• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.161-177
• /
• 2015

With the rapid evolution of technology, the size, number, and the type of databases has increased concomitantly, so data mining approaches face many challenging applications from databases. One such application is discovery of fraud patterns from agricultural product wholesale transaction instances. The agricultural product wholesale market in Korea is huge, and vast numbers of transactions have been made every day. The demand for agricultural products continues to grow, and the use of electronic auction systems raises the efficiency of operations of wholesale market. Certainly, the number of unusual transactions is also assumed to be increased in proportion to the trading amount, where an unusual transaction is often the first sign of fraud. However, it is very difficult to identify and detect these transactions and the corresponding fraud occurred in agricultural product wholesale market because the types of fraud are more intelligent than ever before. The fraud can be detected by verifying the overall transaction records manually, but it requires significant amount of human resources, and ultimately is not a practical approach. Frauds also can be revealed by victim's report or complaint. But there are usually no victims in the agricultural product wholesale frauds because they are committed by collusion of an auction company and an intermediary wholesaler. Nevertheless, it is required to monitor transaction records continuously and to make an effort to prevent any fraud, because the fraud not only disturbs the fair trade order of the market but also reduces the credibility of the market rapidly. Applying data mining to such an environment is very useful since it can discover unknown fraud patterns or features from a large volume of transaction data properly. The objective of this research is to empirically investigate the factors necessary to detect fraud transactions in an agricultural product wholesale market by developing a data mining based fraud detection model. One of major frauds is the phantom transaction, which is a colluding transaction by the seller(auction company or forwarder) and buyer(intermediary wholesaler) to commit the fraud transaction. They pretend to fulfill the transaction by recording false data in the online transaction processing system without actually selling products, and the seller receives money from the buyer. This leads to the overstatement of sales performance and illegal money transfers, which reduces the credibility of market. This paper reviews the environment of wholesale market such as types of transactions, roles of participants of the market, and various types and characteristics of frauds, and introduces the whole process of developing the phantom transaction detection model. The process consists of the following 4 modules: (1) Data cleaning and standardization (2) Statistical data analysis such as distribution and correlation analysis, (3) Construction of classification model using decision-tree induction approach, (4) Verification of the model in terms of hit ratio. We collected real data from 6 associations of agricultural producers in metropolitan markets. Final model with a decision-tree induction approach revealed that monthly average trading price of item offered by forwarders is a key variable in detecting the phantom transaction. The verification procedure also confirmed the suitability of the results. However, even though the performance of the results of this research is satisfactory, sensitive issues are still remained for improving classification accuracy and conciseness of rules. One such issue is the robustness of data mining model. Data mining is very much data-oriented, so data mining models tend to be very sensitive to changes of data or situations. Thus, it is evident that this non-robustness of data mining model requires continuous remodeling as data or situation changes. We hope that this paper suggest valuable guideline to organizations and companies that consider introducing or constructing a fraud detection model in the future.

• Journal of Korea Water Resources Association
• /
• v.57 no.3
• /
• pp.181-193
• /
• 2024

The increasing atmospheric imbalance caused by climate change leads to an elevation in precipitation, resulting in a heightened frequency of flooding. Consequently, there is a growing need for technology to detect and monitor these occurrences, especially as the frequency of flooding events rises. To minimize flood damage, continuous monitoring is essential, and flood areas can be detected by the Synthetic Aperture Radar (SAR) imagery, which is not affected by climate conditions. The observed data undergoes a preprocessing step, utilizing a median filter to reduce noise. Classification techniques were employed to classify water bodies and non-water bodies, with the aim of evaluating the effectiveness of each method in flood detection. In this study, the Otsu method and Support Vector Machine (SVM) technique were utilized for the classification of water bodies and non-water bodies. The overall performance of the models was assessed using a Confusion Matrix. The suitability of flood detection was evaluated by comparing the Otsu method, an optimal threshold-based classifier, with SVM, a machine learning technique that minimizes misclassifications through training. The Otsu method demonstrated suitability in delineating boundaries between water and non-water bodies but exhibited a higher rate of misclassifications due to the influence of mixed substances. Conversely, the use of SVM resulted in a lower false positive rate and proved less sensitive to mixed substances. Consequently, SVM exhibited higher accuracy under conditions excluding flooding. While the Otsu method showed slightly higher accuracy in flood conditions compared to SVM, the difference in accuracy was less than 5% (Otsu: 0.93, SVM: 0.90). However, in pre-flooding and post-flooding conditions, the accuracy difference was more than 15%, indicating that SVM is more suitable for water body and flood detection (Otsu: 0.77, SVM: 0.92). Based on the findings of this study, it is anticipated that more accurate detection of water bodies and floods could contribute to minimizing flood-related damages and losses.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.529-542
• /
• 2000

