• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.6
• /
• pp.1527-1537
• /
• 2016

As increasing of smartphone penetration over the world, various mobile payment services have been emerged and fraud transactions have drastically increased. Although many financial companies have deployed security solutions to detect fraud transactions in on/off-line environment, mobile payment services still lack fraud detection solutions and researches. The mobile payment is mainly comprised of micro-payments and payment environment is different from other payments, so mobile-specialized fraud detection is needed. In this paper, we propose a FDS (Fraud Detection System) based on data mining for mobile payment services. The method of this paper is applied to the real data provided by a PG (Payment Gateway) company in Korea. The proposed FDS consists of two phases; (1) the first phase is focused on classifying transactions at high speed (2) the second is designed to detect abnormal transactions with high accuracy. We could detect 13 transactions per second with 93% accuracy rate.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.363-370
• /
• 2018

Ransomware detection has become a hot topic in computer security for protecting digital contents. Unfortunately, current signature-based and static detection models are often easily evadable by compress, and encryption. For overcoming the lack of these detection approach, we have proposed the dynamic ransomware detection system using data mining techniques such as RF, SVM, SL and NB algorithms. We monitor the actual behaviors of software to generate API calls flow graphs. Thereafter, data normalization and feature selection were applied to select informative features. We improved this analysis process. Finally, the data mining algorithms were used for building the detection model for judging whether the software is benign software or ransomware. We conduct our experiment using more suitable real ransomware samples. and it's results show that our proposed system can be more effective to improve the performance for ransomware detection.

• Journal of the HCI Society of Korea
• /
• v.12 no.3
• /
• pp.13-23
• /
• 2017

In this paper, we propose a new in-hand 3D modeling system that improves user convenience. Since traditional modeling systems are inconvenient to use, an in-hand modeling system has been studied, where an object is handled by hand. However, there is also a problem that it requires additional equipment or specific constraints to remove hands for good modeling. In this paper, we propose a contact state change detection algorithm for automatic hand removal and improved ICP algorithm that enables outlier handling and additionally uses color for accurate registration. The proposed algorithm enables accurate modeling without additional equipment or any constraints. Through experiments using real data, we show that it is possible to accomplish accurate modeling under the general conditions without any constraint by using the proposed system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.355-360
• /
• 1999

In this paper, we propose a method that optimizes the parameters of fuzzy logic controller : centers and widths of membership functions and scaling factors using genetic algorithm. Before fuzzy logic controller controls a plant in real time, first off it is optimized by genetic algorithm. We select error and error variation between reference trajectory and real output for the input signals of fuzzy controller. We compared and investigated conventional fuzzy control method and proposed method through simulation and experiment using one link manipulator with nonlinear characteristic.

• KEPCO Journal on Electric Power and Energy
• /
• v.4 no.2
• /
• pp.55-61
• /
• 2018

본 연구는 시각 동기 위상 측정 정보를 이용하여 전력계통에 나타나는 여러 가지 동요 현상을 검출하기 위한 기초 연구로써, 시계열 데이터 분석 분야로 분류된다. 제시한 방법은 비선형 동특성에 해석 기반으로 접근하여 전력계통에 나타날 수 있는 여러 동요 현상을 범용적으로 검출해 낼 수 있다. 비선형 동요 현상의 신호적 패턴을 수학적으로 기본 순시치 파형으로부터 피크치 샘플링을 통해 전개하여 계통 요소간 간섭으로 인한 원하지 않는 진동 모드를 검출하고자 한다. 계통의 변화로 진동 모드가 나타날 때, 2차원 평면에 실효치로 환산한 시계열 전압 데이터와 선형화된 플로퀘트 상수(Floquet multiplier)를 맵핑하여 도시하고, 정상상태 지점으로부터 거리를 계산하여 최대 리아프노프 지수 계산을 통해 계통이 불안정하게 되는 시간을 시계열 데이터 분석으로 추정하는 것이 본 방법의 핵심이다. 이러한 접근으로 제시한 비선형 동요 검출 알고리즘을 적용하여 디지털 필터 적용 또는 주파수 영역 해석과 같은 오프라인 Study와 달리 온라인으로 신속하게 계통의 현재 상태를 알 수 있게 된다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.158-165
• /
• 2019

