• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.61-73
• /
• 2024

Class imbalance is one of the significant challenges in deep learning tasks, particularly pronounced in areas with limited data. This study proposes a new approach that utilizes minimal labeled data for effectively classifying tomato leaf diseases. We introduced a recursive learning method using the YOLOv8 model. By utilizing the detection predictions of images on the training data as additional training data, the number of labeled data is progressively increased. Unlike conventional data augmentation and up-down sampling techniques, this method seeks to fundamentally solve the class imbalance problem by maximizing the utility of actual data. Based on the secured labeled data, tomato leaves were extracted, and diseases were classified using the EfficientNet model. This process achieved a high accuracy of 98.92%. Notably, a 12.9% improvement compared to the baseline was observed in the detection of Late blight diseases, which has the least amount of data. This research presents a methodology that addresses data imbalance issues while offering high-precision disease classification, with the expectation of application to other crops.

• Journal of the Korean Solar Energy Society
• /
• v.39 no.1
• /
• pp.59-66
• /
• 2019

BIPV or BAPV installation applied to building is increasing through public utility mandates enterprise. Solar PV energy generates only during the day, but if it is operated in convergence with ESS, which stores electrical energy, it can restrain the fossil energy used in buildings throughout the day. A solution is to converge with PV system and ESS. However, PV systems and ESS connected to the power grid in parallel can cause problems of electrical stability. A study was conducted on the case of failure to detect islanding operation under the parallel operation of PV generation and ESS that are connected in parallel to power grid. Experiments conducted various non-islanding detections under the operating conditions. In the experiment results, when one PCS - PV inverter or ESS inverter - was operating under the islanding condition, it stopped working within 0.5 seconds of the Korean grid standard. However, when both of PV inverter and ESS inverter were operating at the same time under the islanding situation, the anti-islanding algorithm did not operate normally and both inverters continuously supplied power to the connected RLC loads. islanding detection Algorithm developed by each inverter manufacturer has caused this phenomenon. Therefore, this paper presented a new test standard for islanding detection.

• Journal of Ecology and Environment
• /
• v.31 no.2
• /
• pp.153-159
• /
• 2008

The timing of the canopy phenology onset (CPO hereafter) indicates the initiation of the growing season, with rapid increases in exchange rates of carbon dioxide and water vapor between vegetation and atmosphere. The CPO is regarded as a potential indicator of ecosystem responses to global warming, but the CPO shows considerable spatial variation depending on the species composition and local temperature regime. at a given geographic location. In this study, we evaluated the utility of satellite observation data for detection of the timing of the CPO. Leaf area indices (LAI) obtained from the Moderate Resolution Imaging Spectrora-diometer (MODIS) were utilized to detect and map the onset dates from 2001 to 2006. The reliability of MODIS-based onset dates was evaluated with ground measured cherry blossom flowering data from national weather stations. The MODIS onset dates preceded the observed flowering dates by 8 days and were linearly related with a correlation coefficient of 0.58 (p < 0.05). In spite of the coarse spatial (1 km) and temporal (8 days) resolutions of MODIS LAI, the MODIS-based onset dates showed reasonable ability to predict flowering dates.

• Proceedings of the KSRS Conference
• /
• 2006.03a
• /
• pp.95-100
• /
• 2006

Measurements of ocean color from space since 1970s provided vital information with reference to physical and biogeochemical properties of the oceanic waters. The utility of these data has been explored in order to map and monitor highly toxic/or harmful algal blooms (HABs) that affected most of coastal waters throughout the world due to accelerated eutrophication from human activities and certain oceanic processes. However, the global atmospheric correction and bio-optical algorithms developed for oceanic waters were found to yield false information about the HABs in coastal waters. The present study aimed to evaluate the potential use of red tide index (RI) method, which has been developed by Ahn and Shanmugam (2005), for mapping of HABs in Korean and neighboring waters. Here we employed the SSMM to remove the atmospheric effect in the SeaWiFS image data and the achieved indices by RI method were found more appropriate in correctly identifying potential areas of the encountered HABs in Korean South Sea (KSS) and Chinese coastal waters during 1999-2004. But the existence of high absorbing and scattering materials greatly interfered with the standard OC4 algorithm which falsely identified red tides in these waters. In comparison with other methods, the RI approach for the early detection of HABs can provide state managers with accurate identification of the extent and location of these blooms as a management tool.

• Safety and Health at Work
• /
• v.2 no.1
• /
• pp.57-64
• /
• 2011

Objectives: Although phthalates like dibutyl phthalate (DBP) and di-2-ethylhexyl phthalate (DEHP) are commonly used as plasticizers and their metabolites are especially suspected of reproductive toxicity, little is known about occupational exposure to those phthalates. The aim of this study was to assess the utility of measuring the metabolite concentrations of DBP and DEHP in serum and urine samples as an indicator of occupational exposure to those phthalates. Methods: Phthalate metabolites were analyzed by using column-switching high-performance liquid chromatography tandem mass spectrometry (LC-MS/MS). Results: We detected phthalate metabolites in serum and urine matrices at approximately 10-fold lower than the limit of detection of those metabolites in the same matrix by LC-MS/MS without column switching, which was sufficient to evaluate concentrations of phthalate metabolites for industrial workers and the general population. Conclusion: The accuracy and precision of the analytical method indicate that urinary metabolite determination can be a more acceptable biomarker for studying phthalate exposure and adverse health outcomes.

