• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.45-50
• /
• 2004

In this paper, we propose a new PCA-based LDA Mixture Algorithm(PLMA) for real-time face recognition system. This system greatly consists of the two parts: 1) face extraction part; 2) face recognition part. In the face extraction part we applied subtraction image, color filtering, eyes and mouth region detection, and normalization method, and in the face recognition part we used the method mixing PCA and LDA in extracted face candidate region images. The existing recognition system using only PCA showed low recognition rates, and it is hard in the recognition system using only LDA to apply LDA to the input images as it is when the number of image pixels ire small as compared with the training set. To overcome these shortcomings, we reduced dimension as we apply PCA to the normalized images, and apply LDA to the compressed images, therefore it is possible for us to do real-time recognition, and we are also capable of improving recognition rates. We have experimented using self-organized DAUface database to evaluate the performance of the proposed system. The experimental results show that the proposed method outperform PCA, LDA and ICA method within the framework of recognition accuracy.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.2
• /
• pp.11-17
• /
• 1999

This paper proposes an observation probability smoothing technique for the robustness of a discrete hidden Markov(DHMM) model based speech recognizer. Also, an appropriate noise robust processing in car environment is suggested from experimental results. The noisy speech is often mislabeled during the vector quantization process. To reduce the effects of such mislabelings, the proposed technique increases the observation probability of similar codewords. For the noise robust processing in car environment, the liftering on the distance measure of feature vectors, the high pass filtering, and the spectral subtraction methods are examined. Recognition experiments on the 14-isolated words consists of the Korean digits and command words were performed. The database was recorded in a stopping car and a running car environments. The recognition rates of the baseline recognizer were 97.4% in a stopping situation and 59.1% in a running situation. Using the proposed observation probability smoothing technique, the liftering, the high pass filtering, and the spectral subtraction the recognition rates were enhanced to 98.3% in a stopping situation and to 88.6% in a running situation.

• The Journal of the Korea Contents Association
• /
• v.12 no.5
• /
• pp.1-9
• /
• 2012

The popularity of digital music and smart phones led to develope noise-robust real-time audio fingerprinting system in various ways. In particular, The Multiple Hashing(MLH) of fingerprint algorithms is robust to noise and has an elaborate structure. In this paper, we propose a filter engine based on MLH to achieve better performance. In this approach, we compose a energy-intensive filter to improve the accuracy of Q/R from music database and a statistic filter to remove continuity and redundancy. The energy-intensive filter uses the Discrite Cosine Transform(DCT)'s feature gathering energy to low-order bits and the statistic filters use the correlation between searched fingerprint's information. Experimental results show that the superiority of proposed algorithm consists of the energy and statistical filtering in noise environment. It is found that the proposed filter engine achieves more robust to noise than Philips Robust Hash(PRH), and a more compact way than MLH.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.8
• /
• pp.1750-1755
• /
• 2011

Recently, it is possible for users to acquire necessary data easily as the various schemes of the searching information are developed. Since these data rise continuously like stream data, it is required to extract the appropriate data for the user's needs from the mass data on the internet. In the traditional scheme, they are acquired by processing the user queries after the occurred data are stored at a database. However, it is inefficient to process the user queries over the large volume of continuous data by using the traditional scheme. In this paper, we propose the Event-Profile Model to define the data occurrence on the internet as the events and the user's requirements as the profiles. We also propose and implement the filtering scheme to process the events and the profiles efficiently. We evaluate the performance of the proposed scheme and our experiments show that the new scheme outperforms the other on various dataset.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.712-716
• /
• 2010

In this paper, we propose a novel shape-based approach to detect CNV regions (CNVR) by analyzing the coverage graph obtained by aligning the giga-sequencing data onto the human reference sequence. The proposed algorithm proceeds in two steps: a filtering step and a post-processing step. In the filtering step, it takes several shape parameters as input and extracts candidate CNVRs having various depth and width. In the post-processing step, it revises the candidate regions to make up for errors potentially included in the reference sequence and giga-sequencing data, and filters out regions with high ratio of GC-contents, and returns the final result set from those candidate CNVRs. To verify the superiority of our approach, we performed extensive experiments using giga-sequencing data publicly opened by "1000 genome project" and verified the accuracy by comparing our results with those registered in DGV database. The result revealed that our approach successfully finds the CNVR having various shapes (gains or losses) in HLA (Human Leukocyte Antigen) region.

• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.653-662
• /
• 2006

In ubiquitous computing that is to build computing environments to provide proper services according to user's context, human being's emotion recognition based on facial expression is used as essential means of HCI in order to make man-machine interaction more efficient and to do user's context-awareness. This paper addresses a problem of rigidly basic emotion recognition in context-sensitive facial expressions through a new Bayesian classifier. The task for emotion recognition of facial expressions consists of two steps, where the extraction step of facial feature is based on a color-histogram method and the classification step employs a new Bayesian teaming algorithm in performing efficient training and test. New context-sensitive Bayesian learning algorithm of EADF(Extended Assumed-Density Filtering) is proposed to recognize more exact emotions as it utilizes different classifier complexities for different contexts. Experimental results show an expression classification accuracy of over 91% on the test database and achieve the error rate of 10.6% by modeling facial expression as hidden context.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.249-252
• /
• 2009

Recently, it is possible for users to acquire necessary data easily as the various schemes of the searching information are developed. Since these data rise continuously like stream data, it is required to extract the appropriate data for the user's needs from the mass data on the internet. In the traditional scheme, they are acquired by processing the user queries after the occurred data are stored at a database. However, it is inefficient to process the user queries over the large volume of continuous data by using the traditional scheme. In this paper, we propose the query processing scheme to extract the data efficiently for the user requirements from the large volume of continuous data. On the proposed scheme, we present the Event-Profile Model to define the data occurrence on the internet as the events and the user's requirements as the profiles. We also show the filtering scheme to process the events and the profiles efficiently.

• International Journal of Computer Science & Network Security
• /
• v.21 no.1
• /
• pp.12-18
• /
• 2021

This paper proposes a framework for the development of the health recommender system, designed to cater COVID-19 symptoms' self-assessment and monitoring as well as to provide recommendations for self-care and medical treatments. The aim is to provide an online platform for Patient Under Investigation (PUI) and close contacts with positive COVID-19 cases in Malaysia who are under home quarantine to perform daily self-assessment in order to monitor their own symptoms' development. To achieve this, three main phases of research methods have been conducted where interviews have been done to thirty former COVID-19 patients in order to investigate the symptoms and practices conducted by the Malaysia Ministry of Health (MOH) in assessing and monitoring COVID-19 patients who were under home quarantine. From the interviews, an algorithm using user-based collaborative filtering technique with Pearson correlation coefficient similarity measure is designed to cater the self-assessment and symptoms monitoring as well as providing recommendations for self-care treatments as well as medical interventions if the symptoms worsen during the 14-days quarantine. The proposed framework will involve the development of the health recommender system for COVID-19 self-assessment and treatments using the progressive web application method with cloud database and PHP codes.

• Journal of Information Technology Services
• /
• v.21 no.2
• /
• pp.109-126
• /
• 2022

The number and variety of products and services offered by companies have increased dramatically, providing customers with more choices to meet their needs. As a solution to this information overload problem, the provision of tailored services to individuals has become increasingly important, and the personalized recommender systems have been widely studied and used in both academia and industry. Existing recommender systems face important problems in practical applications. The most important problem is that it cannot clearly explain why it recommends these products. In recent years, some researchers have found that the explanation of recommender systems may be very useful. As a result, users are generally increasing conversion rates, satisfaction, and trust in the recommender system if it is explained why those particular items are recommended. Therefore, this study presents a methodology of providing an explanatory function of a recommender system using a review text left by a user. The basic idea is not to use all of the user's reviews, but to provide them in a summarized form using only reviews left by similar users or neighbors involved in recommending the item as an explanation when providing the recommended item to the user. To achieve this research goal, this study aims to provide a product recommendation list using user-based collaborative filtering techniques, combine reviews left by neighboring users with each product to build a model that combines text summary methods among deep learning-based natural language processing methods. Using the IMDb movie database, text reviews of all target user neighbors' movies are collected and summarized to present descriptions of recommended movies. There are several text summary methods, but this study aims to evaluate whether the review summary is well performed by training the Sequence-to-sequence+attention model, which is a representative generation summary method, and the BertSum model, which is an extraction summary model.

• Investigative Magnetic Resonance Imaging
• /
• v.4 no.2
• /
• pp.128-135
• /
• 2000

Purpose : The aim of this study is to develope the Magnetic Resonance Spectroscopy(MRS) data processing S/W which plays an important role as a diagnostic tool in clinical field. Materials and methods : Post-processing software of MRS based on graphical user interface(GUI) under windows operating system of personal computer(PC) was developed using MATLAB(Mathwork, U.S.A.). This tool contains many functions to increase the quality of spectrum data such as DC correction, zero filling, line broadening, Gauss-Lorentzian filtering, phase correction, etc. And we obtained the normal human brain $^1H$ MRS data from parietal white matter, basal ganglia and occipital grey matter region using 1.5T Gyroscan ACS-NT R6 (philips, Amsterdam, Netherland) MRS package. The analysis of the MRS peaks were performed by obtaining the ratio of peak area. Results : The peak ratios of NAA/Cr, Cho/Cr, MI/Cr for the different MRS machines have a little different values. But these peak ratios were not significantly different between different echo time MRS peak ratios in the same machine (p<0.05). Conclusion : MRS post-processing S/W based on GUI using PC was developed and applied to the analysis of normal human brain $^1H$ MRS. This independent MRS processing job increases the performance and throughput of patient scan of main console. Finally, we suggest that the database for normal in-yivo human MRS data should be obtained before clinical applications.