• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.31-37
• /
• 2021

In this paper proposed a feature fusion and spatial attention-based modified YOLOv4S for small and occluded detection. Conventional YOLOv4S is a lightweight network and lacks feature extraction capability compared to the method of the deep network. The proposed method first combines feature maps of different scales with feature fusion to enhance semantic and low-level information. In addition expanding the receptive field with dilated convolution, the detection accuracy for small and occluded objects was improved. Second by improving the conventional spatial information with spatial attention, the detection accuracy of objects classified and occluded between objects was improved. PASCAL VOC and COCO datasets were used for quantitative evaluation of the proposed method. The proposed method improved mAP by 2.7% in the PASCAL VOC dataset and 1.8% in the COCO dataset compared to the Conventional YOLOv4S.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.11
• /
• pp.156-163
• /
• 2015

In the using of FBG(Fiber Bragg Grating) developed in home land, we designed and manufactured united FBG acoustic transducers the first in Korea. they are being applied to multi-point signal detection of FBG Hydrophone used Hopper WDM(national patent NO 10-1502954) in the underwater. On united FBG transducers manufactured, we made an demonstrated on respective frequency response peculiarities in the underwater and analyzed the special characters. As the experimental result on frequency response peculiarities, we made it possible underwater acoustic detection on united FBG acoustic transducers type to maximum 30Hz~2.5KHz. it's the optimum conditions of 1.2KHz frequency in detection. And for the purpose of realization on multi-point signal detection on wide scope in the underwater, in the using of WDM(Wavelength Division Multiplexing) method and passive band-pass filter system, established arrays system and succeeded in multi-point underwater acoustic signal detection to the frequency 200Hz~1.3KHz out of the two united type FBG transducers. Additionally, it would be possible directivity detection for the object of its source as the intensity of detection signal varies with the sound source's direction and angle. From now on we prepared a new moment on the practical use study on FBG hydrophone in the future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.12
• /
• pp.2555-2562
• /
• 2009

The algorithm that is proposed in this paper defined a probability function to count connection process and connection-end process to apply TRW algorithm to voice network. Set threshold to evaluate the algorithm that is proposed, Based on the type of connection attack traffic changing the probability to measure the effectiveness of the algorithm, and Attack packets based on the speed of attack detection time was measured. At the result of evaluation, proposed algorithm shows that DDoS attack starts at 10 packets per a second and it detects the attack after 1.2 seconds from the start. Moreover, it shows that the algorithm detects the attack in 0.5 second if the packets were 20 per a second.

• The Korean Journal of Mycology
• /
• v.31 no.3
• /
• pp.121-128
• /
• 2003

This study was carried out to identify the phylogenetic relationship of Phellinus species and to know its distribution by comparing the DNA sequences of internal transcribed spacer regions(ITS1 and IST2) and 5.8S ribosomal DNA (rDNA) repeat unit. The Phellinus species had their specific sequences in IST1 and 2 regions depending on suedes. The comparison of the ITS sequences of standard strains indicated that the sequences of ITS1 were more variable than those of ITS2. Nine strains of the commercial products of Phellinus species used in this study were identified as P. lintues, P. baumii, P. igniarius, and P. pini. Most of commercial species were P. pini and P. baumii, and P. gilvus was not found. Also, P. linteus was only found in form of mycelial culture rather than fruiting body. Moreover, the species-specific primers were designed based on ITS sequence data. Each species-specific primers were bound in P. lintues(ITSF-PL2R), P. baumii(PB1F-ITS4R), P. igniarius(IF1-IR3), P. pini(PF1-PR3), and P. gilvus(GF2-GR4), respectively. These primer sets would be useful fer the detection of specific-species among unidentified Phellinus species rapidly.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.7 no.2
• /
• pp.137-142
• /
• 2004

