• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.87-96
• /
• 2021

The demand for e-learning through video lectures is rapidly increasing due to its diverse advantages over the traditional learning methods. This led to massive volumes of web-based lecture videos. Indexing and retrieval of a lecture video or a lecture video topic has thus proved to be an exceptionally challenging problem. Many techniques listed by literature were either visual or audio based, but not both. Since the effects of both the visual and audio components are equally important for the content-based indexing and retrieval, the current work is focused on both these components. A framework for automatic topic-based indexing and search depending on the innate content of the lecture videos is presented. The text from the slides is extracted using the proposed Merged Bounding Box (MBB) text detector. The audio component text extraction is done using Google Speech Recognition (GSR) technology. This hybrid approach generates the indexing keywords from the merged transcripts of both the video and audio component extractors. The search within the indexed documents is optimized based on the Naïve Bayes (NB) Classification and K-Means Clustering models. This optimized search retrieves results by searching only the relevant document cluster in the predefined categories and not the whole lecture video corpus. The work is carried out on the dataset generated by assigning categories to the lecture video transcripts gathered from e-learning portals. The performance of search is assessed based on the accuracy and time taken. Further the improved accuracy of the proposed indexing technique is compared with the accepted chain indexing technique.

• Journal of Korean Society for Atmospheric Environment
• /
• v.25 no.5
• /
• pp.450-458
• /
• 2009

The range-dependent overlap factor of a lidar system can be determined experimentally if a Raman backscatter signal by molecule is measured in addition to the usually observed elastic backscatter signal, which consists of a molecular component and a particle component. The direct determination of the overlap profile is presented and applied to a lidar measurement according to variation of telescope field-of-view and distance between telescope and transmitting laser. The retrieval of extinction coefficient by Raman method can generate high errors for heights below planetary boundary layer if the overlap effect is ignored. The overlap correction method presented here has been successfully applied to experimental data obtained in Gwangju, Korea.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.33-36
• /
• 2008

This paper presents soil moisture retrieval from measured polarimetric backscattering coefficients of a vegetated surface. Based on the analysis of the quite complicate first-order radiative transfer scattering model for vegetated surfaces, a simplified scattering model is proposed for an inversion algorithm. Extraction of the surface-scatter component from the total scattering of a vegetation canopy is addressed using the simplified model, and also using the three-component decomposition technique. The backscattering coefficients are measured with a polarimetric L-band scatterometer during two months. At the same time, the biomasses, leaf moisture contents, and soil moisture contents are also measured. Then the measurement data are used to estimate the model parameters for vv-, hh-, and vh-polarizations. The scattering model for tall-grass-covered surfaces is inverted to retrieve the soil moisture content from the measurements using a genetic algorithm. The retrieved soil moisture contents agree quite well with the in-situ measured soil moisture data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4534-4555
• /
• 2015

We propose a robust object cataloging method using multiple locally distinct heterogeneous features for aiding image retrieval. Due to challenges such as variations in object size, orientation, illumination etc. object recognition is extraordinarily challenging problem. In these circumstances, we adapt local interest point detection method which locates prototypical local components in object imageries. In each local component, we exploit heterogeneous features such as gradient-weighted orientation histogram, sum of wavelet responses, histograms using different color spaces etc. and combine these features together to describe each component divergently. A global signature is formed by adapting the concept of bag of feature model which counts frequencies of its local components with respect to words in a dictionary. The proposed method demonstrates its excellence in classifying objects in various complex backgrounds. Our proposed local feature shows classification accuracy of 98% while SURF,SIFT, BRISK and FREAK get 81%, 88%, 84% and 87% respectively.

• Journal of KIISE:Software and Applications
• /
• v.29 no.10
• /
• pp.747-754
• /
• 2002

In this paper, We propose a document thematic words extraction by using principal component analysis(PCA) which is one of the multivariate statistical methods. The proposed PCA model understands the flow of words in the document by using an eigenvalue and an eigenvector, and extracts thematic words. The proposed model is estimated by applying to document summarization. Experimental results using newspaper articles show that the proposed model is superior to the model using either word frequency or information retrieval thesaurus. We expect that the Proposed model can be applied to information retrieval , information extraction and document summarization.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1443-1452
• /
• 1996

In this paper, we propose a semantic similarity measure for reusable software components, which aims to provide the automatic classification process of reusable to be stored in the structure of a software library, and to provide an efficient retrieval method of the software components satisfying the user's requirements. We have identified the facets to represent component characteristics by extracting information from the component descriptions written in a natural language, composed the software component identifiers from the automatically extracted terms corresponding to each facets, and stored them which the components in the nearest locations according to the semantic similarity of the classified components. In order to retrieve components satisfying user's requirements, we measured a semantic similarity between the queries and the stored components in the software library. As a result of using the semantic similarity to retrieve reusable components, we could not only retrieve the set of components satisfying user's queries. but also reduce the retrieval time of components of user's request. And we further improve the overall retrieval efficiency by assigning relevance ranking to the retrieved components according to the degree of query satisfaction.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.142-145
• /
• 2005

According as marine leisure industry has developed and the demand of leisure culture has increased rapidly, a desire about service which supply marine safety and connect marine information is enlarging. We wish to develop contents of download form that supply geographic information of Electronic Navigational Chart(ENC) in the marine that is digitalized to carrying along terminal of WIPI base and various informations for marine leisure. For this, DB that offer ENC and additional information should be constructed. Also, we need server(CPS; Contents provider Server) that offer required contents. In this paper, we design web retrieval component which store request information to database. When consumer required necessary information through personal mobile device, CPS can inform that. So, we wish to develop web retrieval agent component that parse informations in various World Wide Webs, and store to database.

• The Journal of the Korea Contents Association
• /
• v.2 no.3
• /
• pp.87-95
• /
• 2002

This study proposes method to classify components in repository and retrieve them introducing the idea of domain orientation for successful reuse of components. About components of existing systems design pattern was applied to, us suggest component classification method to compare structural similarity between each component in relevant domain and criterion pattern. Component reusability and portability between platforms can be increased through classifying reusable components by function and giving their structures with diagram. Efficiency of component reuse can be raised because the most appropriate component to query and similar candidate components and provided in priority by use of E-SARM algorithm.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.381-384
• /
• 2005

We have applied the TOMS aerosols retrieval algorithm to GLI measurements. TOMS has utilized the aerosol index, which is a measure of the change in spectral contrast due to the wavelength-dependent effects of aerosols. We have retrieved the GLI aerosol index, which is made by the pair of 380/400nm, 380/412nm, 380/460nm, and 412/460nm. We have found that the biomass burning aerosols represent the absorbing aerosols. In addition, the pair of 380/460nm has shown the best signal for detecting aerosols in Principal Component Analysis(PCA) and comparison of aerosol optical thickness from AERONET data. The theoretical aerosol index is also shown the best signal in the pair of 380/460nm.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.24
• /
• pp.10573-10576
• /
• 2015

Background: Accuracy in feature extraction is an important factor in image classification and retrieval. In this paper, a breast tissue density classification and image retrieval model is introduced for breast cancer detection based on thermographic images. The new method of thermographic image analysis for automated detection of high tumor risk areas, based on two-directional two-dimensional principal component analysis technique for feature extraction, and a support vector machine for thermographic image retrieval was tested on 400 images. The sensitivity and specificity of the model are 100% and 98%, respectively.