• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• Health Policy and Management
• /
• v.33 no.4
• /
• pp.440-449
• /
• 2023

Background: This study aimed to analyze the prehospital process and reperfusion therapy process of acute ischemic stroke in Busan metropolitan area and examine the impact of living arrangement on the early management and functional outcomes of acute ischemic stroke (AIS). Methods: The patients who diagnosed with AIS and received reperfusion therapy at the Busan Regional Cardiovascular Center between September 2020 and May 2023 were selected. We investigated the patients' hospital arrival time (onset to door time) and utilization of 119 emergency ambulance services. Additionally, various time matrices related to reperfusion therapy after hospital were examined, along with the functional outcome at the 90-day after treatment. Results: Among the 753 AIS patients who underwent reperfusion therapy, 166 individuals (22.1%) were living alone. AIS patients living alone experienced significant delays in symptom detection (p<0.05) and hospital arrival compared to AIS patients with cohabitants (370.1 minutes vs. 210.2 minutes, p<0.001). There were no significant differences between the two groups in terms of 119 ambulance utilization and time metrics related with the reperfusion therapy. Independent predictors of prognosis in AIS patients were found to be age above 70, National Institutes of Health Stroke Scale score at admission, tissue plasminogen activator, living alone (odds ratio [OR], 1.785; 95% confidence interval [CI], 1.155-2.760) and interhospital transfer (OR, 1.898; 95% CI, 1.152-3.127). Delay in identification of AIS was shown significant correlation (OR, 2.440; 95% CI, 1.070-5.561) at living alone patients. Conclusion: This study revealed that AIS patients living alone in the Busan metropolitan region, requiring endovascular treatment, face challenges in the pre-hospital phase, which significantly impact their prognosis.

• Animal Bioscience
• /
• v.36 no.12
• /
• pp.1796-1805
• /
• 2023

Objective: This study aims to identify heat shock protein70-2 (HSP70-2) and protamine-1 (PRM1) mRNA and protein in Madura bull sperm and demonstrate their relation as bull fertility biomarkers. Methods: The Madura bull fertility rates were grouped based on the percentage of first service conception rate (%FSCR) as high fertility (HF) (79.04%; n = 4), and low fertility (LF) (65.84%; n = 4). mRNA of HSP70-2 and PRM1 with peptidylprolyl isomerase A (PPIA) as a housekeeping gene were determined by quantitative real-time polymerase chain reaction, while enzyme-linked immunoassay was used to measure protein abundance. In the post-thawed semen samples, sperm motility, viability, acrosome integrity, and sperm DNA fragmentation index were analyzed. Data analysis was performed on the measured parameters of semen quality, relative mRNA expression, and protein abundance of HSP70-2 and PRM1, among the bulls with various fertility levels (HF and LF) in a one-way analysis of variance analysis. The Pearson correlation was used to analyze the relationship between semen quality, mRNA, proteins, and fertility rate. Results: Relative mRNA expression and protein abundance of HSP70-2 and PRM1 were detected and were found to be highly expressed in bulls with HF (p<0.05) and were associated with several parameters of semen quality. Conclusion: HSP70-2 and PRM1 mRNA and protein molecules have great potential to serve as molecular markers for determining bull fertility.

• Korean Journal of Agricultural Science
• /
• v.50 no.4
• /
• pp.675-696
• /
• 2023

Terpenoids, also referred to as terpenes, are a large family of naturally occurring chemical compounds present in the essential oils extracted from medicinal plants. In this study, a nondestructive methodology was created by combining ATR-FT-IR (attenuated total reflectance-Fourier transform infrared), and Raman spectroscopy for the terpenoids assessment in medicinal plants essential oils from ten different geographical locations. Partial least squares regression (PLSR) and support vector regression (SVR) were used as machine learning methodologies. However, a deep learning based model called as one-dimensional convolutional neural network (1D CNN) were also developed for models comparison. With a correlation coefficient (R²) of 0.999 and a lowest RMSEP (root mean squared error of prediction) of 0.006% for the prediction datasets, the SVR model created for FT-IR spectral data outperformed both the PLSR and 1 D CNN models. On the other hand, for the classification of essential oils derived from plants collected from various geographical regions, the created SVM (support vector machine) classification model for Raman spectroscopic data obtained an overall classification accuracy of 0.997% which was superior than the FT-IR (0.986%) data. Based on the results we propose that FT-IR spectroscopy, when coupled with the SVR model, has a significant potential for the non-destructive identification of terpenoids in essential oils compared with destructive chemical analysis methods.

• Anatomy and Cell Biology
• /
• v.56 no.1
• /
• pp.86-93
• /
• 2023

Age at death estimation has always been a crucial yet challenging part of identification process in forensic field. The use of human skeletons have long been explored using the principle of macro and micro-architecture change in correlation with increasing age. The clavicle is recommended as the best candidate for accurate age estimation because of its accessibility, time to maturation and minimal effect from weight. Our study applies pre-trained convolutional neural network in order to achieve the most accurate and cost effective age estimation model using clavicular bone. The total of 988 clavicles of Thai population with known age and sex were radiographed using Kodak 9000 Extra-oral Imaging System. The radiographs then went through preprocessing protocol which include region of interest selection and quality assessment. Additional samples were generated using generative adversarial network. The total clavicular images used in this study were 3,999 which were then separated into training and test set, and the test set were subsequently categorized into 7 age groups. GoogLeNet was modified at two layers and fine tuned the parameters. The highest validation accuracy was 89.02% but the test set achieved only 30% accuracy. Our results show that the use of medial clavicular radiographs has a potential in the field of age at death estimation, thus, further study is recommended.