Purpose: The resistance of H. pylori to clarithromycin is one of the major causes of eradication failure. In H. pylori, clarithromycin resistance is due to point mutation in 23S rRNA. The aims of this study were to investigate the mutation of 23S rRNA and to examine the association of cagA, vacA genotype and clarithromycin resistant genes. Methods: H. pylori DNA was extracted from antral biopsy specimens from 27 children with H. pylori infection. Specific polymerase chain reaction (PCR) assays were used for cagA and vacA. Mutations associated with clarithromycin resistance were detected by using PCR restriction fragment length polymorphism (RFLP) analysis of 23S rRNA gene. Results: A2143G mutation was detected in one case and A2144G in 4, indicating 18.5% were clarithromycin resistant. Among the total of 27, cagA was present in 25 (93%), vacA s1a/m1 in 6 (22%), s1a/m2 in 3 (11%), s1c/m1 in 16 (59%), and s1c/m2 in 1 (4%). All of the 5 clarithromycin resistant strains were cagA (+), among which 2 were s1a/m1 and 2 were s1c/m1. There was no relation between genotypes and clarithromycin resistant genes. Conclusion: Detection of H. pylori resistance to clarithromycin using PCR RFLP from biopsy specimens might be useful for the selection of antibiotics. Clarithromycin resistant genes are not associated with genotypes of cagA and vacA.

• Journal of the East Asian Society of Dietary Life
• /
• v.18 no.5
• /
• pp.753-759
• /
• 2008

The principal objective of this study was to develop the optimum oligonucleotide primers for the simple detection of Campylobacter in food samples. In order to achieve this goal, a variety of oligonucleotide primers were designed via the modification of 16S rDNA, ceuE and mapA sequences of Campylobacter. Through the subsequent analysis of the specificity and sensitivity of primers, two types of oligonucleotide primers, CB4 and CJ1, were selected for Campylobacter genus-specific and C. jejuni species-specific primers, respectively. The detection limit was found to be $10^0{\sim}10^1$ cells per reaction with the prepared cell suspension, however, the sensitivity in the meat samples was less, at $10^1{\sim}10^2$. We suggested that PCR inhibitors such as hemoglobin or immunoglobulin in pork or beef influenced.

• Journal of Digital Convergence
• /
• v.15 no.6
• /
• pp.391-398
• /
• 2017

In this paper, we compared the performance of "Network Intrusion Detection System based on attack feature selection using fuzzy control language"[1] and "Intelligent Intrusion Detection System Model for attack classification using RNN"[2]. In this paper, we compare the intrusion detection performance of two techniques using KDD CUP 99 dataset. The KDD 99 dataset contains data sets for training and test data sets that can detect existing intrusions through training. There are also data that can test whether training data and the types of intrusions that are not present in the test data can be detected. We compared two papers showing good intrusion detection performance in training and test data. In the comparative paper, there is a lack of performance to detect intrusions that exist but have no existing intrusion detection capability. Among the attack types, DoS, Probe, and R2L have high detection rate using fuzzy and U2L has a high detection rate using RNN.

• Korean Journal of Veterinary Research
• /
• v.30 no.3
• /
• pp.297-307
• /
• 1990

To establish an agar-gel immunodiffusion (AGID) test for detection of antibodies to Aujeszky's disease virus(ADV) in swine, the precipitating antigens were prepared by four procedures using the Aujeszky's disease virus, NYJ-1-87 strain isolated from the affected piglets in Korea. The optimal condition for AGID test and the properties of the antigens were investigated. To determine the optimal concentration of antigens, four antigens were experimentally prepared by concentrating the viral fluids by 1/30 to 1/200. It was proved that the antigen precipitated with ammonium sulfate at concentration of 1/100 was the most efficient to detect ADV antibodies by AGID test. When the relationship between the concentration of the antigens and the size of precipitating in radial immunodiffusion test was investigated, a high correlation coefficiency at r=0.95 (y=0.23x+23.4) was estimated, In study on the effects of various buffered salt solutions and agars on the sensitivity of AGID test by using the experimental ADV antigens, it was found that 0.05M tris buffer without sodium chloride at pH 7.2 induced the most distinctive precipitating lines, and that there was no significant differences in the sensitivity between the agarose and Noble's special agar. When the efficiency of AGID test was compared with serum neutralization(SN) test, the sensitivity of AGID test was 100% in SN titer over 1 : 16, 91.7% in SN titer of 1 : 8 and 57.1% in SN titer of 1 : 4. The specificity of AGID test compared with the sera with SN titer under 1 : 2 was 98.4%. Protein analysis of the antigens by SDS-PAGE indicated that antigen I and antigen III showed a specific band of polypeptides with molecular weight of 116 K in comparison with the control antigen. Antigen IV, treated with tween-80 and ammonium sulfate, revealed specific polypeptides bands at the molecular weights 45K, 98K and 150 K.

