• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.107-113
• /
• 2021

In this paper, we conducted an empirical study to investigate whether Android app descriptions provide enough permission usages for measuring app quality in terms of human writing and consistency between code and descriptions. Android app descriptions are analyzed for various purposes such as quality measurement, functionality recommendation, and malware detection. However, many app descriptions do not disclose permission usages, whether accidentally or on purpose. Most importantly, the previous studies could not precisely analyze app descriptions if permission usages cannot be completely introduced in app descriptions. To assess the consistency between permissions and app descriptions, we implemented a state-of-the-art method to predict Android permissions for 29,270 app descriptions. As a result, 25% of app descriptions may not contain any permission semantic, and 57% of app descriptions cannot accurately reflect permission usages.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.116-123
• /
• 2021

Due to the rapid growth of the online fashion market and the resulting expansion of online choices, there is a problem that the seller cannot directly respond to a large number of consumers individually, although consumers are increasingly demanding for more personalized recommendation services. Images are being tagged as a way to meet consumer's personalization needs, but when people tagging, tagging is very subjective for each person, and artificial intelligence tagging has very limited words and does not meet the needs of users. To solve this problem, we designed an algorithm that recognizes the shape, attribute, and emotional information of the product included in the image with AI, and codes this information to represent all the information that the image has with a combination of codes. Through this algorithm, it became possible by acquiring a variety of information possessed by the image in real time, such as the sensibility of the fashion image and the TPO information expressed by the fashion image, which was not possible until now. Based on this information, it is possible to go beyond the stage of analyzing the tastes of consumers and make hyper-personalized clothing recommendations that combine the tastes of consumers with information about trends and TPOs.

• Journal of The Korean Association of Information Education
• /
• v.26 no.3
• /
• pp.197-207
• /
• 2022

In this paper, we develop a machine learning based block code generation and recommendation model for the purpose of reducing cognitive load of learners during coding education that learns the learner's block that has been made in the block programming environment using natural processing model and fine-tuning and then generates and recommends the selectable blocks for the next step. To develop the model, the training dataset was produced by pre-processing 50 block codes that were on the popular block programming language web site 'Entry'. Also, after dividing the pre-processed blocks into training dataset, verification dataset and test dataset, we developed a model that generates block codes based on LSTM, Seq2Seq, and GPT-2 model. In the results of the performance evaluation of the developed model, GPT-2 showed a higher performance than the LSTM and Seq2Seq model in the BLEU and ROUGE scores which measure sentence similarity. The data results generated through the GPT-2 model, show that the performance was relatively similar in the BLEU and ROUGE scores except for the case where the number of blocks was 1 or 17.

• Computers and Concrete
• /
• v.21 no.1
• /
• pp.11-20
• /
• 2018

The possibilities of non-linear analysis of reinforced-concrete structures are under development. In particular, current research areas include structural analysis with the application of advanced computational and material models. The submitted article aims to evaluate the possibilities of the determination of material properties, involving the tensile strength of concrete, fracture energy and the modulus of elasticity. To evaluate the recommendations for concrete, volume computational models are employed on a comprehensive series of tests. The article particularly deals with the issue of the specific properties of fracture-plastic material models. This information is often unavailable. The determination of material properties is based on the recommendations of Model Code 1990, Model Code 2010 and specialized literature. For numerical modelling, the experiments with the so called "classic" concrete beams executed by Bresler and Scordelis were selected. It is also based on the series of experiments executed by Vecchio. The experiments involve a large number of reinforcement, cross-section and span variants, which subsequently enabled a wider verification and discussion of the usability of the non-linear analysis and constitutive concrete model selected.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1165-1177
• /
• 2017

Many developers utilize specific APIs to develop software, and to identify the use of a particular API, a developer can refer to a website that provides the API or can retrieve the API from the web. However, the site that provides the API does not necessarily provide guidance on how to use it while it can be partially provided in many other cases. In this paper, we propose a novel system JACE (Java AST collocation-pattern extractor) as a method to reuse commonly-used code as a supplement. The JACE extracts the API call nodes, collocation patterns and analyzes the relations between the collocations to extract significant API patterns from the source code. The following experiment was performed to verify the accuracy of a defined pattern: 794 open source projects were analyzed to extract about 15M API call nodes. Then, the Eclipse plug-in test program was utilized to retrieve the pattern using the top 10 classes of API call nodes. Finally, the code search results from reference pages of the API classes and the Searchcode [1] were compared with the test program results.

