• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1499-1508
• /
• 2018

Although fast-growing e-commerce markets gave a lot of companies opportunities to expand their customer bases, it is also the case that there are growing number of cases in which the so-called 'black consumers' cause much damage on many companies. In this study, we will implement and optimize a machine learning model that detects black consumers using customer data from e-commerce store. Using filter method for feature selection and 4 different algorithms for classification, we could get the best-performing machine learning model that detects black consumer with F-measure 0.667 and could also yield improvements in performance which are 11.44% in F-measure, 10.51% in AURC, and 22.87% in TPR.

• Communications of the Korean Mathematical Society
• /
• v.19 no.4
• /
• pp.643-660
• /
• 2004

In this paper, we give a new formula between the conditional Wiener integral E(F｜X), the conditional Wiener integral of F given X, and the integral with respect to a measure-valued measure, a kind of Bartle integral. Using this formula, we give some examples of evaluation of E(F｜X).

• Journal of Broadcast Engineering
• /
• v.20 no.3
• /
• pp.449-463
• /
• 2015

Video object tracking is important for variety of applications, such as security, video indexing and retrieval, video surveillance, communication, and compression. This paper proposes an object tracking method in HEVC bitstreams. Without pixel reconstruction, motion vector (MV) and size of prediction unit in the bitstream are employed in an Spatio-Temporal Markov Random Fields (ST-MRF) model which represents the spatial and temporal aspects of the object's motion. Coefficient-based object shape adjustment is proposed to solve the over-segmentation and the error propagation problems caused in other methods. In the experimental results, the proposed method provides on average precision of 86.4%, recall of 79.8% and F-measure of 81.1%. The proposed method achieves an F-measure improvement of up to 9% for over-segmented results in the other method even though it provides only average F-measure improvement of 0.2% with respect to the other method. The total processing time is 5.4ms per frame, allowing the algorithm to be applied in real-time applications.

• The Journal of the Korea Contents Association
• /
• v.13 no.11
• /
• pp.37-47
• /
• 2013

Recently, lots of research results on program comparison have been reported since the code theft become frequent as the increase of code mobility. This paper proposes a plagiarism detection method using class structures. The proposed method constructs a graph representing the referential relationship between the member variables and the methods. This relationship is shown as a bipartite graph and the test for graph isomorphism is applied on the set of graphs to measure the similarity of the programs. In order to measure the effectiveness of this method, an experiment was conducted on the test set, the set of Java source codes submitted as solutions for the programming assignments in Object-Oriented Programming course of Pusan National University in 2012. In order to evaluate the accuracy of the proposed method, the F-measure is compared to those of JPlag and Stigmata. According to the experimental result, the F-measure of the proposed method is higher than those of JPlag and Stigmata by 0.17 and 0.34, respectively.

• Journal of the Chungcheong Mathematical Society
• /
• v.32 no.4
• /
• pp.461-464
• /
• 2019

In this article, we consider that if a continuous map f : X → X of a compact metric space X is Li-York chaotic then it is positively weak measure expansive.

• Journal of the Korean Mathematical Society
• /
• v.54 no.2
• /
• pp.697-711
• /
• 2017

Let X, Y be real normed vector spaces. We exhibit all the solutions $f:X{\rightarrow}Y$ of the functional equation f(rx + sy) + rsf(x - y) = rf(x) + sf(y) for all $x,y{\in}X$, where r, s are nonzero real numbers satisfying r + s = 1. In particular, if Y is a Banach space, we investigate the Hyers-Ulam stability problem of the equation. We also investigate the Hyers-Ulam stability problem on a restricted domain of the following form ${\Omega}{\cap}\{(x,y){\in}X^2:{\parallel}x{\parallel}+{\parallel}y{\parallel}{\geq}d\}$, where ${\Omega}$ is a rotation of $H{\times}H{\subset}X^2$ and $H^c$ is of the first category. As a consequence, we obtain a measure zero Hyers-Ulam stability of the above equation when $f:\mathbb{R}{\rightarrow}Y$.

