• ETRI Journal
• /
• v.38 no.5
• /
• pp.1019-1029
• /
• 2016

The probability hypothesis density (PHD) filter is an effective means to track multiple targets in that it avoids explicit data associations between the measurements and targets. However, the target birth intensity as a prior is assumed to be known before tracking in a traditional target-tracking algorithm; otherwise, the performance of a conventional PHD filter will decline sharply. Aiming at this problem, a novel target birth intensity scheme and an improved measurement-driven scheme are incorporated into the PHD filter. The target birth intensity estimation scheme, composed of both PHD pre-filter technology and a target velocity extent method, is introduced to recursively estimate the target birth intensity by using the latest measurements at each time step. Second, based on the improved measurement-driven scheme, the measurement set at each time step is divided into the survival target measurement set, birth target measurement set, and clutter set, and meanwhile, the survival and birth target measurement sets are used to update the survival and birth targets, respectively. Lastly, a Gaussian mixture implementation of the PHD filter is presented under a linear Gaussian model assumption. The results of numerical experiments demonstrate that the proposed approach can achieve a better performance in tracking systems with an unknown newborn target intensity.

• Journal of KIISE:Software and Applications
• /
• v.37 no.12
• /
• pp.892-908
• /
• 2010

Services in SOA are typically perceived as black-box to service consumers, and can be dynamically evolved at runtime, and run on a number of unknown and heterogeneous environments. Because of these characteristics of the services, effective and efficient monitoring of various aspects on services is an essential functionality for autonomous management of service. But the problem with or limitation in conventional or existing approaches is, that they focus on services themselves, ignoring the effects by business processes. Consequently, there is a room for service monitoring which provides more useful information of business level by acquisition of only external monitoring data that depend on specific BPEL engine and middleware. Moreover, there is a strong demand to present effective methods to reduce monitoring overhead which can degrade quality of services. EDA can cope with such limitations in SOA by collecting and analyzing events efficiently. In this paper, we first describe EDA benefits in service monitoring, and classify monitorring target, and present an appropriate monitoring method for each monitoring target. Also to provide the applicability of our approach, an event meta-model is defined, and event processing model and architecture based on the meta-model are proposed. And, with the proposed architecture and method, we implement a prototype of an event-driven dynamic monitoring framework which can collect and process internal and external data at runtime. Finally, we present the result of a case study to demonstrate the effectiveness and applicability of the proposed approach.

• Asian Journal for Public Opinion Research
• /
• v.5 no.4
• /
• pp.285-301
• /
• 2018

There have been many studies that applied a data-driven analysis method to social media data, and some have even argued that this method can replace traditional polls. However, some other studies show contradictory results. There seems to be no consensus as to the methodology of data collection and analysis. But as social media-based election research continues and the data collection and analysis methodology keep developing, we need to review the key points of the controversy and to identify ways to go forward. Although some previous studies have reviewed the strengths and weaknesses of the social media-based election studies, they focused on predictive performance and did not adequately address other studies that utilized social media to address other issues related with public opinion during elections, such as public agenda or information diffusion. This paper tries to find out what information we can get by utilizing social media data and what limitations social media data has. Also, we review the various attempts to overcome these limitations. Finally, we suggest how we can best utilize social media data in understanding public opinion during elections.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.03a
• /
• pp.324-337
• /
• 2010

For the development of load and resistance factor design, reliability analysis is required to calibrate resistance factors in the framework of reliability theory. The distribution of measured-to-predicted pile resistance ratio was constructed based on only the results of load tests conducted to failure for the assessment of uncertainty regarding pile resistance and used in the conventional reliability analysis. In other words, successful pile load test (piles resisted twice their design loads without failure) results were discarded, and therefore, were not reflected in the reliability analysis. In this paper, a new systematic method based on Bayesian theory is used to update reliability index of driven steel pile piles by adding more pile load test results, even not conducted to failure, into the prior distribution of pile resistance ratio. Fifty seven static pile load tests performed to failure in Korea were compiled for the construction of prior distribution of pile resistance ratio. Reliability analyses were performed using the updated distribution of pile resistance ratio and the total load distribution using First-order Reliability Method (FORM). The challenge of this study is that the distribution updates of pile resistance ratio are possible using the load test results even not conducted to failure, and that Bayesian update are most effective when limited data are available for reliability analysis or resistance factors calibration.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.7
• /
• pp.429-439
• /
• 2006

