• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.200-206
• /
• 2021

Fraud in e-commerce transaction increased in the last decade especially with the increasing number of online stores and the lockdown that forced more people to pay for services and groceries online using their credit card. Several machine learning methods were proposed to detect fraudulent transaction. Neural networks showed promising results, but it has some few drawbacks that can be overcome using optimization methods. There are two categories of learning optimization methods, first-order methods which utilizes gradient information to construct the next training iteration whereas, and second-order methods which derivatives use Hessian to calculate the iteration based on the optimization trajectory. There also some training refinements procedures that aims to potentially enhance the original accuracy while possibly reduce the model size. This paper investigate the performance of several NN models in detecting fraud in e-commerce transaction. The backpropagation model which is classified as first learning algorithm achieved the best accuracy 96% among all the models.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.214-222
• /
• 2021

Recently, the growth of e-commerce in Saudi Arabia has been exponential, bringing new remarkable challenges. A naive approach for product matching and categorization is needed to help consumers choose the right store to purchase a product. This paper presents a machine learning approach for product matching that combines deep learning techniques with standard artificial neural networks (ANNs). Existing methods focused on product matching, whereas our model compares products based on unstructured descriptions. We evaluated our electronics dataset model from three business-to-consumer (B2C) online stores by putting the match products collectively in one dataset. The performance evaluation based on k-mean classifier prediction from three real-world online stores demonstrates that the proposed algorithm outperforms the benchmarked approach by 80% on average F1-measure.

• International Journal of Advanced Culture Technology
• /
• 제9권1호
• /
• pp.218-223
• /
• 2021

Pervasive enhancement and required enforcement of the Internet of Things (IoTs) in a distributed massively multiplayer online architecture have effected in massive growth of Big-Data in terms of server over-load. There have been some previous works to overcome the overloading of server works. However, there are lack of considered methods, which is commonly applicable. Therefore, we propose a combing Sparse Auto-Encoder and Load-Balancing, which is ProGReGA for Big-Data of server loads. In the process of Sparse Auto-Encoder, when it comes to selection of the feature-pattern, the less relevant feature-pattern could be eliminated from Big-Data. In relation to Load-Balancing, the alleviated degradation of ProGReGA can take advantage of the less redundant feature-pattern. That means the most relevant of Big-Data representation can work. In the performance evaluation, we can find that the proposed method have become more approachable and stable.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권2호
• /
• pp.109-118
• /
• 2022

Workers' anomalous trajectories allow us to detect emergency situations in the workplace, such as accidents of workers, security threats, and fire. In this work, we develop a scheme to detect abnormal trajectories of workers using the edit distance on real sequence (EDR) and density method. Our anomaly detection scheme consists of two phases: offline phase and online phase. In the offline phase, we design a method to determine the algorithm parameters: distance threshold and density threshold using accumulated trajectories. In the online phase, an input trajectory is detected as normal or abnormal. To achieve this objective, neighbor density of the input trajectory is calculated using the distance threshold. Then, the input trajectory is marked as an anomaly if its density is less than the density threshold. We also evaluate performance of the proposed scheme based on the MIT Badge dataset in this work. The experimental results show that over 80 % of anomalous trajectories are detected with a precision of about 70 %, and F1-score achieves 74.68 %.

• 한국군사과학기술학회지
• /
• 제25권1호
• /
• pp.72-81
• /
• 2022

Maritime patrol aircraft is an efficient solution for detecting submarines at sea. The aircraft can only detect submarines by sonobuoy, but the number of buoy is limited. In this paper, we present the online sonobuoy deployment method for estimating the location of submarines. We use Gaussian process regression to estimate the submarine existence probability map, and Bayesian optimization to decide the next best position of sonobuoy. Further, we show the performance of the proposed method by simulation.

• 디지털산업정보학회논문지
• /
• 제19권3호
• /
• pp.165-175
• /
• 2023

Boryeong Mud Festival has become a representative local festival that both domestic and foreign tourists can enjoy together. In addition, it is one of the usual hands-on marine festivals in Korea that can be enjoyed with one mind at the Boryeong Mud Festival, regardless of race, age, and language. This study explored the overall perception and trends of the Boryeong Mud Festival using big data extracted online from the Boryeong Mud Festival. First, keywords such as Chungnam, hosting, summer, reporter, experience, opening ceremony, performance, operation, news, tourist, opening, event, and festival were frequently exposed online. Second, due to centrality analysis, the centrality of festival experience programs and performances, opening ceremonies, and Boryeong mayor was high. Third, due to the CONCOR analysis, five clusters of meaningful keywords related to the Boryeong Mud Festival were formed.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.453-455
• /
• 2021

코로나19의 장기화로 인해 온라인학습은 선택이 아닌 필수 학습으로 자리잡고 있다. 이러한 현실에서 수동적인 동영상 시청에 의지한 온라인 학습 방법은 학생들의 학력 저하 및 낮은 학습 성취도라는 한계점을 가지고 있다. 본 연구에서는 이러한 한계점을 극복하기 위해 PBL 교수법에 PSC-Note를 수업에 적용하여 학습자의 문제해결능력과 자기주도적 학습능력을 향상시키고 또한 학습 성취도를 높이고자 한다.

