• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.391-404
• /
• 2021

This study developed a long-term prediction model for the potential yield of garlic based on a genetic algorithm (GA) by utilizing global climate reanalysis data. The GA is used for digging the inherent signals from global climate reanalysis data which are both directly and indirectly connected with the garlic yield potential. Our results indicate that both deterministic and probabilistic forecasts reasonably capture the inter-annual variability of crop yields with temporal correlation coefficients significant at 99% confidence level and superior categorical forecast skill with a hit rate of 93.3% for 2 × 2 and 73.3% for 3 × 3 contingency tables. Furthermore, the GA method, which considers linear and non-linear relationships between predictors and predictands, shows superiority of forecast skill in terms of both stability and skill scores compared with linear method. Since our result can predict the potential yield before the start of farming, it is expected to help establish a long-term plan to stabilize the demand and price of agricultural products and prepare countermeasures for possible problems in advance.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.308-317
• /
• 2022

Researches are underway to efficiently reduce the size of video data transmitted and stored in the image analysis process using deep learning-based machine vision technology. MPEG (Moving Picture Expert Group) has newly established a standardization project called VCM (Video Coding for Machine) and is conducting research on video encoding for machines rather than video encoding for humans. We are researching a multitask that performs various tasks with one image input. The proposed pipeline does not perform all object detection of each task that should precede object detection, but precedes it only once and uses the result as an input for each task. In this paper, we propose a pipeline for efficient multitasking and perform comparative experiments on compression efficiency, execution time, and result accuracy of the input image to check the efficiency. As a result of the experiment, the capacity of the input image decreased by more than 97.5%, while the accuracy of the result decreased slightly, confirming the possibility of efficient multitasking.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.77-86
• /
• 2022

The Republic of Korea is a country in which coastal surveillance is an imperative national task as it is surrounded by seas on three sides under the confrontation between South and North Korea. However, due to Defense Reform 2.0, the number of R/D (Radar) operating personnel has decreased, and the period of service has also been shortened. Moreover, there is always a possibility that a human error will occur. This paper presents specific guidelines for developing an AI learning model for the intelligent coastal surveillance system. We present a three-step strategy to realize the guidelines. The first stage is a typical stage of building an AI learning model, including data collection, storage, filtering, purification, and data transformation. In the second stage, R/D signal analysis is first performed. Subsequently, AI learning model development for classifying real and false images, coastal area analysis, and vulnerable area/time analysis are performed. In the final stage, validation, visualization, and demonstration of the AI learning model are performed. Through this research, the first achievement of making the existing weapon system intelligent by applying the application of AI technology was achieved.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.263-278
• /
• 2022

With the recent advent of IoT technology, automatic pet feeders are being distributed so that owners can feed their companion animals while they are out. However, due to behaviors of pets, the method of measuring weight, which is important in automatic feeding, can be easily damaged and broken when using the scale. The 3D camera method has disadvantages due to its cost, and the 2D camera method has relatively poor accuracy when compared to 3D camera method. Hence, the purpose of this study is to propose a deep learning approach that can accurately estimate weight while simply using a 2D camera. For this, various convolutional neural networks were used, and among them, the ResNet101-based model showed the best performance: an average absolute error of 3.06 grams and an average absolute ratio error of 3.40%, which could be used commercially in terms of technical and financial viability. The result of this study can be useful for the practitioners to predict the weight of a standardized object such as feed only through an easy 2D image.

• Trans-
• /
• v.12
• /
• pp.81-106
• /
• 2022

The possibility of metaverse system to be a catalyst for hyper-connected society will be dependent on the speed of connected technological development and its social utilization in the same manner as AI technology. Putting these technical realization processes in brackets, this paper focus on some philosophical-political issues in connection with cognitive-ecological changes in the future cinema which will be influenced by the complexive techno-socio couples of accelerated development of metaverse system. Generally speaking, essence of metaverse system seems to be the degree of immersion by technical accuracy, but is not true. In perspective of cognitive-ecology, flow degree of a picture or photograph is relied not on 'accuracy of representation' but on its message's contextual link-up. In this aspect, real potentiality of metaverse system shall be understood in the context of cognitive-ecological changes of human brain's multi-intelligence networking abilities(intersection of augmentation-simulation and outside-inside) which will be activated in the new structure of natural-social-technological coupling of metaverse system. These cognitive-ecological potentialities have been partially actualized in the cinematic process of tripod mimesis for the longest time, [real contradiction/conflicts (Mimesis-1) -->fictional solutions of cinema (Mimesis-2) --> selective interpretation of spectator's wish fulfillment (Mimesis-3) --> real change (Mimesis-1')]. Therefore metaverse's real potentiality must be considered to be dependent on the possibility of deepening and extending of cinematic circulation between real seperation/problems and ideal connection/solutions. In this context, advanced metaverse system can be compared as a modern technical version of ideal circulation of physics and metaphysics