• Food Science of Animal Resources
• /
• v.37 no.6
• /
• pp.799-803
• /
• 2017

In the present study, centrifugation and filtration pretreatments were evaluated to decrease sample preparation time and to improve the sensitivity and specificity of multiplex polymerase chain reaction (PCR) for the detection of low levels of pathogenic Escherichia coli in various foods. Pathogenic E. coli (E. coli NCCP11142, E. coli NCCP14037, E. coli NCCP 14038, E. coli NCCP14039, and E. coli NCCP15661) was inoculated into pork, beef, and baby leafy vegetables at 1, 2, and 3 Log CFU/g. The samples were shaken 30 times (control), then centrifuged or filtered. DNA extracts from the samples were subjected to PCR using the $Powerchek^{TM}$ Diarrheal E. coli 8-plex Detection Kit. In the pork samples, no E. coli was detected in the control samples, while E. coli were detected in 100% of 3-Log CFU/g inoculated and centrifuged samples, and in 100% of 2 and 3-Log CFU/g inoculated, and filtered samples. In the beef samples, all control samples appeared to be E. coli-negative, while E. coli was detected in 50-75% of centrifuged samples, regardless of inoculated level, and in 100% of 2 and 3-Log CFU/g inoculated, and filtered samples. In baby leafy vegetables, E. coli were not detected in 25-50% of the control samples, while E. coli were detected in 0-25% of the centrifuged samples, and 75-100% of the filtered samples, depending on the inoculum amount. In conclusion, filtration pretreatment can be used to minimize sample preparation time, and improve the sensitivity and specificity of rapid detection of pathogenic E. coli in various foods.

• Atmosphere
• /
• v.23 no.4
• /
• pp.471-483
• /
• 2013

Nighttime sea fog detection from satellite is very hard due to limitation in using visible channels. Currently, most widely used method for the detection is the Dual Channel Difference (DCD) method based on Brightness Temperature Difference between 3.7 and 11 ${\mu}m$ channel (BTD). However, this method have difficulty in distinguishing between fog and low cloud, and sometimes misjudges middle/high cloud as well as clear scene as fog. Using CALIPSO Lidar Profile measurements, we have analyzed the intrinsic problems in detecting nighttime sea fog from various satellite remote sensing algorithms and suggested the direction for the improvement of the algorithm. From the comparison with CALIPSO measurements for May-July in 2011, the DCD method excessively overestimates foggy pixels (2542 pixels). Among them, only 524 pixel are real foggy pixels, but 331 pixels and 1687 pixels are clear and other type of clouds, respectively. The 514 of real foggy pixels accounts for 70% of 749 foggy pixels identified by CALIPSO. Our proposed new algorithm detects foggy pixels by comparing the difference between cloud top temperature and underneath sea surface temperature from assimilated data along with the DCD method. We have used two types of cloud top temperature, which obtained from 11 ${\mu}m$ brightness temperature (B_S1) and operational COMS algorithm (B_S2). The detected foggy 1794 pixels from B_S1 and 1490 pixel from B_S2 are significantly reduced the overestimation detected by the DCD method. However, 477 and 446 pixels have been found to be real foggy pixels, 329 and 264 pixels be clear, and 989 and 780 pixels be other type of clouds, detected by B_S1 and B_S2 respectively. The analysis of the operational COMS fog detection algorithm reveals that the cloud screening process was strictly enforced, which resulted in underestimation of foggy pixel. The 538 of total detected foggy pixels obtain only 187 of real foggy pixels, but 61 of clear pixels and 290 of other type clouds. Our analysis suggests that there is no winner for nighttime sea fog detection algorithms, but loser because real foggy pixels are less than 30% among the foggy pixels declared by all algorithms. This overwhelming evidence reveals that current nighttime sea fog algorithms have provided a lot of misjudged information, which are mostly originated from difficulty in distinguishing between clear and cloudy scene as well as fog and other type clouds. Therefore, in-depth researches are urgently required to reduce the enormous error in nighttime sea fog detection from satellite.