• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.167-179
• /
• 2002

In this paper, we propose a new acoustic model for characterizing segmental features and an algorithm based upon a general framework of hidden Markov models (HMMs) in order to compensate the weakness of HMM assumptions. The segmental features are represented as a trajectory of observed vector sequences by a polynomial regression function because the single frame feature cannot represent the temporal dynamics of speech signals effectively. To apply the segmental features to pattern classification, we adopted segmental HMM(SHMM) which is known as the effective method to represent the trend of speech signals. SHMM separates observation probability of the given state into extra- and intra-segmental variations that show the long-term and short-term variabilities, respectively. To consider the segmental characteristics in acoustic model, we present segmental-feature HMM(SFHMM) by modifying the SHMM. The SFHMM therefore represents the external- and internal-variation as the observation probability of the trajectory in a given state and trajectory estimation error for the given segment, respectively. We conducted several experiments on the TIMIT database to establish the effectiveness of the proposed method and the characteristics of the segmental features. From the experimental results, we conclude that the proposed method is valuable, if its number of parameters is greater than that of conventional HMM, in the flexible and informative feature representation and the performance improvement.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.5 no.2
• /
• pp.81-90
• /
• 2002

Remote Sensing has been very useful tool in monitoring of cities and updating of GIS database compare to traditional methods due to its benefit; wide range covering on low cost and advanced data collection. However it had come to a limited method in limited researches because of its relatively poor spatial resolution in scanning. Recently launched satellites are able to produce improved imageries, and new commercial services have been commenced for the use of general public with higher spatial resolution up to $1m{\times}1m$. This study tackled a potential use of these improved satellite imageries in urban planning based on the Multi-temporal satellite imagery with particular reference to monitoring on urban areas, for example urbanization and its expanding. i) Portion of individual features and elements in each pixel of satellite imagery was computed based on 'Endmember' of targeted elements. ii) Urbanized areas were categorized based on the 'Fraction imagery' derived from the 'SMA algorithm'. iii) Alterations and expanding of urban areas were identified based on the Multi-temporal satellite imageries. Tested method showed a strong potential to produce more advanced monitoring skills of urban areas.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.1 s.307
• /
• pp.53-66
• /
• 2006

This paper proposes the combined image retrieval system that gives the same relevance as exhaustive search method while its performance can be considerably improved. This system is combined with two different retrieval methods and each gives the same results that full exhaustive search method does. Both of them are two-stage method. One uses condensation of feature vectors, and the other uses binary-tree clustering. These two methods extract the candidate images that always include correct answers at the first stage, and then filter out the incorrect images at the second stage. Inasmuch as these methods use equal algorithm, they can get the same result as full exhaustive search. The first method condenses the dimension of feature vectors, and it uses these condensed feature vectors to compute similarity of query and images in database. It can be found that there is an optimal condensation ratio which minimizes the overall retrieval time. The optimal ratio is applied to first stage of this method. Binary-tree clustering method, searching with recursive 2-means clustering, classifies each cluster dynamically with the same radius. For preserving relevance, its range of query has to be compensated at first stage. After candidate clusters were selected, final results are retrieved by computing similarities again at second stage. The proposed method is combined with above two methods. Because they are not dependent on each other, combined retrieval system can make a remarkable progress in performance.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.116-128
• /
• 2011

In this paper, we propose the structure of a high-performance face-detection engine that responds well to facial rotating changes using rotation transformation which minimize the required memory usage compared to the previous face-detection engine. The validity of the proposed structure has been verified through the implementation of FPGA. For high performance face detection, the MCT (Modified Census Transform) method, which is robust against lighting change, was used. The Adaboost learning algorithm was used for creating optimized learning data. And the rotation transformation method was added to maintain effectiveness against face rotating changes. The proposed hardware structure was composed of Color Space Converter, Noise Filter, Memory Controller Interface, Image Rotator, Image Scaler, MCT(Modified Census Transform), Candidate Detector / Confidence Mapper, Position Resizer, Data Grouper, Overlay Processor / Color Overlay Processor. The face detection engine was tested using a Virtex5 LX330 FPGA board, a QVGA grade CMOS camera, and an LCD Display. It was verified that the engine demonstrated excellent performance in diverse real life environments and in a face detection standard database. As a result, a high performance real time face detection engine that can conduct real time processing at speeds of at least 60 frames per second, which is effective against lighting changes and face rotating changes and can detect 32 faces in diverse sizes simultaneously, was developed.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.9
• /
• pp.131-143
• /
• 2011

