• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1313-1323
• /
• 2019

With the development of the Internet and the increase of smart phones, various services considering user convenience are increasing, so that users can check news in real time anytime and anywhere. However, online news is categorized by media and category, and it provides only a few related search terms, making it difficult to find related news related to keywords. In order to solve this problem, we propose a method to recommend related documents more accurately by applying Doc2Vec similarity to the specific keywords of news articles and weighting the title and contents of news articles. We collect news articles from Naver politics category by web crawling in Java environment, preprocess them, extract topics using LDA modeling, and find similarities using Doc2Vec. To supplement Doc2Vec, we apply TF-IDF to obtain TC(Title Contents) weights for the title and contents of news articles. Then we combine Doc2Vec similarity and TC weight to generate TC weight-similarity and evaluate the similarity between words using PMI technique to confirm the keyword association.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.33 no.4
• /
• pp.63-82
• /
• 2008

The explosively growing attractiveness of the Web is commencing significant demands for a structuring analysis on various web objects. The larger the substantial number of web objects are available, the more difficult for the clients(i.e. common web users and web robots) and the servers(i.e. Web search engine) to retrieve what they really want. We have in mind focusing on the structure of web objects by introducing optimization models for more convenient and effective information retrieval. For this purpose, we represent web objects and hyperlinks as a directed graph from which the optimal structures are derived in terms of rooted directed spanning trees and Top-k trees. Computational experiments are executed for synthetic data as well as for real web sites' domains so that the Lagrangian Relaxation approaches have exploited the Top-k trees and Hop constraint resolutions. In the experiments, our methods outperformed the conventional approaches so that the complex web graph can successfully be converted into optimal-structured ones within a reasonable amount of computation time.

• Journal of the Semiconductor & Display Technology
• /
• v.13 no.4
• /
• pp.91-96
• /
• 2014

Mobile image retrieval is one of the most exciting and fastest growing research fields in the area of multimedia technology. As the amount of digital contents continues to grow users are experiencing increasing difficulty in finding specific images in their image libraries. This paper proposes a new efficient and effective mobile image retrieval method that applies a weighted combination of color and texture utilizing spatial-color and second order statistics. The system for mobile image searches runs in real-time on an iPhone and can easily be used to find a specific image. To evaluate the performance of the new method, we assessed the iPhone simulations performance in terms of average precision and recall using several image databases and compare the results with those obtained using existing methods. Experimental trials revealed that the proposed descriptor exhibited a significant improvement of over 13% in retrieval effectiveness, compared to the best of the other descriptors.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.2
• /
• pp.69-77
• /
• 2009

Stream service environment demands real-time query processing for voluminous data which are ceaselessly delivered from tremendous sources. Typical R-tree based query processing technologies cannot efficiently handle such situations, which require repetitive and inefficient exploration from the tree root on every data event. However, many stream data including sensor readings show high locality, which we exploit to reduce the search space of queries to explore. In this paper, we propose a query processing scheme exploiting the locality of stream data. From the simulation, we conclude that the proposed scheme performs much better than the traditional ones in terms of scalability and exploration efficiency.

• The Journal of the Korea Contents Association
• /
• v.20 no.2
• /
• pp.561-571
• /
• 2020

Location information service using big data is continuously developing. In terms of navigation, the range of services from map API service to ship navigation information has been expanded, and system application information has been extended to SNS and blog search records for each location. Recently, it is being used as a new industry such as location-based search and advertisement, driverless cars, Internet of Things (IoT) and online to offline (O2O) services. In this study, we propose an information system that enables users to receive information about nearby stores more effectively by using big data when a user moves a specific route. In addition, we have designed this system so that local stores can use this system to effectively promote it at low cost. In particular, we analyzed web-based information in real time to improve the accuracy of information provided to users by complementing the data. Through this system, system users will be able to utilize the information more effectively. Also, from a system perspective, it can be used to create new services by integrating with various web services.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.2
• /
• pp.51-62
• /
• 2018

High utility sequential pattern (HUSP) mining has been considered as an important research topic in data mining. Although some algorithms have been proposed for this topic, they incur the problem of producing a large search space for HUSPs. The tighter utility upper bound of a sequence can prune more unpromising patterns early in the search space. In this paper, we propose a sequence expected utility (SEU) as a new utility upper bound of each sequence, which is the maximum expected utility of a sequence and all its descendant sequences. A sequence utility list for each pattern is used as a new data structure to maintain essential information for mining HUSPs. We devise an algorithm, high sequence utility list-span (HSUL-Span), to identify HUSPs by employing SEU. Experimental results on both synthetic and real datasets from different domains show that HSUL-Span generates considerably less candidate patterns and outperforms other algorithms in terms of execution time.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.109-125
• /
• 2019

