• Food Science of Animal Resources
• /
• v.37 no.4
• /
• pp.599-605
• /
• 2017

Korean native honey (KNH) is much more expensive than European honey (EH) in Korea, because KNH is a favored honey which is produced less than EH. Food fraud of KNH has drawn attention of the government office concerned, which is in need of a method to differentiate between KNH and EH which are produced by the Asiatic honeybee, Apis cerana and the European honeybee, Apis mellifera, respectively. A method to discriminate KNH and EH was established by using duplex polymerase chain reaction (PCR) in this study. Immunochromatographic assay (IC) was examined to analyze the duplex PCR product. The DNA sequences of primers for the duplex PCR were determined by comparing cytochrome C oxidase genes of the two honey bee species. Chelex resin method was more efficient in extracting genomic DNA from honey than the other two procedures of commercial kits. The duplex PCR amplifying DNA of 133 bp were more sensitive than that amplifying DNA of 206 bp in detecting EH in the honey mixture of KNH and EH. Agarose gel electrophoresis and IC detected the DNA of 133 bp at the ratios of down to 1% and 5% EH in the honey mixture, respectively and also revealed that several KNH products distributed by internet shopping sites were actually EH. In conclusion, the duplex PCR with subsequent IC could also discriminate between KNH and EH and save time and labor.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.7
• /
• pp.475-487
• /
• 2020

The paper aims to facilitate a discussion around how big data technologies and data from citizens can be used to help public administration, society, and policy-making to improve community's lives. This paper discusses opportunities and challenges of big data strategies for government, society, and policy-making. It employs the presentation of numerous practical examples from different parts of the world, where public-service delivery has seen transformation and where initiatives have been taken forward that have revolutionized the way governments at different levels engage with the citizens, and how governments and civil society have adopted evidence-driven policy-making through innovative and efficient use of big data analytics. The examples include the governments of the United States, China, the United Kingdom, and India, and different levels of government agencies in the public services of fraud detection, financial market analysis, healthcare and public health, government oversight, education, crime fighting, environmental protection, energy exploration, agriculture, weather forecasting, and ecosystem management. The examples also include smart cities in Korea, China, Japan, India, Canada, Singapore, the United Kingdom, and the European Union. This paper makes some recommendations about how big data strategies transform the government and public services to become more citizen-centric, responsive, accountable and transparent.

• Journal of Industrial Convergence
• /
• v.17 no.2
• /
• pp.1-7
• /
• 2019

The Kakao bank can be conveniently used if there are only smartphones, identity cards, and bank accounts. However, a few days before the inauguration of Kakao Bank, the company opened an account for receiving loans from other people. In order to avoid such cases, the financial transactions will be detected if the SDS is withdrawn at a short interval of time. The detection system of FDS has four functions which are monitoring and auditing, collection, analysis, and response. There are security problems of the cocoa banks in various directions. The Kakao bank has a way to respond to the problem using FDS.: Keywords : Cocoa bank, security issues, information protection, FDS

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.303-304
• /
• 2021

In the 21st century, as we enter the Fourth Industrial Revolution, research in various fields utilizing big data is being conducted, and innovative and useful technologies are constantly emerging in the world. Among several technologies recently in the big data era, among various fields utilizing some algorithms of artificial intelligence, it shines in the field of finance and is used for pin tech, financial fraud detection and risk management, etc., and recently Even in the booming stock market, it is used for investment prediction and investment factor analysis using artificial intelligence algorithm models. In this paper, we plan to investigate various research cases and investigate trends in how they are used in the stock market through artificial intelligence that utilizes big data.

• Korean Journal of Medicinal Crop Science
• /
• v.26 no.1
• /
• pp.26-31
• /
• 2018