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.511-521
• /
• 2022

Cloud detection and removal from satellite images is an essential process for topographic observation and analysis. Threshold-based cloud detection techniques show stable performance because they detect using the physical characteristics of clouds, but they have the disadvantage of requiring all channels' images and long computational time. Cloud detection techniques using deep learning, which have been studied recently, show short computational time and excellent performance even using only four or less channel (RGB, NIR) images. In this paper, we confirm the performance dependence of the deep learning network according to the heterogeneous learning dataset with different resolutions. The DeepLabV3+ network was improved so that channel features of cloud detection were extracted and learned with two published heterogeneous datasets and mixed data respectively. As a result of the experiment, clouds' Jaccard index was low in a network that learned with different kind of images from test images. However, clouds' Jaccard index was high in a network learned with mixed data that added some of the same kind of test data. Clouds are not structured in a shape, so reflecting channel features in learning is more effective in cloud detection than spatial features. It is necessary to learn channel features of each satellite sensors for cloud detection. Therefore, cloud detection of heterogeneous sensors with different resolutions is very dependent on the learning dataset.

• Journal of the Korea Society for Simulation
• /
• v.31 no.3
• /
• pp.55-61
• /
• 2022

Currently police and fire departments use a Network/Wifi/GPS based emergency location positioning system established by mobile carriers to directly link with the device of the people who request the rescue to accurately position the expected location in the call area. However in the case of mountain rescue it is difficult to rescue the victim in golden time because the location of the search area cannot be limited when the victim is located in a radio shadow area of the mountain or the device power is off and this situation become worse if victim fail to report 911 by himself due to the injury. In this paper, we are expected to solve the previous problem by propose the mobile telecommunication forensic simulator consist of time series of cell information, human mobility model which include some general and specific features (age, gender, behavioral characteristics of victim, etc.) and intelligent infer system. The results of analysis appear in heatmap of polygons on the map based on the probability of the expected location information of the victim. With this technology we are expected to contribute to rapid and accurate lifesaving by reducing the search area of rescue team.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.5
• /
• pp.157-166
• /
• 2022

Exercise is necessary for a healthy life, but it is recommended that it be conducted in a non-face-to-face environment in the context of an epidemic such as COVID-19. However, in the existing non-face-to-face exercise content, it is possible to recognize exercise movements, but the process of interpreting and providing feedback information is not automated. Therefore, in this paper, to solve this problem, we propose a method of creating a formalized rule to track the contents of exercise and the motions that constitute it. To make such a rule, first make a rule for the overall exercise content, and then create a tracking rule for the motions that make up the exercise. A motion tracking rule can be created by dividing the motion into steps and defining a key frame pose that divides the steps, and creating a transition rule between states and states represented by the key frame poses. The rules created in this way are premised on the use of posture and motion recognition technology using motion capture equipment, and are used for logical development for automation of application of these technologies. By using the rules proposed in this paper, not only recognizing the motions appearing in the exercise process, but also automating the interpretation of the entire motion process, making it possible to produce more advanced contents such as an artificial intelligence training system. Accordingly, the quality of feedback on the exercise process can be improved.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.125-134
• /
• 2022

The development of information communication and artificial intelligence technology requires the intelligent command and control (C2) system for Korean military, and various studies are attempted to achieve it. In particular, as a volume ofinformation in the C2 workflow increases exponentially, this study pays attention to the collaborative filtering (CF) and recommendation systems (RS) that can provide the essential information for the users of the C2 system has been developed. The RS performing information filtering in the C2 system should provide an explanatory recommendation and consider the context of the tasks and users. In this paper, we propose a contextual pre-filtering CARS framework that recommends information in the C2 workflow. The proposed framework consists of four components: 1) contextual pre-filtering that filters data in advance based on the context and relationship of the users, 2) feature selection to overcome the data sparseness that is a weak point for the CF, 3) the proposed CF with the features distances between the users used to calculate user similarity, and 4) rule-based post filtering to reflect user preferences. In order to evaluate the superiority of this study, various distance methods of the existing CF method were compared to the proposed framework with two experimental datasets in real-world. As a result of comparative experiments, it was shown that the proposed framework was superior in terms of MAE, MSE, and MSLE.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.185-207
• /
• 2022

Recently, with the development of deep learning technology, researches to apply a deep learning algorithm to analyze unstructured data such as text and images are being actively conducted. Text classification has been studied for a long time in academia and industry, and various attempts are being performed to utilize data characteristics to improve classification performance. In particular, a hierarchical relationship of labels has been utilized for hierarchical classification. However, the top-down approach mainly used for hierarchical classification has a limitation that misclassification at a higher level blocks the opportunity for correct classification at a lower level. Therefore, in this study, we propose a methodology for classifying hierarchical data using the autoencoder-based deeply supervised network that high-level classification does not block the low-level classification while considering the hierarchical relationship of labels. The proposed methodology adds a main classifier that predicts a low-level label to the autoencoder's latent variable and an auxiliary classifier that predicts a high-level label to the hidden layer of the autoencoder. As a result of experiments on 22,512 academic papers to evaluate the performance of the proposed methodology, it was confirmed that the proposed model showed superior classification accuracy and F1-score compared to the traditional supervised autoencoder and DNN model.