• Ocean and Polar Research
• /
• v.46 no.1
• /
• pp.43-53
• /
• 2024

This study investigated recent seasonal changes in the phytoplankton community in the southern coast of Korea, analyzing monthly samples collected at four stations (St.1-4) in Jinhae Bay from 2017 to 2022. Environmental factors except nutrients were similar each station. Water temperature ranged from 6.0 to 29.0℃ and DO ranged from 2.7 to 11.6 mg L^-1 with salinity ranging from 25.9 to 33.8 psu. There was no significant differences in environmental factors between stations except for nutrients. Phytoplankton cell concentrations ranged from 5.0×10³ cells L^-1 to 7×10⁵ cells L^-1, with patterns similar to chlorophyll-a at each site. Phytoplankton taxa identified here were 42 genera and 77 species, including 49 diatoms, 27 dinoflagellates, and one Dictyochophyceae species. Diatoms dominated throughout all monitoring stations and seasons; however, dinoflagellates exhibited sporadic patterns during spring seasons. Nine harmful phytoplankton were identified, including one diatome Psuedo-nitzschia and eight dinoflagellate Alexandrium spp., Akashiwo sanguinea, Margalefidinium polykrikoides, Dinophysis spp., Gymnodinium spp., Pheopolykrikos hartmannii, Polykrikos kofoidii and Prorocentrum spp. The appearance pattern of the harmful phytoplankton showed a high correlation with seasonal factors. This study provides fundamental data on the composition of phytoplankton and their relationship with environmental factors in Jinhae Bay. In addition, they may be useful for understanding long-term changes in harmful phytoplankton in the southern coasts of Korea.

• Korean Journal of Environment and Ecology
• /
• v.34 no.1
• /
• pp.1-8
• /
• 2020

This study conducted a full survey of the goral population using sensor cameras to identify the exact habitat of the gorals that inhabit Odaesan National Park and for restoration and habitat management-focused conservation projects following the population growth. We surveyed Odaesan National Park for a year in 2018 and selected18 grids (2km×2km) first based on the survey results. We then further divided each grid into four small grids (1km×1km) and installed a total of 62 sensor cameras in 38 small girds divided by four grids(1km×1km). The survey resulted in a total of 5,096 photographed wild animals, 2,268 of which were gorals, and the analysis by the classification table of goral (horn shape (Ⓐ), ring pattern (Ⓑ), ring formation ratio (Ⓒ), and facial color (Ⓓ)) identified a total of 95 animals. The ratio of male and female was 35 males (36.8%), 46 females (48.4%), and 14 sex unknowns (14.7%), while the ratio of female and male excluding sex unknowns was 4 (male):6 (female). The horn shape (Ⓐ) and face color (Ⓓ) were the important factors for distinguishing male and female and identifying individuals. The analysis of the correlation of 81 individuals, excluding 14 individuals of unknown sex, showed a significant difference (r=-0.635, p<0.01). Since the goral population in Odaesan National Park has reached a minimum viable population, it is necessary to change the focus of the management policy of Odaesan National Park from restoration to conservation.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.1
• /
• pp.45-63
• /
• 2019

The number of domestic construction company is expanding every year while the construction workers' exposure to disaster risk is increasing due to technological advancements and popularity of high-rise buildings. In particular, the industry faces greater fatalities and severe large scale accidents because of construction industry characteristics including influx of foreign workers with different language and culture, large number of aged workers, outsourcing, high place work, heavy machine construction. The construction industry is labor-intensive, which is to be completed under given timeline and consists of unique working environment with a lot of night shifts. In addition, when a fixed construction budget is not secured, there is less investment in safety management resulting in poor risk management at the construction site. Taking account that the construction industry has higher accident risk rate and fatality rate, risky and unique working environment, and various labor pool from foreign to aged workers, preemptive safety management through risk factor identification is a mandatory requirement for the construction industry and site. The study analyzes about 8,500 cases of construction accidents that occurred over the past 10 years and identified risk factor by construction industry sector to secure a systematic insight for risk management. Based on interrelation analysis between accident types, work types, original cause materials and assailing materials, there is correlation between each analysis factor and work industry. Especially for work types, there is great correlation between work tasks and industry type. For reinforced concrete and earthwork are among the most frequent types of accidents, and they are not only high in frequency of accidents, but also have a high risk in categories of occurrence.

• Journal of Music and Human Behavior
• /
• v.14 no.2
• /
• pp.1-18
• /
• 2017

The relationships between the ability to understand changes in meaning depending on the prosody of spoken words and the ability to perceive pitch and melodic contour in cochlear implants (CI) recipients were examined. Fifteen postlingual CI recipients were measured in terms of speech prosody perception, speech perception, pitch discrimination (PD), and melody contour identification (MCI). The speech prosody perception test consists of words with positive (PW) and neutral meaning (NW). Participants were asked to identify the meaning of words depending on the conditions of positive and negative prosody. The MCI consists of subtests 1 and 2 with different chance levels to choose. Then, the relationships between speech prosody perception, speech perception, PD, and MCI performance were analyzed. There was a significant difference in identifying the meaning of words expressed in a different prosody between the PW and NW conditions. Speech prosody perception showed a significant correlation with MCI 1 while there was no significant relationship with speech perception. Although speech perception may be possible after CI, limited spoken word comprehension due to decreased sensitivity for prosodic changes may persist in CI recipients. In addition, there was a limitation in perception of melodic contour change compared to pitch discrimination, which is related to speech prosody perception.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.