• Journal of Nutrition and Health
• /
• v.41 no.6
• /
• pp.561-572
• /
• 2008

Currently, Korea is facing dramatic nutrition transition among children, which may increase risk of degenerative diseases due to excessive intakes of fats, sugars and sodium. Promotion of eating healthier foods among children is difficult because the present nutrition label is not easily understood. Therefore, to promote healthier foods this study was aimed at developing guidance of standard amounts of high, medium and low levels of sugars, sodium, fats and other components contained in foods or drinks that are promoted to or formulated for consumption by children. Multipronged approach was used to collecting information, including key word searches in Medline and other databases, internet searches, reports from world organization, and contact of key individuals who work in organizations. We reviewed dietary reference intakes for Koreans, nutrient reference values, nutrient content claims of nutrition labeling, guideline daily amounts of United Kingdom, dietary guidelines and consumption data of nutrients, and selected components for labeling. And we decided goals of guideline daily amounts for children and nutrient criteria to underpin the high, medium and low content of each component. Then we collected data on processed foods sold at 12 middle schools and 11 high schools in Seoul, and classified processed foods into food category. Sales per one student per day were in the order of snacks, breads, and non-carbonated drinks. One hundred forty five mostly consumed products were selected and classified into criteria of high, medium and low total fat or sodium. Eighty five(58.6%) were classified into high fat food and only 11(7.6%) into high sodium food, in case that the base is chosen per 100 g or 100 mL. In conclusion, the nutrient criteria and choice of 100 g base, which we suggest in this study, need to be tested by simulation with more processed foods and refined in view of the practical issues suggested by stakeholders in future.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.117-126
• /
• 2020

A maritime object detection system is an intelligent assistance system to maritime autonomous surface ship(MASS). It detects automatically floating debris, which has a clash risk with objects in the surrounding water and used to be checked by a captain with a naked eye, at a similar level of accuracy to the human check method. It is used to detect objects around a ship. In the past, they were detected with information gathered from radars or sonar devices. With the development of artificial intelligence technology, intelligent CCTV installed in a ship are used to detect various types of floating debris on the course of sailing. If the speed of processing video data slows down due to the various requirements and complexity of MASS, however, there is no guarantee for safety as well as smooth service support. Trying to solve this issue, this study conducted research on the minimization of computation volumes for video data and the increased speed of data processing to detect maritime objects. Unlike previous studies that used the Hough transform algorithm to find the horizon and secure the areas of interest for the concerned objects, the present study proposed a new method of optimizing a binarization algorithm and finding areas whose locations were similar to actual objects in order to improve the speed. A maritime object detection system was materialized based on deep learning CNN to demonstrate the usefulness of the proposed method and assess the performance of the algorithm. The proposed algorithm performed at a speed that was 4 times faster than the old method while keeping the detection accuracy of the old method.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.4
• /
• pp.331-339
• /
• 2013

LiDAR has been one of the widely used and important technologies for 3D modeling of ground surface and objects because of its ability to provide dense and accurate range measurement. The objective of this research is to develop a method for automatic detection and modeling of railroad power lines using high density LiDAR data and RANSAC algorithms. For detecting railroad power lines, multi-echoes properties of laser data and shape knowledge of railroad power lines were employed. Cuboid analysis for detecting seed line segments, tracking lines, connecting and labeling are the main processes. For modeling railroad power lines, iterative RANSAC and least square adjustment were carried out to estimate the lines parameters. The validation of the result is very challenging due to the difficulties in determining the actual references on the ground surface. Standard deviations of 8cm and 5cm for x-y and z coordinates, respectively are satisfactory outcomes. In case of completeness, the result of visual inspection shows that all the lines are detected and modeled well as compare with the original point clouds. The overall processes are fully automated and the methods manage any state of railroad wires efficiently.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.3
• /
• pp.600-611
• /
• 1996

