• KIISE Transactions on Computing Practices
• /
• v.23 no.3
• /
• pp.183-187
• /
• 2017

Smart phone users prefer fast reading and texting. Hence, users frequently use abbreviated sequences of words and phrases. Nowadays, abbreviations are widely used from chat terms to technical terms. Therefore, gathering abbreviations would be helpful to many services, including information retrieval, recommendation system, and so on. However, manually gathering abbreviations needs to much effort and cost. This is because new abbreviations are continuously generated whenever a new material such as a TV program or a phenomenon is made. Thus it is required to generate of abbreviations automatically. To generate Korean abbreviations, the existing methods use the rule-based approach. The rule-based approach has limitations, in that it is unable to generate irregular abbreviations. Another problem is to decide the correct abbreviation among candidate abbreviations generated rules. To address the limitations, we propose a method of generating Korean abbreviations automatically using sequence-to-sequence learning in this paper. The sequence-to-sequence learning can generate irregular abbreviation and does not lead to the problem of deciding correct abbreviation among candidate abbreviations. Accordingly, it is suitable for generating Korean abbreviations. To evaluate the proposed method, we use dataset of two type. As experimental results, we prove that our method is effective for irregular abbreviations.

• Korean Journal of Cognitive Science
• /
• v.27 no.1
• /
• pp.27-41
• /
• 2016

Named entity recognition is to classify elements in text into predefined categories and used for various departments which receives natural language inputs. In this paper, we propose a method which can generate named entity training corpus automatically using knowledge bases. We apply two different methods to generate corpus depending on the knowledge bases. One of the methods attaches named entity labels to text data using Wikipedia. The other method crawls data from web and labels named entities to web text data using Freebase. We conduct two experiments to evaluate corpus quality and our proposed method for generating Named entity recognition corpus automatically. We extract sentences randomly from two corpus which called Wikipedia corpus and Web corpus then label them to validate both automatic labeled corpus. We also show the performance of named entity recognizer trained by corpus generated in our proposed method. The result shows that our proposed method adapts well with new corpus which reflects diverse sentence structures and the newest entities.

• The Journal of Korean Association of Computer Education
• /
• v.23 no.4
• /
• pp.49-59
• /
• 2020

At the beginning of the discussion of AI education in K-12 education, the study was conducted to develop and apply an AI education program based on Design Thinking and analyze the effects of the AI education programs. In the AI education program, students explored and defined the AI problems they were interested in, gathered the necessary data to build an AI model, and then developed a project using scratch. In order to analyze the effectiveness of the AI education program, the change of learner's perception of the value of AI and the change of AI efficacy were analyzed. The overall perception of the AI project was also analyzed. As a result, AI efficacy was significantly increased through the experience of carrying out the project according to the Design Thinking process. In addition, the efficacy of solving problems with AI was influenced by the level of use of programming languages. The learner's overall perception of the AI project was positive, and the perceptions of each stage of the AI project (AI problem understanding and problem exploration, practice, problem definition, problem solving idea implementation, evaluation and presentation) was also positive. This positive perception was higher among students with high level of programming language use. Based on these results, the implications for AI education were suggested.

• Journal of the Korean Society for Library and Information Science
• /
• v.39 no.1
• /
• pp.147-166
• /
• 2005

The purpose of this study is to redefine the concept and scope of universal service and to develop universal service policy of South Korea for Korean reunification. The basic assumption of this study is that well developed universal service may contribute to the eventual reunification by ensuring equal access to information resources for the two peoples. The theoretical foundation of this study includes social capital and diffusion of innovations theory. This study uses policy analysis as both data collection and data analysis, more specifically qualitative policy analysis with triangulation for improving credibility. Data for the analysis were collected through legislation, other policy documents, and major agreements between North and South Korea related to informatization and unification. This study, identified the major characteristics of universal service and explored the current universal service in South Korea by analyzing major poicy instruments of South Korea. In addition, this study presented a great possibility of cooperating in telecommunication policy and telecommunication infrastructure. Consequently, this study proposed policy recommendations in five areas: 1) redefining the scope of universal service, 2) developing a unified telecommunication infrastructure, 3) developing policy instruments, 4) restructuring government organizations, and 5) creating a participatory universal service model for Korean reunification.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.829-835
• /
• 2018

Recently, studies have been actively conducted to reduce spare power that is unnecessarily generated or wasted in existing power systems and to improve energy use efficiency. In this study, smart meter, which is one of the element technologies of smart grid, is implemented to improve the efficiency of energy use by controlling power of electric devices, and predicting trends of energy usage based on deep learning. We propose and develop an algorithm that controls the power of the electric devices by comparing the predicted power consumption with the real-time power consumption. To verify the performance of the proposed smart meter based on the deep running, we constructed the actual power consumption environment and obtained the power usage data in real time, and predicted the power consumption based on the deep learning model. We confirmed that the unnecessary power consumption can be reduced and the energy use efficiency increases through the proposed deep learning-based smart meter.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.36-41
• /
• 2017