As interest on intelligent search engines increases, various studies have been conducted to extract and utilize the features related to products intelligencely. In particular, when users search for goods in e-commerce search engines, the 'color' of a product is an important feature that describes the product. Therefore, it is necessary to deal with the synonyms of color terms in order to produce accurate results to user's color-related queries. Previous studies have suggested dictionary-based approach to process synonyms for color features. However, the dictionary-based approach has a limitation that it cannot handle unregistered color-related terms in user queries. In order to overcome the limitation of the conventional methods, this research proposes a model which extracts RGB values from an internet search engine in real time, and outputs similar color names based on designated color information. At first, a color term dictionary was constructed which includes color names and R, G, B values of each color from Korean color standard digital palette program and the Wikipedia color list for the basic color search. The dictionary has been made more robust by adding 138 color names converted from English color names to foreign words in Korean, and with corresponding RGB values. Therefore, the fininal color dictionary includes a total of 671 color names and corresponding RGB values. The method proposed in this research starts by searching for a specific color which a user searched for. Then, the presence of the searched color in the built-in color dictionary is checked. If there exists the color in the dictionary, the RGB values of the color in the dictioanry are used as reference values of the retrieved color. If the searched color does not exist in the dictionary, the top-5 Google image search results of the searched color are crawled and average RGB values are extracted in certain middle area of each image. To extract the RGB values in images, a variety of different ways was attempted since there are limits to simply obtain the average of the RGB values of the center area of images. As a result, clustering RGB values in image's certain area and making average value of the cluster with the highest density as the reference values showed the best performance. Based on the reference RGB values of the searched color, the RGB values of all the colors in the color dictionary constructed aforetime are compared. Then a color list is created with colors within the range of ${\pm}50$ for each R value, G value, and B value. Finally, using the Euclidean distance between the above results and the reference RGB values of the searched color, the color with the highest similarity from up to five colors becomes the final outcome. In order to evaluate the usefulness of the proposed method, we performed an experiment. In the experiment, 300 color names and corresponding color RGB values by the questionnaires were obtained. They are used to compare the RGB values obtained from four different methods including the proposed method. The average euclidean distance of CIE-Lab using our method was about 13.85, which showed a relatively low distance compared to 3088 for the case using synonym dictionary only and 30.38 for the case using the dictionary with Korean synonym website WordNet. The case which didn't use clustering method of the proposed method showed 13.88 of average euclidean distance, which implies the DBSCAN clustering of the proposed method can reduce the Euclidean distance. This research suggests a new color synonym processing method based on RGB values that combines the dictionary method with the real time synonym processing method for new color names. This method enables to get rid of the limit of the dictionary-based approach which is a conventional synonym processing method. This research can contribute to improve the intelligence of e-commerce search systems especially on the color searching feature.

• Industrial Engineering and Management Systems
• /
• v.7 no.2
• /
• pp.171-181
• /
• 2008

Home care, known also as domiciliary care, is part of the community care service that is a responsibility of the local government authorities in the UK as well as many other countries around the world. The aim is to provide the care and support needed to assist people, particularly older people, people with physical or learning disabilities and people who need assistance due to illness to live as independently as possible in their own homes. It is performed primarily by care workers visiting clients' homes where they provide help with daily activities. This paper is concerned with the dispatching of care workers to clients in an efficient manner. The optimized routine for each care worker determines a schedule to achieve the minimum total cost (in terms of distance traveled) without violating the capacity and time window constraints. A collaborative population-based meta-heuristic called Particle Swarm Optimization (PSO) is applied to solve the problem. A particle is defined as a multi-dimensional point in space which represents the corresponding schedule for care workers and their clients. Each dimension of a particle represents a care activity and the corresponding, allocated care worker. The continuous position value of each dimension determines the care worker to be assigned and also the assignment priority. A heuristic assignment scheme is specially designed to transform the continuous position value to the discrete job schedule. This job schedule represents the potential feasible solution to the problem. The Earliest Start Time Priority with Minimum Distance Assignment (ESTPMDA) technique is developed for generating an initial solution which guides the search direction of the particle. Local improvement procedures (LIP), insertion and swap, are embedded in the PSO algorithm in order to further improve the quality of the solution. The proposed methodology is implemented, tested, and compared with existing solutions for some 'real' problem instances.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.1149-1152
• /
• 2005

Detecting faces in images with complex backgrounds is a difficult task. Our approach, which obtains state of the art results, is based on a generative neural network model: the Constrained Generative Model (CGM). To detect side view faces and to decrease the number of false alarms, a conditional mixture of networks is used. To decrease the computational time cost, a fast search algorithm is proposed. The level of performance reached, in terms of detection accuracy and processing time, allows to apply this detector to a real word application: the indexation of face images on the Web.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.3
• /
• pp.568-576
• /
• 2003

This paper proposes a moving object tracking algorithm by using hierarchical search method in dynamic scenes. Proposed algorithm is based on two main steps: generation step of initial model from different pictures, and tracking step of moving object under the time-yawing scenes. With a series of this procedure, tracking process is not only stable under far distance circumstance with respect to the previous frame but also reliable under shape variation from the 3-dimensional(3D) motion and camera sway, and consequently, by correcting position of moving object, tracking time is relatively reduced. Partial Hausdorff distance is also utilized as an estimation function to determine the similarity between model and moving object. In order to testify the performance of proposed method, the extraction and tracking performance have tested using some kinds of moving car in dynamic scenes. Experimental results showed that the proposed algorithm provides higher performance. Namely, matching order is 28.21 times on average, and considering the processing time per frame, it is 53.21ms/frame. Computation result between the tracking position and that of currently real with respect to the root-mean-square(rms) is 1.148. In the occasion of different vehicle in terms of size, color and shape, tracking performance is 98.66%. In such case as background-dependence due to the analogy to road is 95.33%, and total average is 97%.