• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1187-1190
• /
• 2015

최근에 비정형 데이터의 잠재적 가치를 유용한 데이터로써 사용하려는 경우가 많아지고 있다. 특히 트위터는 사용자의 상태나 이벤트가 잘 나타나 있어서 하나의 사용자의 이벤트로서 간주될 수 있다. 본 논문은 트위터에서 발생하는 이벤트에 주목하여, 감기라는 이벤트를 트위터 내에서 추적하고자 한다. 추적을 위해서는 트위터를 판단할 필요가 있는데, 이를 위해 기존의 감성 사전 방식 중 하나인 통계적 사전 구축을 기반으로 키워드를 활용하여 감기 판단 사전을 구축하는 방식을 제안한다.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.111-115
• /
• 2023

Knowledge Based Authentication is the most well-known technique for user authentication in a computer security framework. Most frameworks utilize a straightforward PIN (Personal Identification Number) or psssword as an data authenticator. Since password based authenticators typically will be software based, they are inclined to different attacks and weaknesses, from both human and software.Some of the attacks are talked about in this paper.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.1
• /
• pp.85-90
• /
• 2018

The new information service has been demanded due to the recent mobile internet activation, and the government is promoting the activation of the private use of the public data by putting up the Government 3.0. According to government policy, many public sectors provide public data, but the railway sector is inferior to other public sector. In the case of national railway corporation, urban railway is now operated by 14 corporations such as Seoul Metro through the nation and high-speed railway is now operated by Korea Railroad Corporation and Supreme Railways. It is very difficult to standardize and integrate data due to mutual interests of national railway corporation. This paper describes a way to standardize and integrate rail passengers information collected through research project.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.59-70
• /
• 2024

We introduce a high-performance named entity recognition (NER) model for written and spoken language. To overcome challenges related to labeled data scarcity and domain shifts, we use transfer learning to leverage our previously developed KorBERT as the base model. We also adopt a meta-pseudo-label method using a teacher/student framework with labeled and unlabeled data. Our model presents two modifications. First, the student model is updated with an average loss from both human- and pseudo-labeled data. Second, the influence of noisy pseudo-labeled data is mitigated by considering feedback scores and updating the teacher model only when below a threshold (0.0005). We achieve the target NER performance in the spoken language domain and improve that in the written language domain by proposing a straightforward rollback method that reverts to the best model based on scarce human-labeled data. Further improvement is achieved by adjusting the label vector weights in the named entity dictionary.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.3
• /
• pp.15-20
• /
• 1999

This paper presents a climate change information system that provides the data and information about climate change. The system shows the meteorologic data observed, climate change research institutes, and research programs. As the result of analyzing the meteorologic data, it also provides users with the climate change information using the graphic and multimedia data. The terminology retrieval and dictionary facility in the climate change can be useful to the users who are interested in the climate change.

• Journal of Korean Academy of Nursing
• /
• v.29 no.1
• /
• pp.21-33
• /
• 1999

This study was designed to develop a basic plan for computerization of nursing records. The subjects were 7 nursing record forms, 58 charts, 23 nurses, 2 nurse managers, a nurse and computer specialist, 16 master course students and 3 professors. Data collection was conducted through questionnaire, observation and interview. The collected data were analyzed for problems, plan of improvement and needs for computerization. Based upon these results, it is recommended that nursing record computerization was needed a basic plan to integrate needs of nursing record computerization. The basic plan as fellows : 1. To illustrate a data flow path of nursing record and data dictionary that show nurse's work and record process. 2. To establish a system in order to use multi -tasking and graphic user interface. 3. To establish hardware and software in order to embody integrated management of computer based system through structured walkthrough. 4. To choose effective database management system and to achieve Log as record unit.

