• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1045-1055
• /
• 2007

Latent topic models are statistical models which automatically captures salient patterns or correlation among features underlying a data collection in a probabilistic way. They are gaining an increased popularity as an effective tool in the application of automatic semantic feature extraction from text corpus, multimedia data analysis including image data, and bioinformatics. Among the important issues for the effectiveness in the application of latent topic models to the massive data set is the efficient learning of the model. The paper proposes an accelerated learning technique for PLSA model, one of the popular latent topic models, by an incremental EM algorithm instead of conventional EM algorithm. The incremental EM algorithm can be characterized by the employment of a series of partial E-steps that are performed on the corresponding subsets of the entire data collection, unlike in the conventional EM algorithm where one batch E-step is done for the whole data set. By the replacement of a single batch E-M step with a series of partial E-steps and M-steps, the inference result for the previous data subset can be directly reflected to the next inference process, which can enhance the learning speed for the entire data set. The algorithm is advantageous also in that it is guaranteed to converge to a local maximum solution and can be easily implemented just with slight modification of the existing algorithm based on the conventional EM. We present the basic application of the incremental EM algorithm to the learning of PLSA and empirically evaluate the acceleration performance with several possible data partitioning methods for the practical application. The experimental results on a real-world news data set show that the proposed approach can accomplish a meaningful enhancement of the convergence rate in the learning of latent topic model. Additionally, we present an interesting result which supports a possible synergistic effect of the combination of incremental EM algorithm with parallel computing.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.37-45
• /
• 2006

In this paper, we propose the development of MHLA(Modulatory Hippocampus Learning Algorithm) which remodel a principle of brain of hippocampus. Hippocampus takes charge auto-associative memory and controlling functions of long-term or short-term memory strengthening. We organize auto-associative memory based 3 steps system(DG, CA3, CAl) and improve speed of learning by addition of modulator to long-term memory learning. In hippocampal system, according to the 3 steps order, information applies statistical deviation on Dentate Gyrus region and is labelled to responsive pattern by adjustment of a good impression. In CA3 region, pattern is reorganized by auto-associative memory. In CAI region, convergence of connection weight which is used long-term memory is learned fast by neural networks which is applied modulator. To measure performance of MHLA, PCA(Principal Component Analysis) is applied to face images which are classified by pose, expression and picture quality. Next, we calculate feature vectors and learn by MHLA. Finally, we confirm cognitive rate. The results of experiments, we can compare a proposed method of other methods, and we can confirm that the proposed method is superior to the existing method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.333-337
• /
• 2021

Companion animals are physically, mentally, and socially beneficial to humans, giving us great comfort in living in the Corona19 (COVID-19) era. It is also an era of the Fourth Industrial Revolution, featuring the convergence of information and communication technology. Korea, which is facing a super-aged society, has the highest suicide rate among OECD countries, and companion animals that are effective in emotional stability can be the answer. This study is about companion animals that are effective in stabilizing the emotions of the elderly, one of the major problems in the Republic of Korea, which is about to solve in a super-aged society with more than 20 percent of the elderly aged 65 or older, needs to solve. The impact of knowledge of raising companion animals on the satisfaction level of the elderly was investigated through the management and awareness of infectious diseases. Although the level of care of companion animals had a very significant (p<0.001) effect on the satisfaction of the companion animals, the recognition of infectious diseases has no statistical significance (p>0.05). Raising companion animals with knowledge of rearing increases the satisfaction level and can lead to a happier life. While personal learning is important, it is also believed that supporting education will be necessary as a policy consideration.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.4
• /
• pp.77-87
• /
• 2018

The study was a mixed design study that analyzed the effects of developing and applying a program to improve pregnancy recognition for severe low fertility. The study period was from April 1, 2018, to October 26, 2018, and the participants included 16 women of 19~21 age who lived in M City and M Gun. The process of program development is based on Dorothy Johnson 's theory of behavior system to induce change of perception, and reference literature review and national policy report. The program developed through the literature was finally developed by examining the experts panel discussion after deriving causes and alternatives for low fertility from 25 fertility women. The contents of program consist of three areas. Quantitative research results were analyzed using Shapiro Wilk and Wilcoxon sign rank using SPSS 18.0, and qualitative research results were analyzed using focus group. As a result of study, the perception of pregnancy increased significantly (P<0.01) with statistical significance as pre-experimental (M=3.21, SD=.342), post-experimental (M=4.46, SD=.398) and the result of content analysis appeared three themes as , , . In conclusion, the program was effective in improving the recognition of pregnancy for young women.

