• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.297-309
• /
• 2023

The degradation of coastal ecosystems and fishery environments is accelerating due to the recent phenomenon of invertebrate grazers. To effectively monitor and implement preventive measures for this phenomenon, the adoption of remote sensing-based monitoring technology for extensive maritime areas is imperative. In this study, we compared and analyzed the robustness of deep learning-based object detection modelsfor detecting and monitoring invertebrate grazersfrom underwater videos. We constructed an image dataset targeting seven representative species of invertebrate grazers in the coastal waters of South Korea and trained deep learning-based object detection models, You Only Look Once (YOLO)v7 and YOLOv8, using this dataset. We evaluated the detection performance and speed of a total of six YOLO models (YOLOv7, YOLOv7x, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x) and conducted robustness evaluations considering various image distortions that may occur during underwater filming. The evaluation results showed that the YOLOv8 models demonstrated higher detection speed (approximately 71 to 141 FPS [frame per second]) compared to the number of parameters. In terms of detection performance, the YOLOv8 models (mean average precision [mAP] 0.848 to 0.882) exhibited better performance than the YOLOv7 models (mAP 0.847 to 0.850). Regarding model robustness, it was observed that the YOLOv7 models were more robust to shape distortions, while the YOLOv8 models were relatively more robust to color distortions. Therefore, considering that shape distortions occur less frequently in underwater video recordings while color distortions are more frequent in coastal areas, it can be concluded that utilizing YOLOv8 models is a valid choice for invertebrate grazer detection and monitoring in coastal waters.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.12
• /
• pp.157-167
• /
• 2009

Recently, the leakage of confidential information and personal information is taking place on the Internet more frequently than ever before. Most of such online security incidents are caused by attacks on vulnerabilities in web applications developed carelessly. It is impossible to detect an attack on a web application with existing firewalls and intrusion detection systems. Besides, the signature-based detection has a limited capability in detecting new threats. Therefore, many researches concerning the method to detect attacks on web applications are employing anomaly-based detection methods that use the web traffic analysis. Much research about anomaly-based detection through the normal web traffic analysis focus on three problems - the method to accurately analyze given web traffic, system performance needed for inspecting application payload of the packet required to detect attack on application layer and the maintenance and costs of lots of network security devices newly installed. The UTM(Unified Threat Management) system, a suggested solution for the problem, had a goal of resolving all of security problems at a time, but is not being widely used due to its low efficiency and high costs. Besides, the web filter that performs one of the functions of the UTM system, can not adequately detect a variety of recent sophisticated attacks on web applications. In order to resolve such problems, studies are being carried out on the web application firewall to introduce a new network security system. As such studies focus on speeding up packet processing by depending on high-priced hardware, the costs to deploy a web application firewall are rising. In addition, the current anomaly-based detection technologies that do not take into account the characteristics of the web application is causing lots of false positives and false negatives. In order to reduce false positives and false negatives, this study suggested a realtime anomaly detection method based on the analysis of the length of parameter value contained in the web client's request. In addition, it designed and suggested a WAF(Web Application Firewall) that can be applied to a low-priced system or legacy system to process application data without the help of an exclusive hardware. Furthermore, it suggested a method to resolve sluggish performance attributed to copying packets into application area for application data processing, Consequently, this study provide to deploy an effective web application firewall at a low cost at the moment when the deployment of an additional security system was considered burdened due to lots of network security systems currently used.

• Korean Journal of Heritage: History & Science
• /
• v.57 no.3
• /
• pp.24-35
• /
• 2024