The mobile mapping system first introduced at Ohio State University in 1991 is being developed in various forms as sensor technology develops. The mobile mapping system can acquire geospatial information around amoving object quickly using the information gathered using the position and attitude information of the moving object and the data from various sensors. The mobile mapping system can rapidly acquire large amounts of Geospatial information and MMS provides maximum productivity in the same measurement methods as existing GNSS and total stations. Currently, a variety of systems are being launched, mainly by foreign companies, and they are applied to the construction of geospatial information. On the other hand, the application of domestic technology development or production is insufficient. This paper provides basic data for the introduction of a mobile mapping system to geospatial information related business by conducting the status survey and feature analysis of a commercialized system focusing on the ground-based mobile mapping system. The research identified the current status and characteristics of high-priced, low-priced, indoor, and handheld mobile mapping systems based on vehicles and suggest that the recent system development trends are moving toward lowering the unit prices. The mobile mapping system is currently being developed as a platform for the application of geospatial information construction and the launch of low-cost models. The development of data processing technologies, such as automatic matching and the launch of low-cost models, are forming a basis for the application of mobile mapping systems in the field of geospatial information construction.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.1
• /
• pp.16-24
• /
• 2000

In this paper the performance of a closed-loop power control scheme using variable step size decision method for DS/CDMA based-low earth orbit(LEO) mobile satellite systems in which the long round trip delay is a dominant performance degradation factor is evaluated. Because there are fundamental differences in the characteristics between the LEO mobile satellite channel and terrestrial mobile channel, such as long round trip delay and different elevation angle, these factors are considered in channel modeling based on the European Space Agency(ESA) measurement data. Since the round trip delay (from the mobile terminal to the gateway station via satellite) is typically 10∼20ms in low altitude satellite channels, closed-loop power control is much less effective than it is on a terrestrial channel. Thus, the adaptive power control scheme using a variable step size control is essential for overcoming the long round trip delay and fading due to the elevation angle. It is shown that the standard deviation of signal to interference ratio(SIR) adopting a variable step size closed-loop power control scheme is much less than that of a fixed step size closed-loop power control. Furthermore, we have driven the conclusion that the measurement interval of power control commands is optimal choice when it is twice the round trip delay.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.3
• /
• pp.556-563
• /
• 2020

Most of a BIPVS (Building Integrated Photovoltaic System) is installed on the rooftop or wall of a building. Therefore, the main factor to consider for selecting the installation site is the shadow effects produced by the surrounding buildings. On the other hand, when the photovoltaic was installed on soundproof walls, shadow effects were produced by not only surrounding buildings but also the surrounding trees. Therefore, a different data model and algorithm with the BIPVS case are essential for proper installation sites selection of a SIPVS (Soundproof wall Integrated Photovoltaic System). This paper deals with the DSM (Digital Surface Model)-based proper installation site analysis for SIPVS. First, the solar incident and altitude angles of the installation candidate sites (solar panel) during the year were calculated. Second, the shadow effects (shadowed or unshadowed) were determined for the candidate sites at each time with the DSM. Third, the amount of solar radiation was calculated with the incident angle for the candidate sites at an unshadowed period. The proper installation site of the SIPVS could then be selected by comparing the accumulated annual solar radiation for each candidate. The proposed algorithm was implemented as a prototype (Java program). From the experiment, the order of the installation suitability was determined among the nine candidates. The proposed algorithm could be used for proper BIPVS installation site analysis aimed at the lower part of a building and calculation of the expected power production.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.5
• /
• pp.219-230
• /
• 2017

General-Purpose Graphics Processing Units (GPGPUs) build massively parallel architecture and apply multithreading technology to explore parallelism. By using programming models like CUDA, and OpenCL, GPGPUs are becoming the best in exploiting plentiful thread-level parallelism caused by parallel applications. Unfortunately, modern GPGPU cannot efficiently utilize its available hardware resources for numerous general-purpose applications. One of the primary reasons is the inefficiency of existing warp/thread block schedulers in hiding long latency instructions, resulting in lost opportunity to improve the performance. This paper studies the effects of hardware thread scheduling policy on GPGPU performance. We propose a novel warp scheduling policy that can alleviate the drawbacks of the traditional round-robin policy. The proposed warp scheduler first classifies the warps of a thread block into two groups, warps with long latency and warps with short latency and then schedules the warps with long latency before the warps with short latency. Furthermore, to support the proposed warp scheduler, we also propose a supplemental technique that can dynamically reduce the number of streaming multiprocessors to which will be assigned thread blocks when encountering a high contention degree at the memory and interconnection network. Based on our experiments on a 15-streaming multiprocessor GPGPU platform, the proposed warp scheduling policy provides an average IPC improvement of 7.5% over the baseline round-robin warp scheduling policy. This paper also shows that the GPGPU performance can be improved by approximately 8.9% on average when the two proposed techniques are combined.

• Journal of KIISE:Software and Applications
• /
• v.28 no.9
• /
• pp.688-698
• /
• 2001

A homonym could be disambiguated by anther words in the context such as nouns, predicates used with the homonym. This paper proposes a homonym disambiguation system based on statistical semantic information which is extracted from definitions in dictionary. The semantic information consists of nouns and predicates that are used with the homonym in definitions. In order to extract accurate semantic information, definitions are used with the homonym in definitions. In order to extract accurate semantic information, definitions are classified into two types. One has hyponym-hypernym relation between title word and head word (homonym) in definition. The hyponym-hypernym relation is one level semantic hierarchy and can be extended to deeper levels in order to overcome the problem of data sparseness. The other is the case that the homonym is used in the middle of definition. The system considers nouns and predicates simultaneously to disambiguate the homonym. Nine homonyms are examined in order to determine the weight of nouns and predicates which affect accrutacy of homonym disambiguation. From experiments using training corpus(definitions in dictionary), the average accruracy of homonym disamguation is 96.11% when the weight is 0.9 and 0.1 for noun and verb respectively. And another experiment to meaure the generality of the homonym disambiguation system results in the 80.73% average accuracy to 1,796 untraining sentences from Korean Information Base I and ETRI corpus.