• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.2
• /
• pp.45-56
• /
• 2015

In this paper we propose a very rapid moving object tracking method for an object-based auto focus on a smart phone camera. By considering the limit of non-learning approach on low-performance platforms, we use a sliding-window detection technique based on histogram features. By adapting the integral histogram, we solve the problem of the time-consuming histogram computation on each sub-window. For more speed up, we propose a local candidate search, and an adaptive scaling template method. In addition, we propose to apply a stabilization term in the matching function for a stable detection location. In experiments on our dataset, we demonstrated that we achieved a very rapid tracking performance demonstrating over 100 frames per second on a PC environment.

• Journal of Microbiology and Biotechnology
• /
• v.25 no.3
• /
• pp.321-327
• /
• 2015

Nocardia salmonicida is one of the main pathogens of fish nocardiosis. The purpose of this study was to build a loop-mediated isothermal amplification (LAMP) method for the rapid and sensitive detection of N. salmonicida. A set of four primers were designed from the 16S-23S rRNA intergenic spacer region of N. salmonicida, and conditions for LAMP were optimized as incubating all the reagents for 60 min at 64℃. LAMP products were judged with agar gel electrophoresis as well as with the naked eye after the addition of SYBR Green I. Results showed the sensitivity of the LAMP assay was 1.68 × 10³ CFU/ml (16.8 CFU per reaction) and 10-fold higher than that of PCR. The LAMP method was also effectively applied to detect N. salmonicida in diseased fish samples, and it may potentially facilitate the surveillance and early diagnosis of fish nocardiosis.

• Korean Journal of Clinical Laboratory Science
• /
• v.45 no.1
• /
• pp.16-20
• /
• 2013

Outbreaks of vancomycin-resistant enterococci (VRE) are being reported more frequently in many countries. While seven glycopeptide resistance genotypes have been described in Enterococci, vanA and vanB are the most common resistance genotypes. The aim of this study was to detect antibiotic susceptibilities of 23 Enterococcus faecium strains, which caused an outbreak in a University hospital by a disk diffusion test to investigate the presence of the species specific gene, and the resistant genotypes, vanA and vanB by duplex PCR. PCR for vanA and vanB was performed on 23 enterococci. Twenty three were identified as E. faecium and were tested positive for the vanA genotype. This study will report on the validation of a simple and accurate VRE detection method that can be easily incorporated into the daily routine of a clinical laboratory. Early detection of VRE strains, including those with susceptibility to vancomycin, is of paramount clinical importance as it allows rapid initiation of strict infection control practices, as well as the therapeutic guidance for confirmed infections. The PCR method developed in the present study is simple and reliable for the rapid characterization of VRE.

• The Plant Pathology Journal
• /
• v.39 no.1
• /
• pp.141-148
• /
• 2023

Black shoot blight disease caused by Erwinia pyrifoliae has serious impacts on quality and yield in pear production in Korea; therefore, rapid and accurate methods for its detection are needed. However, traditional detection methods require a great deal of time and fail to achieve absolute quantification. In the present study, we developed a droplet digital polymerase chain reaction (ddPCR) method for the detection and absolute quantification of E. pyrifoliae using a pair of species-specific primers. The detection range was 10³-10⁷ copies/ml (DNA templates) and cfu/ml (cell culture templates). This new method exhibited good linearity and repeatability and was validated by absolute quantification of E. pyrifoliae DNA copies from samples of artificially inoculated immature pear fruits. Here, we present the first study of ddPCR assay for the detection and quantification of E. pyrifoliae. This method has potential applications in epidemiology and for the early prediction of black shoot blight outbreaks.

• Journal of Microbiology and Biotechnology
• /
• v.20 no.3
• /
• pp.569-573
• /
• 2010

A quantitative detection method for Salmonella in seafood was developed using a SYBR Green-based real-time PCR assay. The assay was developed using pure Salmonella DNA at different dilution levels [i.e., 1,000 to 2 genome equivalents (GE)]. The sensitivity of the real-time assay for Salmonella in seeded seafood samples was determined, and the minimum detection level was 20 CFU/g, whereas a detection level of 2 CFU/ml was obtained for pure culture in water with an efficiency of ${\geq}85%$. The real-time assay was evaluated in repeated experiments with seeded seafood samples and the regression coefficient ($R^2$) values were calculated. The performance of the real-time assay was further assessed with naturally contaminated seafood samples, where 4 out of 9 seafood samples tested positive for Salmonella and harbored cells <100 GE/g, which were not detected by direct plating on Salmonella Chromagar media. Thus, the method developed here will be useful for the rapid quantification of Salmonella in seafood, as the assay can be completed within 2-3 h. In addition, with the ability to detect a low number of Salmonella cells in seafood, this proposed method can be used to generate quantitative data on Salmonella in seafood, facilitating the implementation of control measures for Salmonella contamination in seafood at harvest and post-harvest levels.