• The Plant Pathology Journal
• /
• v.25 no.2
• /
• pp.184-188
• /
• 2009

Identification of differently expressed genes under specific tissues and/or environments provides insights into the nature and underlying mechanisms of cellular processes. Although cDNA-AFLP (Amplified Fragment Length Polymorphism) is a powerful method for analyzing differentially expressed genes, its use has been limited to the requirement of radioactive isotope use and the difficulty of isolating the bands of interest from a gel. Here, we describe a modified method for cDNA-AFLP that uses a fluorescence dye for detection and isolation of bands directly from a small size polyacrylamide gel. This method involves three steps: (i) preparation of cDNA templates, (ii) PCR amplification and differential display, and (iii) identification of differentially expressed genes. To demonstrate its utility and efficiency, differentially expressed genes during vegetative growth and appressorial development of Magnaporthe oryzae were analyzed. This method could be applied to compare gene expression profiles in a diverse array of organisms.

• Korean Journal of Optics and Photonics
• /
• v.26 no.4
• /
• pp.187-194
• /
• 2015

A system of infrared camera optics with wide field of view and anamorphic lenses is proposed, and its validity verified through manufacture. The infrared camera produced provides a wide field of view of over 100 degrees in the horizontal direction, and an even greater magnification in the vertical direction. As a result, the system can have a wider surveillance range and improved detection ability at the same time. In addition, a new optomechanical automatic athermalization mechanism is proposed and applied to the infrared camera. Its performance and utility is proved through testing.

• Journal of Electrochemical Science and Technology
• /
• v.11 no.1
• /
• pp.68-83
• /
• 2020

A fast and simple method for synthesis of Cu_xO-ZnO/PPy/RGO nanocomposite by electrochemical manner have been reported in this paper. For testing the utility of this nanocomposite we modified a GCE with the nanocomposite to yield a sensor for simultaneous determination of four analytes namely ascorbic acid (AA), dopamine (DA), uric acid (UA), and folic acid (FA). Cyclic voltammetry (CV) and Differential pulse voltammetry (DPV) selected for the study. The modified electrode cause to enhance electron transfer rate so overcome to overlapping their peaks and consequently having the ability to the simultaneous determination of AA, DA, UA, and FA. To synthesis confirmation of the nanocomposite, Field emission scanning electron microscopy (FE-SEM), Raman spectroscopy, and electrochemical impedance spectroscopy (EIS) were applied. The linearity ranges were 0.07-485 μM, 0.05-430 μM, 0.02-250 μM and 0.022-180 μM for AA, DA, UA, and FA respectively and the detection limits were 22 nM, 10 nM, 5 nM and 6 nM for AA, DA, UA, and FA respectively Also, the obtained electrode can be used for the determination of the AA, DA, UA, and FA in human blood, and human urine real samples.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.3
• /
• pp.975-978
• /
• 2012

P63 is a gene product required in cell cycle regulation which plays vital roles in tumor differentiation. Aims of the present study were to assess the frequency, pattern, sensitivity and specificity of two p63 protein clones P63 4A4 and P63 4A4+Y4A3 in squamous cell carcinomas (SCCs). Thirty cases of head and neck region SCC diagnosed on the basis of H&E staining were examined along with 60 cases of head and neck region biopsies other than squamous cell carcinoma, negative on H&E staining, were taken as control. Immunostaining was performed on slides according to the Thermo Scientific UltraVision LP detection System. P63 4A4+Y4A3 clone is more sensitive 96.6% in comparison to 86% in P63 4A4 with having greater NPV of 98.3%. The results signify the importance of P63 4A4+Y4A3 marker over the old markers and may be used as a confirmatory marker of squamous cell carcinoma.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.4
• /
• pp.39-49
• /
• 2009

Nowadays, according to rapid development of computing environments, information processing and analysis system are very interesting research area. As a viewpoint of data preparation-processing-analysis in knowledge technology, the goal of automated information system is to satisfy high reliability and confidence and to minimize of human-administrator intervention. In addition, we expect the system which can deal with problem and abnormal error effectively as a fault detection and fault tolerance. In this paper, we design a monitoring system as follows. A productive monitoring information from various systems has unstructured forms and characteristics and crawls informative data by conditions and gathering rules. For representing of monitering information which requested by administrator, running-status can be able to check dynamically and systematic like connection/closed status in real-time. Our proposed system can easily correct and processing for monitoring information from various type of server and support to make objective judgement and analysis of administrator under operative target of information system. We implement semi-realtime monitering system using AJAX technology for dynamic browsing of web information and information processing using XML and XPATH. We apply our system to SMS server for checking running status and the system shows that has high utility and reliability.