Although evaluation of writing disabilities identification and timely intervention are required, clinicians adopt a manual scoring method and there is a possibility of error due to subjective evaluation. In this study, the size ratio and position of letters are digitized and quantified through image processing of offline handwritten characters. We tried to evaluate objectively and accurately the performance of writing through comparison with existing methods. From November 12th to 16th, 2018, 20 adults without neurological injury were selected. They used a pencil to follow the 10 words, 2 sentence stimuli after keeping the usual habit, and we collected the writing test data. The results showed that the height of the word was 1.2 times larger than the width and it tilted to the lower left. The spacing interval was 9mm on average. In the Paired T test, a high correlation was showed between our system and existing methods in the word and sentence 2. This demonstrated the possibility as a testing tool. This study evaluated objectively and precisely writing performance of offline handwritten characters through image processing and provided preliminary data for performance standards. In the future, it can be suggested as a basic data on writing diagnosis of various ages.

• KIISE Transactions on Computing Practices
• /
• v.23 no.2
• /
• pp.110-115
• /
• 2017

We propose a new indoor positioning algorithm named Cut-off algorithm. This algorithm cuts off candidates of beacons and reference points in advance, before looking for K neighbor reference points which are guessed to be closest to the user's actual location. The algorithm consists of two phases: off-line phase, and on-line phase. In the off-line phase, RSSI and UUID data from beacons are gathered at reference points placed in the indoor environment, and construct a fingerprint map of the data. In the on-line phase, the map is reduced to a smaller one according to the RSSI data of beacons received from the user's device. The nearest K reference points are selected using the reduced map, which are used for estimating user's location. In both phases, relative ranks of the peak signals received from each beacon are used, which smoothen the fluctuations of the signals. The algorithm is shown to be more efficient in terms of accuracy and estimating time.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.201-207
• /
• 2012

A RAM-based neural network is a weightless neural network based on binary neural network(BNN) which is efficient neural network with a one-shot learning. RAM-based neural network has multiful information bits and store counts of training in BNN. Supervised learning based on the RAM-based neural network has the excellent performance in pattern recognition but in pattern categorization with unsupervised learning as unsuitable. In this paper, we propose a unsupervised learning algorithm in the RAM-based neural network to perform pattern categorization. By the proposed unsupervised learning algorithm, RAM-based neural network create categories depending on the input pattern by itself. Therefore, RAM-based neural network for supervised learning and unsupervised learning should proof of all possible complex models. The training data for experiments provided by the MNIST offline handwritten digits which is consist of 0 to 9 multi-pattern.

• The KIPS Transactions:PartB
• /
• v.11B no.3
• /
• pp.337-344
• /
• 2004

Most of the virtual space constructed sufficiently realistic need a lot of memory space to navigate smoothly. And this kind of virtual space also requires real-time responsibility for the navigation as well as realism. In the off-line virtual system, real-time responsibility can be resolved by using large scale if secondary memory. In the web-based online virtual system, on the other hand, real-time responsibility is highly related to the latency time of network data communication. This induces the necessity of the algorithm for fast data loading. In this paper, we propose and verify the validity of the two methodology for cell leading algorithm. According to the results of computer simulation, the algorithm using hexagonal type cell promotes the real-time responsibility over 30％ than that of the rectangular type.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.12
• /
• pp.885-893
• /
• 2006

The Bayesian network(BN) has emerged in recent years as a powerful technique for handling uncertainty iii complex domains. Parameter learning of BN to find the most proper network from given data set has been investigated to decrease the time and effort for designing BN. Off-line learning needs much time and effort to gather the enough data and since there are uncertainties in real world, it is hard to get the complete data. In this paper, we propose an online learning method of Bayesian network parameters from incomplete data. It provides higher flexibility through learning from incomplete data and higher adaptability on environments through online learning. The results of comparison with Voting EM algorithm proposed by Cohen at el. confirm that the proposed method has the same performance in complete data set and higher performance in incomplete data set, comparing with Voting EM algorithm.