• Journal of Korea Multimedia Society
• /
• v.10 no.6
• /
• pp.699-706
• /
• 2007

This article is an approach to improving the clustering of Web images by using high-level semantic features from text information relevant to Web images as well as low-level visual features of image itself. These high-level text features can be obtained from image URLs and file names, page titles, hyperlinks, and surrounding text. As a clustering algorithm, a self-organizing map (SOM) proposed by Kohonen is used. To evaluate the clustering efficiencies of SOMs, we propose a simple but effective measure indicating the accumulativeness of same class images and the perplexities of class distributions. Our approach is to advance the existing measures through defining and using new measures accumulativeness on the most superior clustering node and concentricity to evaluate clustering efficiencies of SOMs. The experimental results show that the high-level text features are more useful in SOM-based Web image clustering.

• Korean Linguistics
• /
• v.65
• /
• pp.211-236
• /
• 2014

The aim of this study is to investigate categorical characteristics of 'mak' and their discourse functions through analyzed the prosodic features of 'mak'. The previous studies of 'mak' focused on grammatical or semantic characteristics, but this study focuses on the prosodic features of 'mak' based on speech data. As a result, adverb 'mak' and discourse marker 'mak' are distinguished from prosodic boundary, duration, pause and sort of number tonal patterns. Functions of discourse marker 'mak' is as follows: Maintenance of utterance, Attention, Delay, Expression negative manner. These functions have salient prosodic features related to their functions. Consequently prosodic features are important to analyze categorical characteristics and to establish functions of 'mak'.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2633-2648
• /
• 2015

The problem of visual words' synonymy and ambiguity always exist in the conventional bag of visual words (BoVW) model based object category methods. Besides, the noisy visual words, so-called "visual stop-words" will degrade the semantic resolution of visual dictionary. In view of this, a novel bag of visual words method based on PLSA and chi-square model for object category is proposed. Firstly, Probabilistic Latent Semantic Analysis (PLSA) is used to analyze the semantic co-occurrence probability of visual words, infer the latent semantic topics in images, and get the latent topic distributions induced by the words. Secondly, the KL divergence is adopt to measure the semantic distance between visual words, which can get semantically related homoionym. Then, adaptive soft-assignment strategy is combined to realize the soft mapping between SIFT features and some homoionym. Finally, the chi-square model is introduced to eliminate the "visual stop-words" and reconstruct the visual vocabulary histograms. Moreover, SVM (Support Vector Machine) is applied to accomplish object classification. Experimental results indicated that the synonymy and ambiguity problems of visual words can be overcome effectively. The distinguish ability of visual semantic resolution as well as the object classification performance are substantially boosted compared with the traditional methods.

• The Journal of Society for e-Business Studies
• /
• v.14 no.2
• /
• pp.95-116
• /
• 2009

Ontologies have provided supports in integrating heterogeneous and distributed information. More and more ontologies and tools have been developed in various domains. However, building ontologies requires much time and effort. Therefore, ontologies need to be shared and reused among users. Specifically, finding the desired ontology from an ontology repository will benefit users. In the past, most of the studies on retrieving and ranking ontologies have mainly focused on lexical level supports. In those cases, it is impossible to find an ontology that includes concepts that users want to use at the semantic level. Most ontology libraries and ontology search engines have not provided semantic matching capability. Retrieving an ontology that users want to use requires a new ontology selection and ranking mechanism based on semantic similarity matching. We propose an ontology selection and ranking model consisting of selection criteria and metrics which are enhanced in semantic matching capabilities. The model we propose presents two novel features different from the previous research models. First, it enhances the ontology selection and ranking method practically and effectively by enabling semantic matching of taxonomy or relational linkage between concepts. Second, it identifies what measures should be used to rank ontologies in the given context and what weight should be assigned to each selection measure.

• Cross-Cultural Studies
• /
• v.52
• /
• pp.341-369
• /
• 2018

Li ShangYin (李商隱) was a poet who represented the late Tang period and authored more than 590 poems. In this paper, I have searched for various phonetic and semantic relationships through the attention of scholars' annotation about Li ShangYin (李商隱)'s poetry. As a result, we found 12 types of "examples that explain the phonetic and semantic relationships of poetic words" and five types of "examples that explain the features of poetic words and prosody." Especially, through analysis of "examples that explain the phonetic and semantic relationships of poetic words", it is divided into two types. The first type is that the scholars' annotation about Li ShangYin (李商隱)'s poetry and phonetic and semantic relationships of poetic words are matched, and the second type is that the scholars' annotation about Li ShangYin (李商隱)'s poetry and phonetic and semantic relationships of poetic words are inconsistent. In this study, I applied the theory of level and oblique tones for more detailed analysis of each type.

• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.251-258
• /
• 2021

In this paper, we proposed an encoder-decoder model utilizing residual learning to improve the accuracy of the U-Net-based semantic segmentation method. U-Net is a deep learning-based semantic segmentation method and is mainly used in applications such as autonomous vehicles and medical image analysis. The conventional U-Net occurs loss in feature compression process due to the shallow structure of the encoder. The loss of features causes a lack of context information necessary for classifying objects and has a problem of reducing segmentation accuracy. To improve this, The proposed method efficiently extracted context information through an encoder using residual learning, which is effective in preventing feature loss and gradient vanishing problems in the conventional U-Net. Furthermore, we reduced down-sampling operations in the encoder to reduce the loss of spatial information included in the feature maps. The proposed method showed an improved segmentation result of about 12% compared to the conventional U-Net in the Cityscapes dataset experiment.

• Journal of Korea Multimedia Society
• /
• v.7 no.11
• /
• pp.1540-1549
• /
• 2004

In this paper, we propose an algorithm to detect semantic events in golf video using Hidden Markov Model. The purpose of this paper is to identify and classify the golf events to facilitate highlight-based video indexing and summarization. In this paper we first define 4 semantic events, and then design HMM model with states made up of each event. We also use 10 multiple visual features based on MPEG-7 visual descriptors to acquire parameters of HMM for each event. Experimental results showed that the proposed algorithm provided reasonable detection performance for identifying a variety of golf events.

• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.147-156
• /
• 2006

Event logging plays increasingly an important role in system and network management, and syslog is a de-facto standard for logging system events. However, due to the semi-structured features of Common Log Format data most studies on log analysis focus on the frequent patterns. The extensible Markup Language can provide a nice representation scheme for structure and search of formatted data found in syslog messages. However, previous XML-formatted schemes and applications for system logging are not suitable for semantic approach such as ranking based search or similarity measurement for log data. In this paper, based on ranked keyword search techniques over XML document, we propose an XML tree structure through a new data modeling approach for syslog data. Finally, we show suitability of proposed structure for semantic retrieval.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.1
• /
• pp.84-97
• /
• 2012

M2M (Machine-to-Machine) Technology makes it possible to network all kinds of terminal devices and their corresponding enterprise applications. Therefore, several M2M platforms were developed in China in order to collect information from terminal devices dispersed all over the local places through 3G wireless network. However, when enterprise applications try to integrate with M2M platforms, they should be maintained and refactored to adapt the heterogeneous features and properties of M2M platforms. Moreover, syntactical and semantic unification for information sharing among applications and devices are still unsolved because of raw data transmission and the usage of distinguished business vocabularies. In this paper, we propose and develop an M2M Middleware to support agile application integration with M2M platform. This middleware imports the event engine and XML-based syntax to handle the syntactical unification, makes use of Ontology-based semantic mapping to solve the semantic unification and adopts WebService and ETL techniques to sustain multi-pattern interactive approach, in order to agilely make applications integrated with the M2M platform. Now, the M2M Middleware has been applied in the China Telecom M2M platform. The operation results show that applications will cost less time and workload when being integrated with M2M platform.

• ETRI Journal
• /
• v.33 no.5
• /
• pp.720-730
• /
• 2011

Opinion mining involves the analysis of customer opinions using product reviews and provides meaningful information including the polarity of the opinions. In opinion mining, feature extraction is important since the customers do not normally express their product opinions holistically but separately according to its individual features. However, previous research on feature-based opinion mining has not had good results due to drawbacks, such as selecting a feature considering only syntactical grammar information or treating features with similar meanings as different. To solve these problems, this paper proposes an enhanced feature extraction and refinement method called FEROM that effectively extracts correct features from review data by exploiting both grammatical properties and semantic characteristics of feature words and refines the features by recognizing and merging similar ones. A series of experiments performed on actual online review data demonstrated that FEROM is highly effective at extracting and refining features for analyzing customer review data and eventually contributes to accurate and functional opinion mining.