Recently, neural network-based speech recognition has been studied to utilize the adaptivity and learnability of neural network models. However, conventional neural network models have difficulty in the co-articulation processing and the boundary detection of similar phonmes of the Korean speech. Also, in case of using one phonotopic map, learning speed may dramatically increase and inaccuracies may be caused because homogeneous learning and recognition method should be applied for heterogenous data. Hence, in this paper, a neural net typewriter has been designed using a hierarchical self-organizing classifier(HSOC), and related algorithms are presented. This HSOC, during its learing stage, distributed phoneme data on hierarchically structured multiple phonotopic maps, using Kohonen's self-organizing feature maps(SOFM). Presented and experimented in this paper were the algorithms for deciding the number of maps, map sizes, the selection of phonemes and their placement per map, an approapriate learning and preprocessing method per map. If maps are divided according to a priorlinguistic knowledge, we would have difficulty in acquiring linguistic knowledge and how to alpply it(e.g., processing extended phonemes). Contrarily, our HSOC has an advantage that multiple phonotopic maps suitable for given input data are self-organizable. The resulting three korean phonotopic maps are optimally labelled and have their own optimal preprocessing schemes, and also confirm to the conventional linguistic knowledge.

• Journal of Nutrition and Health
• /
• v.47 no.3
• /
• pp.193-205
• /
• 2014

Purpose: This study was conducted in order to investigate nutrient and food intake status and dietary quality in Korean adults according to nutrition label utilization. Methods: We analyzed data from the combined 2010-2011 KNHANES (Korean National Health and Nutrition Examination Survey). The analysis included 8190 adults aged 19 to 64 years. In this study, according to nutrition label utilization, we classified the subjects according to the "non-utilization of nutrition label (NUNL)" group (male, n = 2716, female, n = 3147), "identification of nutrition label (INL)" group (male, n = 143, female, n = 330), and "Utilization of nutrition label (UNL)" group (male, n = 363, female, n = 1491). Nutrient and food group intake, NAR (nutrient adequacy ratio), MAR (mean adequacy ratio), and INQ (index of nutritional quality) were analyzed using data from the 24-recall method. Results: Results of this study showed that subjects in the NUNL group were significantly more likely to drink alcohol compared with the other two groups. The NUNL group showed a significantly higher frequency of consuming instant noodles, Soju (male), and carbonated drink (female) than the UNL group, whereas the NUNL group showed a significantly lower frequency of consuming milk, soymilk, and yogurt than the UNL group. In addition, regarding diet quality (NAR and INQ), significantly lower vitamin $B_2$, vitamin C, and calcium was observed in the NUNL group compared with the UNL group. For both male and female, significantly higher MAR was observed in the UNL group than in the NUNL group. The NUNL group showed significantly lower consumption of milk compared to the UNL group. Conclusion: Good dietary practice such as referring to nutrition labels and its influence can affect the quality of nutritional intake and selection of food, while it can also provide basic data for specific nutrition education regarding use of nutrition labeling.

• Journal of Advanced Navigation Technology
• /
• v.25 no.1
• /
• pp.115-123
• /
• 2021

Pine nuts are Korea's representative nut forest products and profitable crops. However, pine nuts are harvested by climbing the trees themselves, thus the risk is high. In order to solve this problem, it is necessary to harvest pine nuts using a robot or an unmanned aerial vehicle(UAV). In this paper, we propose a deep learning based detection method for harvesting pine nut in UAV aerial images. For this, a video was recorded in a real pine forest using UAV, and a data augmentation technique was used to supplement a small number of data. As the data for 3D detection, Unity3D was used to model the virtual pine nut and the virtual environment, and the labeling was acquired using the 3D transformation method of the coordinate system. Deep learning algorithms for detection of pine nuts distribution area and 2D and 3D detection of pine nuts objects were used DeepLabV3+, YOLOv4, and CenterNet, respectively. As a result of the experiment, the detection rate of pine nuts distribution area was 82.15%, the 2D detection rate was 86.93%, and the 3D detection rate was 59.45%.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.26 no.4
• /
• pp.307-326
• /
• 2021

