• International journal of advanced smart convergence
• /
• v.1 no.1
• /
• pp.43-47
• /
• 2012

Parkinson's disease is representative degenerative diseases of the nervous system, which is from deficiency of dopamine neurons to pass in which the gradual degeneration of the body. In this paper, open UCI repository data of Parkinson's patients is used for experiments. The classification based on correlation analysis is examined. In addition, the relationship between groups is differentiated by cluster analysis based on patients with Parkinson's disease by apriori algorithm and correlation analysis. It is used to find the properties that distinguish cluster analysis. Though the disease is the same in the basic structure, each group is compared as each gender group with the most distinctive part of the characteristics.

• International journal of advanced smart convergence
• /
• v.7 no.2
• /
• pp.33-37
• /
• 2018

In this study, we propose an iterative clustering algorithm that automatically clusters a set of voice signal data without a label into an optimal number of clusters and generates hmm model for each cluster. In the clustering process, the likelihood calculations of the clusters are performed using iterative hmm learning and testing while varying the number of clusters for given data, and the maximum likelihood estimation method is used to determine the optimal number of clusters. We tested the effectiveness of this clustering algorithm on a small-vocabulary digit clustering task by mapping the unsupervised decoded output of the optimal cluster to the ground-truth transcription, we found out that they were highly correlated.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1893-1894
• /
• 2008

Advances in hardware and wireless network technologies have placed us at the doorstep of a new era where small wireless devices will provide access to information anytime, anywhere as well as actively participate in creating smart environments. In this paper, we propose location-aware clustering method in wireless sensor networks. Previous clustering algorithm assumes that all nodes know its own location by GPS. But, it is unrealistic because of GPS module cost and large energy consumption. So, we operate localization ahead of cluster set-up phase. And Considering node density and geographic information, Cluster Heads are elected uniformly. Moreover, communication between CHs is prolonged network lifetime.

• Journal of Applied Reliability
• /
• v.5 no.4
• /
• pp.465-486
• /
• 2005

A unreliable network system results in unsatisfied performance. A performance criterion of a network is throughput and availability. One of the most compelling technological advances of this decade has been the advent of deploying wireless networks of heterogeneous smart sensor nodes for complex information gathering tasks, The advancement and popularization of wireless communication technologies make more efficiency to network devices with wireless technology than with wired technology. Recently, the research of wireless sensor network has been drawing much attentions. In this paper, We evaluate throughput and availability of wireless sensor network, which have hierarchical structure based on clustering and estimate the maximum hroughput, average throughput and availability of the network considering several link failure patterns likely to happen at a cluster consisted of sensor nodes. Also increasing a number of sensor nodes in a cluster, We analysis the average throughput and availability of the network.

• Communications for Statistical Applications and Methods
• /
• v.27 no.6
• /
• pp.589-602
• /
• 2020

The development of smart grids has enabled the easy collection of a large amount of power data. There are some common patterns that make it useful to cluster power consumption patterns when analyzing s power big data. In this paper, clustering analysis is based on distance functions for time series and clustering algorithms to discover patterns for power consumption data. In clustering, we use 10 distance measures to find the clusters that consider the characteristics of time series data. A simulation study is done to compare the distance measures for clustering. Cluster validity measures are also calculated and compared such as error rate, similarity index, Dunn index and silhouette values. Real power consumption data are used for clustering, with five distance measures whose performances are better than others in the simulation.

• Journal of Digital Convergence
• /
• v.10 no.2
• /
• pp.55-61
• /
• 2012

This space is for the abstract of your study in English. Recently, we began to face a significant change in our daily lives due to the expansion of the use of smartphones. In this regard, this study aims at examining the mechanism of Smart Work, necessary for the creation of job, led by the use of smart devices, and ways of its development. Accordingly, this study defined concepts of Smart Work clearly and analyzed the convergence of information through IT, the exploitation of new markets, derived from information industry, along with foreign cases of job creation through ICT. Furthermore, change in people's cultural recognition is required for the place of smart Work. For example, cluster development based on the public-private cooperation will promote the creation of job. In addition, the cooperation of the academic world and the service industry will play a leading role in developing local economy. To attain this end, the policy support of government for Smart Work and the public-private cooperation are needed.

• Journal of Convergence for Information Technology
• /
• v.11 no.9
• /
• pp.138-144
• /
• 2021

In the electronic component assembly business, when product defects occur, it is important to track incoming raw material defects or work defects, and it is important to improve suppliers or work sites according to the results. The core task of the smart factory is to build an integrated data hub to process storage, management, and analysis in real time, and to manage cluster processes, energy, environment, and safety. In order to improve reliability through accurate analysis and collection of production data by real-time monitoring of production site management for electronic parts-related small and medium-sized enterprises (SMEs), the establishment of a smart factory is essential. This paper was developed to be utilized in the construction by defining the system configuration method, smart factory-related technology and application cases, considering the characteristics of SMEs related to electronic components that want to introduce a smart factory.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.149-162
• /
• 2021

This paper established a new smart factory based on manufacturing data for an introductory company focusing on the personalized cosmetics manufacturing industry. We build on an example of a system that collects, manages, and analyzes documents and data that were previously managed by CGMP-based analog for data-driven use. To this end, we have established a system that can collect all data in real time at the production site by introducing artificial intelligence smart factory platform LINK5 MOS and POP system, collecting PLC data, and introducing monitoring system and pin board. It also aims to create a new business cluster space based on this project.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.4
• /
• pp.119-135
• /
• 2022

Digital platforms play crucial roles in terms of enabling and sustaining online communities. However, who really benefits from digital platform development, and what are the benefits digital platforms provide for the development of smart communities. This paper explores this question, the goal was to understand the links between digital platforms and smart communities, using the clustering methodology process to have a better understanding of characteristic of each digital platform, Twenty nine digital platforms is clustered and used as a study case. This paper explores how the categorization of digital platform characteristics encourages participation by a smart community, thus improving information and service delivery. On another side, the rise of digital platforms brings new challenges for policy maker to foster a smart community and firms the digital platform also offer benefits to giving effective and efficient service.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1699-1706
• /
• 2011

This study analyzed the level of service on passenger transfer between metro and bus based on transit smart card data obtained in 2010. In order to evaluate the level of service on transfer, we defined the service level specially on transfer time at metro stations. The data of passenger transfer time were used in cluster analysis to classify the service level from A to F. The results show that the average transfer time from metro to bus was 6.45 minutes. The number of stations with level of service A(approximately less than 7 minutes) and B(less than 16minutes) were found to be 215 and 227stations respectively. Also, the number of stations with the level of service C and D (greater than 20 minutes for transfer) were found to be 6 stations where any type of improvement on transfer facilities is required.