Recent years, the use of multimedia information is rapidly increasing, and the video media is the most rising one than any others, and this field Integrates all the media into a single data stream. Though the availability of digital video is raised largely, it is very difficult for users to make the effective video access, due to its length and unstructured video format. Thus, the minimal interaction of users and the explicit definition of video structure is a key requirement in the lately developing image and video management systems. This paper defines the terms and hierarchical video structure, and presents the system, which construct the clustering-based video hierarchy, which facilitate users by browsing the summary and do a random access to the video content. Instead of using a single feature and domain-specific thresholds, we use multiple features that have complementary relationship for each other and clustering-based methods that use normalization so as to interact with users minimally. The stage of shot boundary detection extracts multiple features, performs the adaptive filtering process for each features to enhance the performance by eliminating the false factors, and does k-means clustering with two classes. The shot list of a result after the proposed procedure is represented as the video hierarchy by the intelligent unsupervised clustering technique. We experimented the static and the dynamic movie videos that represent characteristics of various video types. In the result of shot boundary detection, we had almost more than 95% good performance, and had also rood result in the video hierarchy.

• Microbiology and Biotechnology Letters
• /
• v.43 no.3
• /
• pp.296-299
• /
• 2015

Cowpea mild mottle virus (CPMMV) has a wide range of hosts, such as the pea family and tomato. CPMMV is a non-reported virus in Korea, and is domestically designated as a controlled virus associated with plant quarantine. In this study, a rapid diagnostic method for the detection of CPMMV at quarantine sites was developed. For the development of a user-based system, the PCR compositions and conditions use existing methods of quarantine for the viruses. Two sets of RT-PCR and nested PCR were developed in this study that could be amplified from 579 → 298 dp and 638 → 252 bp, respectively. Furthermore, a sequence inserted positive control plasmid was developed, which is able to identify false-positives resulting from laboratory contamination. The findings of this study are important for the diagnosis of CPMMV in imported crops held in plant quarantine.

• Journal of Korea Multimedia Society
• /
• v.14 no.10
• /
• pp.1252-1261
• /
• 2011

In this paper, we propose the comparison method of pattern similarity for video segmentation algorithm. The shot boundary type is categorized as 2 types, abrupt change and gradual change. The representative examples of gradual change are dissolve, fade-in, fade-out or wipe transition. The proposed method consider the problem to detect shot boundary as 2-class problem. We concentrated if the shot boundary event happens or not. It is essential to define similarity between frames for shot boundary detection. We proposed 2 similarity measures, within similarity and between similarity. The within similarity is defined by feature comparison between frames belong to same shot. The between similarity is defined by feature comparison between frames belong to different scene. Finally we calculated the statistical patterns comparison between the within similarity and between similarity. Because this measure is robust to flash light or object movement, our proposed algorithm make contribution towards reducing false positive rate. We employed color histogram and mean of sub-block on frame image as frame feature. We performed the experimental evaluation with video dataset including set of TREC-2001 and TREC-2002. The proposed algorithm shows the performance, 91.84% recall and 86.43% precision in experimental circumstance.