Real-time sea level observations from tide gauges include missing and erroneous values. Classification as abnormal values can be done for the latter by the quality control procedure. Although the 3𝜎 (three standard deviations) rule has been applied in general to eliminate them, it is difficult to apply it to the sea-level data where extreme values can exist due to weather events, etc., or where erroneous values can exist even within the 3𝜎 range. An artificial intelligence model set designed in this study consists of non-annotated recurrent neural networks and ensemble techniques that do not require pre-labeling of the abnormal values. The developed model can identify an erroneous value less than 20 minutes of tide gauge recording an abnormal sea level. The validated model well separates normal and abnormal values during normal times and weather events. It was also confirmed that abnormal values can be detected even in the period of years when the sea level data have not been used for training. The artificial neural network algorithm utilized in this study is not limited to the coastal sea level, and hence it can be extended to the detection model of erroneous values in various oceanic and atmospheric data.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1407-1422
• /
• 2022

This study was conducted to classify tree species and assess the classification accuracy, using SE-Inception, a classification-based deep learning model. The input images of the dataset used Worldview-3 and GeoEye-1 images, and the size of the input images was divided into 10 × 10 m, 30 × 30 m, and 50 × 50 m to compare and evaluate the accuracy of classification of tree species. The label data was divided into five tree species (Pinus densiflora, Pinus koraiensis, Larix kaempferi, Abies holophylla Maxim. and Quercus) by visually interpreting the divided image, and then labeling was performed manually. The dataset constructed a total of 2,429 images, of which about 85% was used as learning data and about 15% as verification data. As a result of classification using the deep learning model, the overall accuracy of up to 78% was achieved when using the Worldview-3 image, the accuracy of up to 84% when using the GeoEye-1 image, and the classification accuracy was high performance. In particular, Quercus showed high accuracy of more than 85% in F₁ regardless of the input image size, but trees with similar spectral characteristics such as Pinus densiflora and Pinus koraiensis had many errors. Therefore, there may be limitations in extracting feature amount only with spectral information of satellite images, and classification accuracy may be improved by using images containing various pattern information such as vegetation index and Gray-Level Co-occurrence Matrix (GLCM).

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1177-1185
• /
• 2022

The water and sewage system is an infrastructure that provides safe and clean water to people. In particular, since the water and sewage pipelines are buried underground, it is very difficult to detect system defects. For this reason, the diagnosis of pipelines is limited to post-defect detection, such as system diagnosis based on the images taken after taking pictures and videos with cameras and drones inside the pipelines. Therefore, real-time detection technology of pipelines is required. Recently, pipeline diagnosis technology using advanced equipment and artificial intelligence techniques is being developed, but AI-based defect detection technology requires a variety of learning data because the types and numbers of defect data affect the detection performance. Therefore, in this study, various defect scenarios are implemented using 3D printing model to improve the detection performance when detecting defects in pipelines. Afterwards, the collected images are performed to pre-processing such as classification according to the degree of risk and labeling of objects, and real-time defect detection is performed. The proposed technique can provide real-time feedback in the pipeline defect detection process, and it would be minimizing the possibility of missing diagnoses and improve the existing water and sewerage pipe diagnosis processing capability.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.183-192
• /
• 2023

The remotely sensed data, such as satellite imagery and aerial photos, can be used to extract and detect some objects in the image through image interpretation and processing techniques. Significantly, the possibility for utilizing digital map updating and land monitoring has been increased through automatic object detection since spatial resolution of remotely sensed data has improved and technologies about deep learning have been developed. In this paper, we tried to extract plastic greenhouses into aerial orthophotos by using fully convolutional densely connected convolutional network (FC-DenseNet), one of the representative deep learning models for semantic segmentation. Then, a quantitative analysis of extraction results had performed. Using the farm map of the Ministry of Agriculture, Food and Rural Affairsin Korea, training data was generated by labeling plastic greenhouses into Damyang and Miryang areas. And then, FC-DenseNet was trained through a training dataset. To apply the deep learning model in the remotely sensed imagery, instance norm, which can maintain the spectral characteristics of bands, was used as normalization. In addition, optimal weights for each band were determined by adding attention modules in the deep learning model. In the experiments, it was found that a deep learning model can extract plastic greenhouses. These results can be applied to digital map updating of Farm-map and landcover maps.