• Journal of the Korea Computer Graphics Society
• /
• v.22 no.3
• /
• pp.21-29
• /
• 2016

Cell segmentation is an important but time-consuming and laborious task in biological image analysis. An automated, robust, and fast method is required to overcome such burdensome processes. These needs are, however, challenging due to various cell shapes, intensity, and incomplete boundaries. A precise cell segmentation will allow to making a pathological diagnosis of tissue samples. A vast body of literature exists on cell segmentation in microscopy images [1]. The majority of existing work is based on input images and predefined feature models only - for example, using a deformable model to extract edge boundaries in the image. Only a handful of recent methods employ data-driven approaches, such as supervised learning. In this paper, we propose a novel data-driven cell segmentation algorithm for bright-field microscopy images. The proposed method minimizes an energy formula defined by two dictionaries - one is for input images and the other is for their manual segmentation results - and a common sparse code, which aims to find the pixel-level classification by deploying the learned dictionaries on new images. In contrast to deformable models, we do not need to know a prior knowledge of objects. We also employed convolutional sparse coding and Alternating Direction of Multiplier Method (ADMM) for fast dictionary learning and energy minimization. Unlike an existing method [1], our method trains both dictionaries concurrently, and is implemented using the GPU device for faster performance.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.2
• /
• pp.353-378
• /
• 2014

The purpose of this study is to find factors to affect on the formation of semantic relation from terminology and what is to be affected by these factors to build the database scheme of terminology dictionary by a structural definition. In this research, 826,905 keywords of 88,874 social science articles and 985,580 keywords of 125,046 humanities science articles in the KCI journals from 2007 to 2011 were collected. From collected data, subject complexity, structural hole, term frequency, occurrence pattern and an effect between the number of nodes and the number of patterns which were derived from the semantic relation of linked terms of established 'STNet' System were analyzed. The summarized results from analyzed data and network patterns are as follows. Betweenness Centrality, term frequency, and effective size affect the numbers of semantic relation node. Among these factors, betweenness centrality was the most effective and effective size. But term frequency was the least effective. Betweenness Centrality, term frequency, and effective size affect the numbers of semantic relation type. Term frequency is the most effective. Therefore, when building a terminology dictionary, factors of betweenness centrality, term frequency, effective size, and complexity of subject are needed to select term. As a result, these factors can be expected to improve the quality of terminology dictionary.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.1-21
• /
• 2016

IT-based subjective well-being (SWB) services, a main part of wellness IT, should measure the SWB state of individuals in an unrestrained, cost-effective manner. The dictionaries for sentiment analysis available in the market may be useful for this purpose, but obtaining proper sentiment values using only words from the sentiment lexicon is impossible; therefore, a new dictionary including wellness vocabulary is needed. The existing sentiment dictionaries link only a single sentiment value to a single sentiment word, although sentiment values may vary depending on personal traits. In this study, we develop an extended version of the SenticNet sentiment dictionary dubbed WellnessWordNet. SenticNet is considered the best and most expressive among the already existing sentiment dictionaries. Using the information provided by SenticNet, we created a database including the wellness states (estimated values) of stress, depression, and anger to develop the WellnessWordNet system. The accuracy of the system was validated through actual tests with live subjects. This study is unique and unprecedented in that i) an extended sentiment dictionary, WellnessWordNet, is developed; ii) values for wellness state language are offered; and iii) different sentiment values, namely contextual polarity, for people of the same gender or age group are suggested.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1161-1167
• /
• 2018

The development of machine learning has enabled machines to perform delicate tasks that only humans could do, and thus many companies have introduced machine learning based translators. Existing translators have good performances but they have problems in number translation. The translators often mistranslate numbers when the input sentence includes a large number. Furthermore, the output sentence structure completely changes even if only one number in the input sentence changes. In this paper, first, we optimized a neural machine translation model architecture that uses bidirectional RNN, LSTM, and the attention mechanism through data cleansing and changing the dictionary size. Then, we implemented a number-processing algorithm specialized in number translation and applied it to the neural machine translation model to solve the problems above. The paper includes the data cleansing method, an optimal dictionary size and the number-processing algorithm, as well as experiment results for translation performance based on the BLEU score.