Previous alerting service based on LBS was caused severe overload problem of server by using the method to confirm the location of each moving object on server. In this paper, by loading an App on smart moving object, we proposed a novel algorithm named ADAS(Active Disaster Alert Service) for accessing to the server site with oneself location information as needed and implemented the disaster alerting service system with visualization for user. In the proposed method, running App access to the server periodically with the present location coordinate gained from GPS module or network module and the ID of moving object. Then, the server compare the present location coordinate of moving object and the coordinates of disasters registered in DIDB and transmit the n NDIs existed in near distance orderly from the coordinate of present moving object to the client. The App compares the coordinate of present location for moving object and the coordinates of NDI is transmitted from server by real time and executes the service with classifying levels of alert into three steps such as danger, carefulness and safety. And new NDIs are gained by accessing DIDB on Server periodically during running App. Therefore, this will be become a novel method for reducing fundamentally the server overload problem in comparison with previous alerting service that the career of moving object is managed on server.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• Journal of Korea Spatial Information System Society
• /
• v.8 no.2 s.17
• /
• pp.91-107
• /
• 2006

To handling the extreme situation that must manage positional information of a very large volume, at least millions of moving objects. A cluster-based sealable distributed computing system architecture, called the GALIS which consists of multiple data processors, each dedicated to keeping records relevant to a different geographical zone and a different time zone, was proposed. In this paper, we proposed a valid time management and time-zone shifting scheme, which are essential in realizing the long-term location data subsystem of GALIS, but missed in our previous prototype development. We explain how to manage valid time of moving objects to avoid ambiguity of location information. We also describe time-zone shifting algorithm with three variations, such as Real Time-Time Zone Shifting, Batch-Time Zone Shifting, Table Partitioned Batch-Time Zone Shifting, Through experiments related with query processing time and CPU utilization, we show the efficiency of the proposed time-zone shifting schemes.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.197-206
• /
• 2010

For an emotion retrieval system implementation to support pedestrian navigation, coordinating the pedestrian emotion model with the system user's emotion is considered a key component. This study proposes a new method for capturing the user's model that corresponds to the pedestrian emotion model and examines the validity of the method. In the first phase, a database comprising a set of interior images that represent hypothetical destinations was developed. In the second phase, 10 subjects were recruited and asked to evaluate on navigation and satisfaction toward each interior image in five rounds of navigation experiments. In the last phase, the subjects' feedback data was used for of the pedestrian emotion model, which is called ‘learning' in this study. After evaluations by the subjects, the learning effect was analyzed by the following aspects: recall ratio, precision ratio, retrieval ranking, and satisfaction. Findings of the analysis verify that all four aspects significantly were improved after the learning. This study demonstrates the effectiveness of the learning algorithm for the proposed pedestrian emotion model. Furthermore, this study demonstrates the potential of such pedestrian emotion model to be well applicable in the development of various mobile contents service systems dealing with visual images such as commercial interiors in the future.

• Korean Journal of Clinical Laboratory Science
• /
• v.52 no.3
• /
• pp.229-236
• /
• 2020

Sixty-five molds isolated from clinical specimens were included in this study. All the isolates were molds that could be identified morphologically, strains that are difficult to identify because of morphological similarities, and strains that require species-level identification. PCR and direct sequencing were performed to target the internal transcribed spacer (ITS) region, the D1/D2 region, and the β-tubulin gene. Comparative sequence analysis using the GenBank database was performed using the basic local alignment search tool (BLAST) algorithm. The fungi identified morphologically to the genus level were 67%. Sequencing analysis was performed on 62 genera and species level of the 65 strains. Discrepancies were 14 (21.5%) of the 65 strains between the results of phenotypic and molecular identification. B. dermatitidis, T. marneffei, and G. argillacea were identified for the first time in Korea using the DNA sequencing method. Morphological identification is a very useful method in terms of the reporting time and costs in cases of frequently isolated and rapid growth, such as Aspergillus. When molecular methods are employed, the cost and clinical significance should be considered. On the other hand, the molecular identification of molds can provide fast and accurate results.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.42 no.1
• /
• pp.13-20
• /
• 2005

In this paper, I recognized Korean isolated words using CVEM which is suggested by M. Bilginer et al. CVEM is an algorithm which is easy to extract the common properties from training voice signals and also doesn't need complex calculation. In addition CVEM shows high accuracy in recognition results. But, CVEM has couple of problems which are impossible to use for many training voices and no discriminant information among extracted common vectors. To get the optimal common vectors from certain voice classes, various voices should be used for training. But CVEM is impossible to get continuous high accuracy in recognition because CVEM has a limitation to use many training voices and the absence of discriminant information among common vectors can be the source of critical errors. To solve above problems and improve recognition rate, k-clustering subspace method and DCVEM suggested. And did various experiments using voice signal database made by ETRI to prove the validity of suggested methods. The result of experiments shows improvements in performance. And with proposed methods, all the CVEM problems can be solved with out calculation problem.