• Journal of the Korean Statistical Society
• /
• v.33 no.4
• /
• pp.401-410
• /
• 2004

We address the problem of parameter estimation in multivariate distributions under ignorable non-monotone missing data. The factoring likelihood method for monotone missing data, termed by Rubin (1974), is extended to a more general case of non-monotone missing data. The proposed method is algebraically equivalent to the Newton-Raphson method for the observed likelihood, but avoids the burden of computing the first and the second partial derivatives of the observed likelihood. Instead, the maximum likelihood estimates and their information matrices for each partition of the data set are computed separately and combined naturally using the generalized least squares method.

• Environmental Analysis Health and Toxicology
• /
• v.20 no.4 s.51
• /
• pp.351-358
• /
• 2005

The n -octanol/water partition coefficient (Pow) is one of the most important parameters employed for estimating a chemiral's environmental fate and toxicity. The shake-flask method, one direct experimental method, i.1 prone to experimental artifacts for highly hydrophobic compounds. Thus, a valid method for direct determination of the Pow of highly hydrophobic compounds is needed. The slow -stirring method has been demonstrated to provide reliable log Pow data to log Pow greater than 5. This study was performed to evaluate the accuracy of slow- stirring experiment for determination of log Pow, particularly for highly hydrophobic compounds. 1, 2, 3, 4-tetrachlorobenzene, hexachlorobezene, 2, 2', 3, 3', 5, 5', 6, 6'-octachlorobiphenyl, decachlorobiphenyl, and p, p'-DDT (4.5$\times$0.02, 5.41$\times$0.06, 7.26$\times$0.04, 7.87$\times$0.10, and 6.03$\times$0.06, respectively. The octanol/water partition coefficient by the slow-stirring method were very similar to the literature values. These results indicate that the slow- stirring method allows for reliable determination of log Pow of highly hydrophobic chemicals.

• Health Policy and Management
• /
• v.30 no.2
• /
• pp.178-184
• /
• 2020

Background: Korea set up a new diagnosis-related group as a demonstration project in 2009. The new diagnosis-related group was reformed in 2016. The main purpose of the study is to identify the effect of reform on coverage of national health insurance. Methods: This study collected inpatient data from a hospital that contains medical information and cost from 2015 July to 2016 June. The dependent variable was the coverage of national health insurance. The dependent variable was divided by total, internal medicine partition, surgical partition, and psychiatric partition. To analyze the effect of the reform, this study conducted an interrupted time series analysis. The final sample included 23,695. Results: The health insurance coverage of internal medicine has the highest, followed by surgery and psychiatry. The health insurance coverage of bundle payment is higher than that of unbundled payment. The proportion of bundled payment and non-benefit decreased and the proportion of unbundled payment increased. The coverage of national health insurance significantly increased after policy reform in internal medicine partition (p-value=0.0356). Conclusion: The results of the study imply that policy reform enhanced the coverage of national health insurance in internal medicine. The government needs to monitor side effects such as an increase of unbundled payment.

• Journal of IKEEE
• /
• v.5 no.1 s.8
• /
• pp.1-7
• /
• 2001

In this paper, we have investigated the CDMA(Code Division Multiple Access) Cellular System with non-linear equalizer in reverse link channel. In general, due to unknown characteristics of channel in the wireless communication, the distribution of the observables cannot be specified by a finite set of parameters; instead, we partitioned the m-dimensional sample space Into a finite number of disjointed regions by using quantiles and a vector quantizer based on training samples. The algorithm proposed is based on a piecewise approximation to regression function based on quantiles and conditional partition moments which are estimated by Robbins Monro Stochastic Approximation (RMSA) algorithm. The resulting equalizers and detectors are robust in the sense that they are insensitive to variations in noise distributions. The main idea is that the robust equalizers and robust partition detectors yield better performance in equiprobably partitioned subspace of observations than the conventional equalizer in unpartitioned observation space under any condition. And also, we apply this idea to the CDMA system and analyze the BER performance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.141-147
• /
• 2024