• Journal of the Microelectronics and Packaging Society
• /
• v.22 no.1
• /
• pp.15-19
• /
• 2015

We demonstrated an inspection system for detecting discoloration of PCB Cu ball pad with an OSP surface finish. Though the OSP surface finish has many advantages such as eco-friendly and low cost, however, it often shows a discoloration phenomenon due to a heating process. In this study, the discoloration was analyzed with device-independent CIELAB color space. First of all, the PCB samples were inspected with standard lamps and CCD camera. The measured data was processed with Labview program for detecting discoloration of Cu ball pad. From the original PCB sample image, the localized Cu ball pad image was selected to reduce the image size by the binarization and edge detection processes and it was also converted to device-independent CIELAB color space using $3{\times}3$ conversion matrix. Both acquisition time and false acceptance rate were significantly reduced with this proposed inspection system. In addition, $L^*$ and $b^*$ values of CIELAB color space were suitable for inspection of discoloration of Cu ball pad.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.48 no.2
• /
• pp.158-167
• /
• 2015

A lateral flow immunoassay kit based on antigen-antibody interactions was developed to detect residues of beta-lactams, quinolones, tetracyclines, and sulfonamides in farmed fish. Group-specific antibodies showing cross-reactivity with other antibiotics in the same group were produced in rabbits. The rabbits were immunized eight times to obtain the maximum titers. Antibodies were extracted from the antisera collected from the immunized rabbits and produced group-specific reactions with antibiotics from the four groups. A kit was prepared that optimize conditions for the antigen-antibody reaction, using colloidal gold conjugated antibodies, and was designed to detect the four groups of antibiotics simultaneously. The kit enabled the detection of antibiotics in the four groups at below maximum residue limits (MRLs), which were $200{\mu}g/kg$ for tetracyclines, $100{\mu}g/kg$ for sulfonamides, $50{\mu}g/kg$ for beta-lactams, and $100{\mu}g/kg$ for quinolones. The cross-reactivity of the antibodies ranged from 10-80% for the sulfonamides, 20-100% for tetracyclines, 38-100% for quinolones, and 20-100% for the beta-lactams, confirming that the antibodies were group specific. The test kit was used 30 times to examine spiked antibiotics at the limits of detection (LODs) and all produced positive results, indicating high sensitivity. The LODs for the assay ranged from 4-20 ng/mL for beta-lactams, 25-50 ng/mL for sulfonamides, 20-100 ng/mL for tetracyclines, and 30-80 ng/mL for quinolones, and there were no false negative reactions at above these LODs. In addition, all of the LODs of the developed kit were correlated with high-performance liquid chromatography (HPLC) data. Our lateral flow immunoassay kit can simultaneously detect antibiotic residues from a large number of fish samples rapidly, strengthening the safety of domestic farmed and imported fish.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.18
• /
• pp.7719-7724
• /
• 2014

Background: Lymph node metastasis is believed to be a dependent negative prognostic factor of esophageal cancer. To explore detection methods with high sensitivity and accuracy for metastases to regional and distant lymph nodes in the clinic is of great significance. This study focused on clinical application of FDG PET/CT and contrast-enhanced multiple-slice helical computed tomography (MSCT) in lymph node staging of esophageal cancer. Materials and Methods: One hundred and fifteen cases were examined with enhanced 64-slice-MSCT scan, and FDG PET/CT imaging was conducted for neck, chest and upper abdomen within one week. The primary lesion, location and numbers of metastatic lymph nodes were observed. Surgery was performed within one week after FDG PET/CT detection. All resected lesions were confirmed histopathologically as the gold standard. Comparative analysis of the sensitivity, specificity, and accuracy based on FDG PET/CT and MSCT was conducted. Results: There were 946 lymph node groups resected during surgery from 115 patients, and 221 were confirmed to have metastasis pathologically. The sensitivity, specificity, accuracy of FDG PET/CT in detecting lymph node metastasis were 74.7%, 97.2% and 92.0%, while with MSCT they were 64.7%, 96.4%, and 89.0%, respectively. A significance difference was observed in sensitivity (p=0.030), but not the others (p>0.05). The accuracy of FDG PET/CT in detecting regional lymph node with or without metastasis were 91.9%, as compared to 89.4% for MSCT, while FDG PET/CT and MSCT values for detecting distant lymph node with or without metastasis were 94.4% and 94.7%. No significant difference was observed for either regional or distant lymph node metastasis. Additionally, for detecting para-esophageal lymph nodes metastasis, the sensitivity of FDG PET/CT was 72%, compared with 54.7% for MSCT (p=0.029). Conclusions: FDG PET/CT is more sensitive than MSCT in detecting lymph node metastasis, especially for para-esophageal lymph nodes in esophageal cancer cases, although no significant difference was observed between FDG PET/CT and MSCT in detecting both regional and distant lymph node metastasis. However, enhanced MSCT was found to be of great value in distinguishing false negative metastatic lymph nodes from FDG PET/CT. The combination of FDG PET/CT with MSCT should improve the accuracy in lymph node metastasis staging of esophageal cancer.