Recently, research using deep learning technologies such as artificial intelligence, convolutional neural networks, etc. has been actively conducted in various fields including healthcare, manufacturing, autonomous driving, and security, and is having a significant influence on society. In line with this trend, the present study attempted to apply deep learning to the classification of archaeological artifacts, specifically ancient Korean roof-end tiles. Using 100 images of roof-end tiles from each of the Goguryeo, Baekje, and Silla dynasties, for a total of 300 base images, a dataset was formed and expanded to 1,200 images using data augmentation techniques. After building a model using transfer learning from the pre-trained EfficientNetB0 model and conducting five-fold cross-validation, an average training accuracy of 98.06% and validation accuracy of 97.08% were achieved. Furthermore, when model performance was evaluated with a test dataset of 240 images, it could classify the roof-end tile images from the three dynasties with a minimum accuracy of 91%. In particular, with a learning rate of 0.0001, the model exhibited the highest performance, with accuracy of 92.92%, precision of 92.96%, recall of 92.92%, and F1 score of 92.93%. This optimal result was obtained by preventing overfitting and underfitting issues using various learning rate settings and finding the optimal hyperparameters. The study's findings confirm the potential for applying deep learning technologies to the classification of Korean archaeological materials, which is significant. Additionally, it was confirmed that the existing ImageNet dataset and parameters could be positively applied to the analysis of archaeological data. This approach could lead to the creation of various models for future archaeological database accumulation, the use of artifacts in museums, and classification and organization of artifacts.

• Journal of Life Science
• /
• v.18 no.8
• /
• pp.1132-1139
• /
• 2008

A CpG island is a short stretch of DNA in which the frequency of the CG dinucleotide is higher than other regions. CpG islands are present in the promoters and exonic regions of approximately $30{\sim}60$% of mammalian genes so they are useful markers for genes in organisms containing 5-methylcytosine in their genomes. Recent evidence supports the notion that the hypermethylation of CpG island, by silencing tumor suppressor genes, plays a major causal role in cancer, which has been described in almost every tumor types. In this respect, CpG island search by computational methods is very helpful for cancer research and computational promoter and gene predictions. I therefore developed a window program (called CpGi) on the basis of CpG island criteria defined by D. Takai and P. A. Jones. The program 'CpGi' was implemented in Visual C++ 6.0 and can determine the locations of CpG islands using diverse parameters (%GC, Obs (CpG)/Exp (CpG), window size, step size, gap value, # of CpG, length) specified by user. The analysis result of CpGi provides a graphical map of CpG islands and G+C% plot, where more detailed information on CpG island can be obtained through pop-up window. Two human contigs, i.e. AP00524 (from chromosome 22) and NT_029490.3 (from chromosome 21), were used to compare the performance of CpGi and two other public programs for the accuracy of search results. The two other programs used in the performance comparison are Emboss-CpGPlot and CpG Island Searcher that are web-based public CpG island search programs. The comparison result showed that CpGi is on a level with or outperforms Emboss-CpGPlot and CpG Island Searcher. Having a simple and easy-to-use user interface, CpGi would be a very useful tool for genome analysis and CpG island research. To obtain a copy of CpGi for academic use only, contact corresponding author.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2
• /
• pp.199-210
• /
• 2002

In this paper, we carried out the study on speech recognition using the KM-Net topology design algorithm based on decision tree state-clustering to improve the performance of acoustic models in speech recognition. The Korean has many allophonic and grammatical rules compared to other languages, so we investigate the allophonic variations, which defined the Korean phonetics, and construct the phoneme question set for phonetic decision tree. The basic idea of the HM-Net topology design algorithm is that it has the basic structure of SSS (Successive State Splitting) algorithm and split again the states of the context-dependent acoustic models pre-constructed. That is, it have generated. the phonetic decision tree using the phoneme question sets each the state of models, and have iteratively trained the state sequence of the context-dependent acoustic models using the PDT-SSS (Phonetic Decision Tree-based SSS) algorithm. To verify the effectiveness of the above algorithm we carried out the speech recognition experiments for 452 words of center for Korean language Engineering (KLE452) and 200 sentences of air flight reservation task (YNU200). Experimental results show that the recognition accuracy has progressively improved according to the number of states variations after perform the splitting of states in the phoneme, word and continuous speech recognition experiments respectively. Through the experiments, we have got the average 71.5%, 99.2% of the phoneme, word recognition accuracy when the state number is 2,000, respectively and the average 91.6% of the continuous speech recognition accuracy when the state number is 800. Also we haute carried out the word recognition experiments using the HTK (HMM Too1kit) which is performed the state tying, compared to share the parameters of the HM-Net topology design algorithm. In word recognition experiments, the HM-Net topology design algorithm has an average of 4.0% higher recognition accuracy than the context-dependent acoustic models generated by the HTK implying the effectiveness of it.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.43 no.3 s.345
• /
• pp.21-32
• /
• 2006