• Journal of Microbiology and Biotechnology
• /
• v.29 no.10
• /
• pp.1543-1552
• /
• 2019

Salmonella is a common zoonotic and foodborne pathogen that causes high morbidity and mortality in developing countries. In this study, we established and validated a polymerase spiral reaction (PSR) assay which targeted the conserved invasion gene (invA) of Salmonella by SYBR Green I indicator methods. Subsequently, assays for determination of the optimal conditions for optimal specificity and sensitivity of PSR were performed. We performed comprehensive evaluations using loop-mediated isothermal amplification (LAMP) and real-time PCR. A total number of 532 samples of daily food were analyzed by PSR. Twenty-seven bacterial strains were tested in the specificity assay, from which positive results were obtained only for 14-Salmonella strains. However, none of the 13 non-Salmonella strains was amplified. Similarly with LAMP and real-time PCR, the detection limit of the PSR assay was 50 CFU/ml. The PSR method was also successfully applied to evaluate the contamination with Salmonella in 532 samples of daily food, corroborating traditional culture method data. The novel PSR method is simple, sensitive, and rapid and provides new insights into the prevention and detection of foodborne diseases.

• Parasites, Hosts and Diseases
• /
• v.49 no.1
• /
• pp.33-38
• /
• 2011

Prompt and accurate diagnosis of malaria is the key to prevent disease morbidity and mortality. This study was carried out to evaluate diagnostic performance of 3 commercial rapid detection tests (RDTs), i.e., Malaria Antigen Pf/Pan$^{TM}$, Malaria Ag-Pf$^{TM}$, and Malaria Ag-Pv$^{TM}$ tests, in comparison with the microscopic and PCR methods. A total of 460 blood samples microscopically positive for Plasmodium falciparum (211 samples), P. vivax (218), mixed with P. falciparum and P. vivax (30), or P. ovale (1), and 124 samples of healthy subjects or patients with other fever-related infections, were collected. The sensitivities of Malaria Ag-Pf$^{TM}$ and Malaria Antigen Pf/Pan$^{TM}$ compared with the microscopic method for P. falciparum or P. vivax detection were 97.6% and 99.0%, or 98.6% and 99.0%, respectively. The specificities of Malaria Ag-Pf$^{TM}$, Malaria Ag-Pv$^{TM}$, and Malaria Antigen Pf/Pan$^{TM}$ were 93.3%,98.8%, and 94.4%, respectively. The sensitivities of Malaria Ag-Pf$^{TM}$, Malaria Antigen Pf/Pan$^{TM}$, and microscopic method, when PCR was used as a reference method for P. falciparum or P. vivax detection were 91.8%, 100%, and 96.7%, or 91.9%,92.6%, and 97.3%, respectively. The specificities of Malaria Ag-Pf$^{TM}$, Malaria Ag-Pv$^{TM}$, Malaria Antigen Pf/Pan$^{TM}$, and microscopic method were 66.2%, 92.7%, 73.9%, and 78.2%, respectively. Results indicated that the diagnostic performances of all the commercial RDTs are satisfactory for application to malaria diagnosis.

• Proceedings of the Korean Society of Plant Pathology Conference
• /
• 2003.10a
• /
• pp.150.2-150
• /
• 2003

Carnation mottle carmovirus(CarMV) was isolated from Lilium spp. in Korea. This isolate, CarMV, was done bioassay, which plants were Dianthus caryophyllus, Gomphrena globosa, Chenopodium amaranticolor, Dianths chinensis. CarMV was propagated on the leaves of Chenopodium amaranticolor with the crude-sap inoculation method and purified by Mossops method(1976). We produced antiserum against CarMV and analyzed the antiserum specificity with ELISA, Gel diffusion method, and Rapid Immunofilter Paper Assay (RIPA). From these results of the assay, RIPA method was simple and rapid for CarMV detection. We have established successfully the CarMV detection system. CarMV coat protein gene was amplified by RT-PCR with specific primers and sequencing analysis was done.

• Journal of Multimedia Information System
• /
• v.6 no.1
• /
• pp.1-6
• /
• 2019

In the field of industrial applications, the real-time performance of the target detection problem is very important. The most serious time consumption in the pedestrian detection process is the extraction phase of the candidate window. To accelerate the speed, in this paper, a fast extraction of pedestrian candidate window based on the BING (Binarized Normed Gradients) algorithm replaces the traditional sliding window scanning. The BING features are extracted with the positive and negative samples and input into the two-stage SVM (Support Vector Machine) classifier for training. The obtained BING template may include a pedestrian candidate window. The trained template is loaded during detection, and the extracted candidate windows are input into the classifier. The experimental results show that the proposed method can extract fewer candidate window and has a higher recall rate with more rapid speed than the traditional sliding window detection method, so the method improves the detection speed while maintaining the detection accuracy. In addition, the real-time requirement is satisfied.