• Journal of Digital Convergence
• /
• v.18 no.9
• /
• pp.103-112
• /
• 2020

The purpose of this study is to examine the current status and components of Korean National Debt and to analyze the effects of each component on National Debt. In the Korean Statistical Information Service (KOSIS), we searched for data such as General Accounting Deficit Conservation, For Foreign Exchange Market Stabilization, For Common Housing Stability, Local Government Net Debt Public Funds, etc that constitute National Debt. The analysis period used a total of 23 annual data from 1997 to 2019. The data collected in this study use the rate of change compared to the previous year for each component. Using this, this study attempted index analysis, numerical analysis, and model analysis. Correlation analysis result, the National Debt has a high relationship with the For Common Housing Stability. For Foreign Exchange Market Stabilization, Public Funds, etc., but has a low relationship with the Local Government Net Debt. Since 1997, National Debt has been increasing similarly to the For Foreign Exchange Market Stabilization, For Common Housing Stability and Public Funds etc. Since 2020, Korea is expected to increase significantly in terms of For Common Housing Stability and Public Funds, etc due to Corona19. At a time when the global economic situation is difficult, Korea's National Debt is expected to increase significantly due to the use of national disaster subsidies. However, if possible, the government expects to operate efficiently for economic growth and financial market stability.

• Journal of Industrial Convergence
• /
• v.21 no.12
• /
• pp.63-73
• /
• 2023

This study aimed to investigate factors influencing depressive symptoms among middle-aged women based on walking and nonwalking. The participants of the study were 56,007 women aged 40-64 years. A complex sample statistical analysis was conducted. Notably, 48.9% of middle-aged women were in the walking group and 51.1% were in the nonwalking. In the nonwalking group, relative to the walking group, more people had high school diploma as their highest level of education, and were 40-49 years old, unemployed, and public assistance recipients than in the walking group. In addition, in the nonwalking group, more people had sleeping durations of less than 7 hours, perceived stress, and depressive symptoms than in the walking group. Factors influencing depressive symptoms were identified as less than 7 hours of sleeping duration and high perceived stress in both the walking and nonwalking groups, and the degree of influence was higher in the walking group than in the non-walking group, suggesting than further studies are needed to identify the cause. The results confirmed that perceived stress and depressive symptoms in middle-aged women could be reduced by walking. Therefore, if middle-aged women continue to engage in walking practices appropriate for them, it will enhance their walking rate, reduce stress, and improve their depressive symptoms.

• The Korean Journal of Applied Statistics
• /
• v.26 no.5
• /
• pp.847-856
• /
• 2013

We propose a modified learning process for generalized neural network using a learning algorithm by Liu et al. (2001). We consider the effect of initial weights, training results and learning errors using a modified learning process. We employ an incremental training procedure where training patterns are learned systematically. Our algorithm starts with a single training pattern and a single hidden layer neuron. During the course of neural network training, we try to escape from the local minimum by using a weight scaling technique. We allow the network to grow by adding a hidden layer neuron only after several consecutive failed attempts to escape from a local minimum. Our optimization procedure tends to make the network reach the error tolerance with no or little training after the addition of a hidden layer neuron. Simulation results with suitable initial weights indicate that the present constructive algorithm can obtain neural networks very close to minimal structures and that convergence to a solution in neural network training can be guaranteed. We tested these algorithms extensively with small training sets.

• Journal of Digital Convergence
• /
• v.10 no.10
• /
• pp.333-338
• /
• 2012

Human resource management is bringing the various changes with the IT technology. In particular, if HRM is non-scientific method such as group management, physical plant, working hours constraints, personal contacts, etc, the current enterprise human resources management(e-HRM) appeared in the individual dimension management, virtual workspace (for example: smart work center, home work, etc.), working time flexibility and elasticity, computer-based statistical data and the scientific method of analysis and management has been a big difference in the sense. Therefore, depending on changes in the environment, companies have introduced a variety of techniques as RFID card, fingerprint time & attendance systems in order to build more efficient and strategic human resource management system. In this paper, time and attendance, access control management system was developed using multi camera for 2D and 3D face recognition technology-based for efficient enterprise human resource management. We had an issue with existing 2D-style face-recognition technology for lighting and the attitude, and got more than 90% recognition rate against the poor readability. In addition, 3D face recognition has computational complexities, so we could improve hybrid video recognition and the speed using 3D and 2D in parallel.