A new SRAM circuit with row-by-row activation and low-swing write schemes is proposed to reduce switching power of active cells as well as leakage one of sleep cells in this paper. By driving source line of sleep cells by $V_{SSH}$ which is higher than $V_{SS}$, the leakage current can be reduced to 1/100 due to the cooperation of the reverse body-bias. Drain Induced Barrier Lowering (DIBL), and negative $V_{GS}$ effects. Moreover, the bit line leakage which may introduce a fault during the read operation can be eliminated in this new SRAM. Swing voltage on highly capacitive bit lines is reduced to $V_{DD}-to-V_{SSH}$ from the conventional $V_{DD}-to-V_{SS}$ during the write operation, greatly saving the bit line switching power. Combining the row-by-row activation scheme with the low-swing write does not require the additional area penalty. By the SPICE simulation with the Berkeley Predictive Technology Modes, 93% of leakage power and 43% of switching one are estimated to be saved in future leakage-dominant 70-un process. A test chip has been fabricated using $0.35-{\mu}m$ CMOS process to verify the effectiveness and feasibility of the new SRAM, where the switching power is measured to be 30% less than the conventional SRAM when the I/O bit width is only 8. The stored data is confirmed to be retained without loss until the retention voltage is reduced to 1.1V which is mainly due to the metal shield. The switching power will be expected to be more significant with increasing the I/O bit width.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.5
• /
• pp.338-343
• /
• 2004

Purpose: The purpose of this study was to develop a small animal PET using dual layer phoswich detector to minimize parallax error that degrades spatial resolution at the outer part of field-of-view (FOV). Materials and Methods: A simulation tool GATE (Geant4 Application for Tomographic Emission) was used to derive optimal parameters of small PET, and PET was developed employing the parameters. Lutetium Oxyorthosilicate (LSO) and Lutetium-Yttrium Aluminate-Perovskite(LuYAP) was used to construct dual layer phoswitch crystal. $8{\times}8$ arrays of LSO and LuYAP pixels, $2mm{\times}2mm{\times}8mm$ in size, were coupled to a 64-channel position sensitive photomultiplier tube. The system consisted of 16 detector modules arranged to one ring configuration (ring inner diameter 10 cm, FOV of 8 cm). The data from phoswich detector modules were fed into an ADC board in the data acquisition and preprocessing PC via sockets, decoder block, FPGA board, and bus board. These were linked to the master PC that stored the events data on hard disk. Results: In a preliminary test of the system, reconstructed images were obtained by using a pair of detectors and sensitivity and spatial resolution were measured. Spatial resolution was 2.3 mm FWHM and sensitivity was 10.9 $cps/{\mu}Ci$ at the center of FOV. Conclusion: The radioactivity distribution patterns were accurately represented in sinograms and images obtained by PET with a pair of detectors. These preliminary results indicate that it is promising to develop a high performance small animal PET.

• Korean Journal of Soil Science and Fertilizer
• /
• v.43 no.6
• /
• pp.968-974
• /
• 2010

We assessed the feasibility of discrete wavelet transform (DWT) applied for the spectral processing to enhance the estimation performance quality of soil organic matters using visible-near infrared spectra and mapped their distribution via block Kriging model. Continuum-removal and $1^{st}$ derivative transform as well as Haar and Daubechies DWT were used to enhance spectral variation in terms of soil organic matter contents and those spectra were put into the PLSR (Partial Least Squares Regression) model. Estimation results using raw reflectance and transformed spectra showed similar quality with $R^2$ > 0.6 and RPD> 1.5. These values mean the approximation prediction on soil organic matter contents. The poor performance of estimation using DWT spectra might be caused by coarser approximation of DWT which not enough to express spectral variation based on soil organic matter contents. The distribution maps of soil organic matter were drawn via a spatial information model, Kriging. Organic contents of soil samples made Gaussian distribution centered at around 20 g $kg^{-1}$ and the values in the map were distributed with similar patterns. The estimated organic matter contents had similar distribution to the measured values even though some parts of estimated value map showed slightly higher. If the estimation quality is improved more, estimation model and mapping using spectroscopy may be applied in global soil mapping, soil classification, and remote sensing data analysis as a rapid and cost-effective method.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.1
• /
• pp.103-113
• /
• 2019