• Journal of Intelligence and Information Systems
• /
• v.13 no.4
• /
• pp.65-78
• /
• 2007

This paper proposes a new method of weighted template matching for machine-printed numeral recognition. The proposed weighted template matching, which emphasizes the feature of a pattern using adaptive Hamming distance on local feature areas, improves the recognition rate while template matching processes an input image as one global feature. Template matching is vulnerable to random noises that generate ragged outlines of a pattern when it is binarized. This paper offers a method of chain code trimming in order to remove ragged outlines. The method corrects specific chain codes within the chain codes of the inner and the outer contour of a pattern. The experiment compares confusion matrices of both the template matching and the proposed weighted template matching with chain code trimming. The result shows that the proposed method improves fairly the recognition rate of the machine-printed numerals.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2010.05a
• /
• pp.115-116
• /
• 2010

To research the fragility of exterior joints of RC frame building which are not designed to seismic design code, four T shaped beam-column subassemblies are designed and tested with displacement control until to reach 3.5% story drift. From the results, the non-seismic detailed specimen failed in exterior joint before to reach to 1.0% drift, which is far less than the recommendation value of FEMA 356 and their strengths are less than 0.85 times of the nominal flexural strength.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.577-578
• /
• 2016

QR 코드를 이용한 접촉 매체를 이용해 본 경험자 중 대부분은 스마트폰을 사용한 것으로 나타났으며, 해당 접촉 매체 중 가장 높은 이용 비율을 나타낸 매체는 홍보용 전단지나 브로슈어 등 이다. 이와 같이 스마트폰의 보급에 따른 QR 코드의 이용 범위가 마케팅 분야에 집중되면서 효율적인 이용 방법에 대한 연구가 증가하고 있는 추세이다. 본 연구에서는 QR 코드에 저장된 음식에 대한 상세 정보를 활용한 모바일 웹 기반의 음식 추천을 위한 개인화 서비스 시스템을 제안한다.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.12
• /
• pp.173-178
• /
• 2016

In this paper many discussions are raised regarding the outside director system in order to establish the position of the outside director within institutional organizations and to review ways to activate the outside director system in for-Profit Hospital. it seems to be more desirable in Korea for each company to establish an efficient system by itself in accordance with suggested guidelines suitable for each for-Profit Hospital management circumstances rather than to apply a unilateral outside director system to for-Profit Hospital through legalization. In this regard, while keeping the current outside director system for the time being, it is necessary to review and improve the management status of companies and the usefulness of the system, and various recommendations from lawyer associations, Hospital business associations, and academia should be allowed rather than just for-Profit Hospital recommendation by the government.

• Journal of Satellite, Information and Communications
• /
• v.1 no.2
• /
• pp.51-55
• /
• 2006

Digital satellite communication systems are usually integrated with terrestrial systems to provide various services. In these cases, they should satisfy the performance objectives defined by the terrestrial systems. Recommendation ITU-R S.1062 specifies the error performance objectives of digital satellite communication systems operating below 15 GHz. The error performance are given in terms of bit error probability divided by the number of the average bit errors in the burst ($\alpha$). This paper presents a theoretical method to estimate $\alpha$ that is a very important parameter in the satellite communication systems to analyze the error performance objectives. We show performance estimation result of DVB-RCS turbo code using the presented method, and verify them by comparing to the simulation results.