A desktop grid, which is a computing grid composed of idle computing resources in a large network of desktop computers, is a promising platform for compute-intensive distributed computing applications. However, due to reliability and unpredictability of computing resources, effective scheduling of parallel computing applications on such a platform is a difficult problem. This paper proposes a new scheduling method aimed at reducing the total execution time of a parallel application on a desktop grid. The proposed method is based on utilizing the histories of execution behavior of individual computing nodes in the scheduling algorithm. In order to test out the feasibility of this idea, execution trace data were collected from a set of 40 desktop workstations over a period of seven weeks. Then, based on this data, the execution of several representative parallel applications were simulated using trace-driven simulation. The simulation results showed that the proposed method improves the execution time of the target applications significantly when compared to previous desktop grid scheduling methods. In addition, there were fewer instances of application suspension and failure.

• Management Science and Financial Engineering
• /
• v.20 no.1
• /
• pp.1-9
• /
• 2014

In multi-objective scheduling problems, the objectives are usually in conflict. To obtain a satisfactory compromise and resolve the issue of NP-hardness, most existing works have suggested employing meta-heuristic methods, such as genetic algorithms. In this research, we propose a novel data-driven approach for generating a single solution that compromises multiple rules pursuing different objectives. The proposed method uses a data mining technique, namely, random forests, in order to extract the logics of several historic schedules and aggregate those. Since it involves learning predictive models, future schedules with the same previous objectives can be easily and quickly obtained by applying new production data into the models. The proposed approach is illustrated with a simulation study, where it appears to successfully produce a new solution showing balanced scheduling performances.

• Journal of Power Electronics
• /
• v.9 no.5
• /
• pp.800-808
• /
• 2009

This paper presents a practical method of pressure control for a hydraulic oil-pump system using an SR (Switched Reluctance) drive. For a 6Mpa grade hydraulic oil-pump, a 2.6kW SR drive is developed. In order to get high performance pressure dynamics in actual applications, a data based PID control scheme is proposed. The look-up table from a pre-measured data base produces an approximate current reference based on motor speed and oil-pressure. A PID controller can compensate for the pressure error. With the combination of the two references, the proposed control scheme can achieve fast dynamics and stable operation. Furthermore, a suitable current controller considering the nonlinear characteristics of an SRM (Switched Reluctance Motor) and practical test methods for data measuring are presented. The proposed control scheme is verified by experimental tests.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.6
• /
• pp.345-359
• /
• 2011

In high performance embedded systems, the use of multiple on-chip memories is an essential architectural feature for exploiting inherent parallelism in multimedia applications. This feature allows multiple data accesses to be executed in parallel. However, it remains difficult to effectively exploit of multiple on-chip memories. The successful use of this architecture strongly depends on how to efficiently detect and exploit memory parallelism in target applications. In this paper, we propose a technique based on a linear array access descriptor [1], which is generated from profiled data, to detect and exploit memory parallelism. The proposed technique tackles an array reorganization problem to maximize memory parallelism in multimedia applications. We present preliminary experiments applying the proposed technique onto a representative coarse grained reconfigurable array processor (CGRA) with multimedia kernel codes. Our experimental results demonstrate that our technique optimizes data placement by putting independent data on separate storage. The results exhibit 9.8% higher performance on average compared to the existing method.

• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.54-61
• /
• 2023

The family tree is one of the key elements of humanities classics research and is very important for accurately understanding people or families. In this paper, we introduce a method for automatically generating a family tree using information on interpersonal relationships (IIPR) from the Korean Classics Database (KCDB) and visualize interpersonal searches within a family tree using data-driven document JavaScript (d3.js). To date, researchers of humanities classics have wasted considerable time manually drawing family trees to understand people's influence relationships. An automatic family tree builder analyzes a database that visually expresses the desired family tree. Because a family tree contains a large amount of data, we analyze the performance and bottlenecks according to the amount of data for visualization and propose an optimal way to construct a family tree. To this end, we create an n-ary tree with fake data, visualize it, and analyze its performance using simulation results.

• Communications for Statistical Applications and Methods
• /
• v.4 no.3
• /
• pp.891-901
• /
• 1997

The objective of this research is to investigate the problem of goodness of fit testing based on nonparametric density estimation with a data-driven smoothing parameter. The small and large smaple properties of the proposed test statistic $Z_{mn}$ are investigated with the minimizer $\widehat{m}$ of the estimated mean integrated squared error by the Diggle and Hall (1986) method.