• Journal of the Chungcheong Mathematical Society
• /
• v.7 no.1
• /
• pp.59-67
• /
• 1994

Let (${\Omega},{\Sigma},{\mu}$) be a measure space. A function $f:{\Omega}{\rightarrow}X$ is said to be equioscillated if for each set $A{\in}{\Sigma}$ of positive measure and for each ${\epsilon}$ > 0, there is a measurable subset B of A of positive measure such that the inequality s$sup_{{\omega}{\in}B}x^*f({\omega})-inf_{{\omega}{\in}B}x^*f({\omega})$ < ${\epsilon}$ holds for every $x^*$ with $||x^*||{\leq}1$. Strong measurability of a vector valued function is characterized using equioscillation.

• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.87-91
• /
• 2009

전문용어의 수가 급증하면서 전문용어를 자동으로 인식하는 연구가 활발히 진행되고 있다. 전문용어를 인식하기 위해서 전문용어의 범위를 정한 뒤 그 전문용어의 분야를 선택해야 한다. 본 논문에서는 생물/의학 사전정보와 CRF(Conditional Random Fields) 기계학습 기법을 사용하여 연구를 진행한다. 기계학습을 위한 자질로 품사, 접사, 대소문자, 숫자, 특수문자, 단서어휘 등을 사용한다. 특히 단서어휘와 사전정보를 중요한 요소로 생각하여, 3가지 방법으로 나누어 실험한다. 총 분야의 개수는 7개이며, 각 분야별로 정확률, 재현율, F-measure를 측정한다. 경계인식은 83.92%의 정확률, 96.42%의 재현율, 89.73의 F-measure가 결과로 나타났고, 분야분류는 79.29%의 정확률, 91.06%의 재현율, 84.77%의 F-measure가 결과로 나타났다.

• Bulletin of the Korean Mathematical Society
• /
• v.36 no.2
• /
• pp.287-303
• /
• 1999

The general solution of the functional equation f1(pr, qs) + f2(ps, qr) = g(p,q) + h(r,s) for p, q, r, s $\in$] 0, 1[will be investigated without any regularity assumptions on the unknown functions f1, f2, g, h:]0.1[->R.

• Journal of the Korean Society of Costume
• /
• v.25
• /
• pp.233-247
• /
• 1995

The objectives of this study were to classify the contents of clothing involvement, to group elderly women into life style types. A method of this study was face to face re-search and questionnaire. Questionnaire was comprised of four sections : 18 Likert type items of clothing involvement measure ; 26 Likert type items of life style measure ; 3 items of clothing purchase measure ; and 3 demographic variables. Samples were 215 elderly women(60∼79 years of age) in Seoul, Korea. The data were analyzed using factor analy-sis, cluster analysis, one-way ANOVA, Dun-can's multiple range test,χ2 test. The results of the study were the follow-ings. 1. Four factors of clothing involvement derived by factor analysis : F.1 'clothing pleasure'; F.2 'clothing symbolism' ; F.3 'perceived risk in clothing purchase' ; F.4 'clothing interest'. 2. Four factors of life style derived by factor analysis : F.1 'active-leisure';F.2 'confidence oriented';F.3 'appearance interest';F.4 'house-work interest and community conciousness'. Three types of life style were defined by the cluster analysis of the 4 factors : T.1 'passive stag-nation'; T.3'outside activity'. 3. There were significant differences in clothing involvement factors according to life style types. Outside activity type perceived 'clothing pleasure' highest level among 3 life style types. Outside activity type and house-work and positive living type perceived 'cloth-ing symbolism' and 'clothing interest' higher level than did passive stagnation types. 4. Elderly women high in educational level were more distributed in outside activity type and the low in educational level in passive stagnation types. 5. There were significant relationships be-tween life style types and source of a clothing allowance, clothing purchase frequency, and a companion of dress store.