Background: Angelica gigas, A. sinensis, and A. acutiloba are commercially important in the herbal medicine market, and among them, A. gigas has the highest economic value and price. However, their similar morphological traits are often used for fraud. Despite their importance in herbal medicine, recognition of the differences between Angelica species is currently inadequate. Methods and Results: A multiplex polymerase chain reaction (PCR) method was developed for direct detection and identification of A. gigas, A. sinensis, and A. acutiloba. The gene for the distinction of species was targeted at ITS in the nucleus and trnC-petN gene in chloroplasts. The optimized multiplex PCR in the present study utilized each Angelica species-specific primer pairs. Each primer pair yielded products of 229 base pairs (bp) for A. gigas, 53 bp for A. sinensis, 170 bp for A. acutiloba. Additionally non-specific PCR products were not detected in similar species by species-specific primers. Conclusions: In the present study, a multiplex-PCR assay, successfully assessed the authenticity of Angelica species (A. gigas, A. sinensis, and A. acutiloba). and whole genome amplification (WGA) was performed after DNA extraction to identify, the species in the product. The detection method of raw materials developed in the present study could be applied to herbal medicine and health functional food management.

• Journal of Advanced Navigation Technology
• /
• v.18 no.6
• /
• pp.569-575
• /
• 2014

Since 2009 the number of users of smart phones and tablet PC is growing exponentially. In particular Apple's iOS and Google's Android OS are the heart of this remarkable growth, most of smart phone and tablet PC are designed to operate based on these two OS. Such increasing use of smart devices has led to changes in the social environment that allows, without the constraints of time and place. However, such development does not supply only ease to do something, even compared to past, financial fraud and information leakage are easier than before by variety of new types of attack for example phishing, pharming, smishing and qshing. So according to this paper, analyzes for smishing attack, propose a countermeasure system of the technical way and proved its higher performance compare to the existing method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.876-880
• /
• 2008

Outliers are the observations which are very larger or smaller than most observations in the given data set. These are shown by some sources. The result of the analysis with outliers may be depended on them. In general, we do data analysis after removing outliers. But, in data mining applications such as fraud detection and intrusion detection, outliers are included in training data because they have crucial information. In regression models, simple and multiple regression models need to eliminate outliers from given training data by standadized and studentized residuals to construct good model. In this paper, we use support vector regression(SVR) based on statistical teaming theory to analyze data with outliers in regression. We verify the improved performance of our work by the experiment using synthetic data sets.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.763-765
• /
• 2015

The study is being conducted to ensure the transparency of research and development have identified the problems of the current system and improve the way out. Such a study about the subject that do not follow either outside the institutional system has a disadvantage compared to an unfulfilled. R & D in order to prevent the misuse and fraud enforcement shall detect abnormal transactions that occur from transactions between research institutions and credit card issuers in real time. In this paper, we propose a detection method for real-time transaction over. It is able to detect and respond fraudulent transactions that may occur in a variety of environments by adding the data obtained by the business rules to derive stopped making detection system.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.209-225
• /
• 2020

This study tried to establish a base level for the form of ginseng in order to prevent fraud in which novice consumers, who have no information on ginseng and mountain ginseng, regard ginseng as mountain ginseng. To that end, researchers designed a service design in which when a consumer takes a picture of ginseng with an APP dedicated to a smartphone, the photo is sent remotely and the determined results are sent to the consumer based on machine learning data. In order to minimize the difference between the data set in the research process and the background color, location, size, illumination, and color temperature of the mountain ginseng when consumers took pictures through their smartphones, the filming box exclusively for consumers was designed. Accordingly, the collection of mountain ginseng samples was made under the same controlled environment and setting as the designed box. This resulted in a 100% predicted probability from the CNN(VGG16) model using a sample that was about one-tenth less than widley required in machine learning.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1053-1065
• /
• 2020

With the recent development of hardware performance and artificial intelligence technology, sophisticated fake videos that are difficult to distinguish with the human's eye are increasing. Face synthesis technology using artificial intelligence is called Deepfake, and anyone with a little programming skill and deep learning knowledge can produce sophisticated fake videos using Deepfake. A number of indiscriminate fake videos has been increased significantly, which may lead to problems such as privacy violations, fake news and fraud. Therefore, it is necessary to detect fake video clips that cannot be discriminated by a human eyes. Thus, in this paper, we propose a deep-fake detection model applied with Bidirectional Convolution LSTM and Attention Module. Unlike LSTM, which considers only the forward sequential procedure, the model proposed in this paper uses the reverse order procedure. The Attention Module is used with a Convolutional neural network model to use the characteristics of each frame for extraction. Experiments have shown that the model proposed has 93.5% accuracy and AUC is up to 50% higher than the results of pre-existing studies.