• Smart Structures and Systems
• /
• 제14권6호
• /
• pp.1247-1267
• /
• 2014

Real-Time Hybrid Simulation (RTHS) is a novel approach conceived to evaluate dynamic responses of structures with parts of a structure physically tested and the remainder parts numerically modelled. In RTHS, delay estimation is often a precondition of compensation; nonetheless, system delay may vary during testing. Consequently, it is sometimes necessary to measure delay online. Along these lines, this paper proposes an online delay estimation method using least-squares algorithm based on a simplified physical system model, i.e., a pure delay multiplied by a gain reflecting amplitude errors of physical system control. Advantages and disadvantages of different delay estimation methods based on this simplified model are firstly discussed. Subsequently, it introduces the least-squares algorithm in order to render the estimator based on Taylor series more practical yet effective. As a result, relevant parameter choice results to be quite easy. Finally in order to verify performance of the proposed method, numerical simulations and RTHS with a buckling-restrained brace specimen are carried out. Relevant results show that the proposed technique is endowed with good convergence speed and accuracy, even when measurement noises and amplitude errors of actuator control are present.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제4권3호
• /
• pp.129-134
• /
• 2015

역 사회공학 기반 스팸공격은 공격자가 직접적인 공격을 수행하는 것이 아니라 피해자가 문제 있는 사이트 주소, 문자, 이메일 수신 및 친구 수락 등을 통해 유도하기 때문에 온라인 소셜 네트워크에서 활성화되기 쉽다. 스팸 탐지 관련 기존 연구들은 소셜 네트워크 특성을 반영하지 않은 채, 관리자의 수동적인 판단 및 라벨링을 바탕으로 스팸을 정상 데이터와 구분하는 단계에 머물러있다. 본 논문에서는 소셜 네트워크 데이터 중 하나인 Twitter spam데이터 셋을 실제로 분석하고 소셜 네트워크에서 다양한 속성들을 반영하여 정상 (ham)과 비정상 (spam)을 구분할 수 있는 탐지 메트릭을 제안한다. 또한, 관리자의 관여 없이도 실시간 및 점진적으로 스팸의 특성을 학습하여 새로운 스팸에 대해서도 탐지할 수 있는 비지도 학습 기법(unsupervised scheme)을 제안한다. 실험 결과, 제안하는 기법은 90% 이상의 정확도로 정상과 스팸을 구별했고 실시간 및 점진적 학습 결과도 정확함을 보였다.

• 한국경영과학회지
• /
• 제38권1호
• /
• pp.123-138
• /
• 2013

Keyword advertising has been used as a promotion tool rather than the advertising itself to online retailers. This is because the online retailer expects the direct sales increase when they deploy the keyword sponsorship. In practice, many online sellers rely on keyword advertising to promote their sales in short term with limited budget. Most of the previous researches use direct revenue factors as dependent variables such as CTR (click through rate) and CVI (conversion per impression) in their researches on the keyword advertising[14, 16, 22, 25, 31, 32]. Previous studies were, however, conducted in the context of aggregate-level due to the limitations on the data availability. These researches cannot evaluate the performance of keyword advertising in the individual level. To overcome these limitations, our research focuses on conversion of keyword advertising in individual-level. Also, we consider manageable factors as independent variables in terms of online retailers (the costs of keyword by implementation methods and meanings of keyword). In our study we developed the keyword advertising conversion model in the individual-level. With our model, we can make some theoretical findings and managerial implications. Practically, in the case of a fixed cost plan, an increase of the number of clicks is revealed as an effective way. However, higher average CPC is not significantly effective in increasing probability of purchase conversion. When this type (fixed cost plan) of implementation could not generate a lot of clicks, it cannot significantly increase the probability of purchase choice. Theoretically, we consider the promotional attributes which influence consumer purchase behavior and conduct individuals-level research based on the actual data. Limitations and future direction of the study are discussed.