establishing and expressing thesaurus, and information retrieval technique. As the result of analyzing them, this paper shows us theoretical model, that is to say, the thesaurus browser by clustering algorithm. The result in the paper will be a theoretical basis on new retrieval algorithm.

• Korean Journal of Remote Sensing
• /
• v.1 no.1
• /
• pp.5-27
• /
• 1985

A hill-sliding technique was devised to extract Gaussian clusters from the multivariate probability density estimates of sample data for the first step of iterative unsupervised classification. The underlying assumption in this approach was that each cluster possessed a unimodal normal distribution. The key idea was that a clustering function proposed could distinguish elements of a cluster under formation from the rest in the feature space. Initial clusters were extracted one by one according to the hill-sliding tactics. A dimensionless cluster compactness parameter was proposed as a universal measure of cluster goodness and used satisfactorily in test runs with Landsat multispectral scanner (MSS) data. The normalized divergence, defined by the cluster divergence divided by the entropy of the entire sample data, was utilized as a general separability measure between clusters. An overall clustering objective function was set forth in terms of cluster covariance matrices, from which the cluster compactness measure could be deduced. Minimal improvement of initial data partitioning was evaluated by this objective function in eliminating scattered sparse data points. The hill-sliding clustering technique developed herein has the potential applicability to decomposition of any multivariate mixture distribution into a number of unimodal distributions when an appropriate diatribution function to the data set is employed.

• Smart Structures and Systems
• /
• v.5 no.1
• /
• pp.43-54
• /
• 2009

This study introduces a novel approach for locating damage in a structure using wireless sensor system with local level computational capability to alleviate data traffic load on the centralized computation. Smart wireless sensor systems, capable of iterative damage-searching, mimic an optimization process in a decentralized way. The proposed algorithm tries to detect damage in a structure by monitoring abnormal increases in strain measurements from a group of wireless sensors. Initially, this clustering technique provides a reasonably effective sensor placement within a structure. Sensor clustering also assigns a certain number of master sensors in each cluster so that they can constantly monitor the structural health of a structure. By adopting a voting system, a group of wireless sensors iteratively forages for a damage location as they can be activated as needed. Since all of the damage searching process occurs within a small group of wireless sensors, no global control or data traffic to a central system is required. Numerical simulation demonstrates that the newly developed searching algorithm implemented on wireless sensors successfully localizes stiffness damage in a plate through the local level reconfigurable function of smart sensors.

• Journal of Korea Spatial Information System Society
• /
• v.9 no.1
• /
• pp.105-115
• /
• 2007

Data mining extracts interesting knowledge from a large database. Among numerous data mining techniques, research work is primarily concentrated on clustering and association rules. The clustering technique of the active research topics mainly deals with analyzing spatial and attribute data. And, the technique of association rules deals with identifying frequent patterns. There was an advanced apriori algorithm using an existing bit-clustering algorithm. In an effort to identify an alternative algorithm to improve apriori, we investigated FP-Growth and discussed the possibility of adopting bit-clustering as the alternative method to solve the problems with FP-Growth. FP-Growth using bit-clustering demonstrated better performance than the existing method. We used chess data in our experiments. Chess data were used in the pattern mining evaluation. We made a creation of FP-Tree with different minimum support values. In the case of high minimum support values, similar results that the existing techniques demonstrated were obtained. In other cases, however, the performance of the technique proposed in this paper showed better results in comparison with the existing technique. As a result, the technique proposed in this paper was considered to lead to higher performance. In addition, the method to apply bit-clustering to GML data was proposed.