Spatial resolution is still one of the most important parameters for evaluating image quality. In this study, we propose an approach to evaluate spatial resolution and MTF(Modulation Transfer Function) using bar target and Siemens star chart as a part of quality evaluation for UAV images. To this end, images were taken with a fixed-wing eBee(Canon IXUS) at the flight height of 130m and 260m, and with a rotary-wing GD-800(SONY NEX-5N) at flight height of 130m, with a Phantom 4 pro(FC 6310) at flight height of 90m, respectively. Spatial resolution was measured on orthoimages produced from this data. Results show that the resolution measured on the Siemens star and bar target was accurately degraded in proportion to the flight height regardless of the cameras. In the words, the spatial resolution of images taken at the same altitude of 130m with the eBee(Canon IXUS) and the GD-800(SONY NEX-5N) equipped with different cameras was the same as 4.1cm, and that of the eBee(Canon IXUS) at 260m was 8.0cm. In addition, the resolution measured on the Siemens star was about 1~2cm lower than that of the bar target at every flight height. The general tendency was also found to be proportional to the flight height in the measurement of the ${\sigma}_{MTF}$ from MTF, which simultaneously represents the resolution and contrast information of the image. However, at the same altitude of 130m, the ${\sigma}_{MTF}$ of the GD-800(SONY NEX-5N) is 0.36 and the eBee(Canon IXUS) is 0.59, which shows that the GD-800(SONY NEX-5N) has better camera performance. It is expected that study results will contribute to the analysis of spatial resolution of UAV images and to improve the reliability of quality.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.137-154
• /
• 2018

Animal infectious diseases, such as avian influenza and foot and mouth disease, occur almost every year and cause huge economic and social damage to the country. In order to prevent this, the anti-quarantine authorities have tried various human and material endeavors, but the infectious diseases have continued to occur. Avian influenza is known to be developed in 1878 and it rose as a national issue due to its high lethality. Food and mouth disease is considered as most critical animal infectious disease internationally. In a nation where this disease has not been spread, food and mouth disease is recognized as economic disease or political disease because it restricts international trade by making it complex to import processed and non-processed live stock, and also quarantine is costly. In a society where whole nation is connected by zone of life, there is no way to prevent the spread of infectious disease fully. Hence, there is a need to be aware of occurrence of the disease and to take action before it is distributed. Epidemiological investigation on definite diagnosis target is implemented and measures are taken to prevent the spread of disease according to the investigation results, simultaneously with the confirmation of both human infectious disease and animal infectious disease. The foundation of epidemiological investigation is figuring out to where one has been, and whom he or she has met. In a data perspective, this can be defined as an action taken to predict the cause of disease outbreak, outbreak location, and future infection, by collecting and analyzing geographic data and relation data. Recently, an attempt has been made to develop a prediction model of infectious disease by using Big Data and deep learning technology, but there is no active research on model building studies and case reports. KT and the Ministry of Science and ICT have been carrying out big data projects since 2014 as part of national R &D projects to analyze and predict the route of livestock related vehicles. To prevent animal infectious diseases, the researchers first developed a prediction model based on a regression analysis using vehicle movement data. After that, more accurate prediction model was constructed using machine learning algorithms such as Logistic Regression, Lasso, Support Vector Machine and Random Forest. In particular, the prediction model for 2017 added the risk of diffusion to the facilities, and the performance of the model was improved by considering the hyper-parameters of the modeling in various ways. Confusion Matrix and ROC Curve show that the model constructed in 2017 is superior to the machine learning model. The difference between the2016 model and the 2017 model is that visiting information on facilities such as feed factory and slaughter house, and information on bird livestock, which was limited to chicken and duck but now expanded to goose and quail, has been used for analysis in the later model. In addition, an explanation of the results was added to help the authorities in making decisions and to establish a basis for persuading stakeholders in 2017. This study reports an animal infectious disease prevention system which is constructed on the basis of hazardous vehicle movement, farm and environment Big Data. The significance of this study is that it describes the evolution process of the prediction model using Big Data which is used in the field and the model is expected to be more complete if the form of viruses is put into consideration. This will contribute to data utilization and analysis model development in related field. In addition, we expect that the system constructed in this study will provide more preventive and effective prevention.