Recently, there has been growing interest in personalized services tailored to an individual's preferences. This has led to ongoing research aimed at recognizing and leveraging an individual's personality traits. Among various methods for personality assessment, the OCEAN model stands out as a prominent approach. In utilizing OCEAN for personality recognition, a multi modal artificial intelligence model that incorporates linguistic, paralinguistic, and non-linguistic information is often employed. This paper examines the impact of the margin value set for extracting facial areas from video data on the accuracy of a personality recognition model that uses facial expressions to determine OCEAN traits. The study employed personality recognition models based on 2D Patch Partition, R2plus1D, 3D Patch Partition, and Video Swin Transformer technologies. It was observed that setting the facial area extraction margin to 60 resulted in the highest 1-MAE performance, scoring at 0.9118. These findings indicate the importance of selecting an optimal margin value to maximize the efficiency of personality recognition models.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.12
• /
• pp.5042-5048
• /
• 2010

In ubiquitous environments, many continuous query processing techniques make use of operator network and sharing methods on continuous data stream generated from various sensors. Since similar continuous queries with the location information intensively occur in specific regions, we suggest a new operator sharing method based on grid partition for the spatial continuous query processing for location-based applications. Due to the proposed method shares moving objects by the given grid cell without sharing spatial operators individually, our approach can not only share spatial operators including similar conditions, but also increase the query processing performance and the utilization of memory by reducing the frequency of use of spatial operators.

• Journal of Biomedical Engineering Research
• /
• v.31 no.1
• /
• pp.40-49
• /
• 2010

A rule weight -based fuzzy classification model is proposed to analyze the patterns of admission-discharge of patients as a previous research for differential diagnosis of dyspnea. The proposed model is automatically generated from a labeled data set, supervised learning strategy, using three procedure methodology: i) select fuzzy partition regions from spatial distribution of data; ii) generate fuzzy membership functions from the selected partition regions; and iii) extract a set of candidate rules and resolve a conflict problem among the candidate rules. The effectiveness of the proposed fuzzy classification model was demonstrated by comparing the experimental results for the dyspnea patients' data set with 11 features selected from 55 features by clinicians with those obtained using the conventional classification methods, such as standard fuzzy classifier without rule weights, C4.5, QDA, kNN, and SVMs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4703-4723
• /
• 2018

In recent years, dense small cell network has been deployed to address the challenge that has resulted from the unprecendented growth of mobile data traffic and users. It has proven to be a cost efficeient solution to offload traffic from macro-cells. Software defined heterogeneous wireless network can decouple the control plane from the data plane. The control signal goes through the macro-cell while the data traffic can be offloaded by small cells. In this paper, we propose a framework for cell virtualization and user association in order to satisfy versatile requirements of multiple tenants. In the proposed framework, we propose an interference graph partioning based virtual-cell association and customized physical-cell association for multi-homed users in a software defined small cell network. The proposed user association scheme includes 3 steps: initialization, virtual-cell association and physical-cell association. Simulation results show that the proposed virtual-cell association outperforms the other schemes. For physical-cell association, the results on resource utilization and user fairness are examined for mobile users and infrastructure providers.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.6
• /
• pp.1397-1404
• /
• 2017

When a digital forensic investigation is conducted on a damaged storage medium, recovery is performed using a recovery tool. But the result of each recovery tool is different depending on the tools. Therefore, it is necessary to identify and use the performance and limitations of the tool for accurate investigation. In this paper, we propose a scenario considering the disk recognition type such as MBR, GPT and the structural characteristics of FAT32 and NTFS filesystem to verify the performance of the partition recovery tool. And then We validate the existing tools with the data set built on the scenarios.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.351-353
• /
• 2003

We present a retrieval scheme for the remote sensing of evapotranspiration (ET) over rice paddy. To perform the retrieval, high-resolution airborne imagery of multi-spectral visible and thermal infrared data, and ground-based meteorological measurements are utilized. Our ET retrieval scheme is based on the basic principal of surface energy budget, which is a result of balance in longwave and shortwave radiation, latent heat, sensible heat, and energy flux into the ground. To partition the latent and sensible heat fluxes of interest from the energy balance equation, three basic parameters are of most concern, including albedo, surface temperature, and normalized difference vegetation index (NDVI). The NDVI and albedo can be easily derived from the visible and near infrared spectral data, while the surface tem-perature can be determined through the analysis of the infrared data with the Stefan Boltzmann law. From the airborne imagery taken on 28 April 2003, we observe very good dry and wet pixels that can be easily corre-sponded to the radiation and evaporation controlled crite-ria, respectively, and, hence, for the further use in defin-ing the evaporative fraction needed to partition sensible and latent heat fluxes from the net energy flux. The de-rived ET is compared with the in situ measurements.