• Childhood Kidney Diseases
• /
• v.6 no.2
• /
• pp.218-226
• /
• 2002

Purpose: The purpose of this study is to assess the ability of power Doppler sonography in the detection of acute pyelonephritis. Materials and Methods: We performed gray scale sonography, power Doppler sonography, and $^{Tc-99m}DMSA$ scintigraphy of the kidney in 80 patients with symptoms suggesting upper urinary tract infection. All imaging studies were obtained within 4 days. On $^{Tc-99m}DMSA$ scintigraphy, decreased radioactivity or photopenic lesions were considered indicative of acute pyelonephritis. Triangular areas of decreased perfusion identified on power Doppler sonography were considered as parenchymal lesions of acute pyelonephritis. The results of gray scale sonography and power Doppler sonography were retrospectively analysed and compared with those of $^{Tc-99m}DMSA$ scintigraphy which was given as the standards of reference. Results: For 40(85%) of the 47 patients with scintigraphy-proven acute pyelonephritis, power Doppler sonography diagnosed this condition on the correct side. The acute pyelonephritis which was not revealed by power Doppler sonography was observed in seven patients. Also, in three patients, false-positive indication of pyelonephritis was given by power Doppler sonography. Gray scale sonography showed positive findings in 23(49%) of 47 patients with positive findings on scintigraphy. Conclusion: Power Doppler sonography seems to be less sensitive than $^{Tc-99m}DMSA$ DMSA scintigraphy but significantly more sensitive than gray scale sonography for the detection of acute pyelonephritis in children. Power Doppler sonography shows promise as a noninvasive means of assessing renal cortical perfusion in children with clinically suspected acute pyelonephritis.

• The Bulletin of The Korean Astronomical Society
• /
• v.43 no.1
• /
• pp.41.1-41.1
• /
• 2018

We introduce a current status and future plans of Korea Microlensing Telescope Network (KMTNet) microlensing experiments, which include an observational strategy, pipeline, event-finder, and collaborations with Spitzer. The KMTNet experiments were initiated in 2015. From 2016, KMTNet observes 27 fields including 6 main fields and 21 subfields. In 2017, we have finished the DIA photometry for all 2016 and 2017 data. Thus, it is possible to do a real-time DIA photometry from 2018. The DIA photometric data is used for finding events from the KMTNet event-finder. The KMTNet event-finder has been improved relative to the previous version, which already found 857 events in 4 main fields of 2015. We have applied the improved version to all 2016 data. As a result, we find that 2597 events are found, and out of them, 265 are found in KMTNet-K2C9 overlapping fields. For increasing the detection efficiency of event-finder, we are working on filtering false events out by machine-learning method. In 2018, we plan to measure event detection efficiency of KMTNet by injecting fake events into the pipeline near the image level. Thanks to high-cadence observations, KMTNet found fruitful interesting events including exoplanets and brown dwarfs, which were not found by other groups. Masses of such exoplanets and brown dwarfs are measured from collaborations with Spitzer and other groups. Especially, KMTNet has been closely cooperating with Spitzer from 2015. Thus, KMTNet observes Spitzer fields. As a result, we could measure the microlens parallaxes for many events. Also, the automated KMTNet PySIS pipeline was developed before the 2017 Spitzer season and it played a very important role in selecting the Spitzer target. For the 2018 Spitzer season, we will improve the PySIS pipeline to obtain better photometric results.