• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.63-71
• /
• 2020

In this paper, we propose a fire detection technology using YOLOv3 and EfficientDet, the most reliable artificial intelligence detection algorithm recently, an alert service that simultaneously transmits four kinds of notifications: text, web, app and e-mail, and an AWS system that links fire detection and notification service. There are two types of our highly accurate fire detection algorithms; the fire detection model based on YOLOv3, which operates locally, used more than 2000 fire data and learned through data augmentation, and the EfficientDet, which operates in the cloud, has conducted transfer learning on the pretrained model. Four types of notification services were established using AWS service and FCM service; in the case of the web, app, and mail, notifications were received immediately after notification transmission, and in the case of the text messaging system through the base station, the delay time was fast enough within one second. We proved the accuracy of our fire detection technology through fire detection experiments using the fire video, and we also measured the time of fire detection and notification service to check detecting time and notification time. Our AI fire detection and notification service system in this paper is expected to be more accurate and faster than past fire detection systems, which will greatly help secure golden time in the event of fire accidents.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.133-139
• /
• 2021

Currently, the process of constructing a high-definition road map has a high proportion of manual labor, so there are limitations in construction time and cost. Research to automate map production with high-definition road maps using artificial intelligence is being actively conducted, but since the construction of training data for the map construction is also done manually, there is a need to automatically build training data. Therefore, in this study, after converting to images using point clouds acquired by a mobile mapping system, the road marking areas were extracted through image reclassification and overlap analysis using thresholds. Then, a methodology was proposed to automatically construct training data for deep learning data for the high-definition road map through the classification of the polygon types in the extracted regions. As a result of training 2,764 lane data constructed through the proposed methodology on a deep learning-based PointNet model, the training accuracy was 99.977%, and as a result of predicting the lanes of three color types using the trained model, the accuracy was 99.566%. Therefore, it was found that the methodology proposed in this study can efficiently produce training data for high-definition road maps, and it is believed that the map production process of road markings can also be automated.

• Journal of Apiculture
• /
• v.34 no.1
• /
• pp.47-55
• /
• 2019

Honey bees are a vital part of the food chain as the most important pollinators for a broad palette of crops and wild plants. The climate change and colony collapse disorder (CCD) phenomenon make it challenging to develop ICT solutions to predict changes in beehive and alert about potential threats. In this paper, we report the test results of the bee-counting system which stands out against the previous analogues due to its comprehensive components including an improved dual infrared sensor to detect honey bees entering and leaving the hive, environmental sensors that measure ambient and interior, a wireless network with the bluetooth low energy (BLE) to transmit the sensing data in real time to the gateway, and a cloud which accumulate and analyze data. To assess the system accuracy, 3 persons manually counted the outgoing and incoming honey bees using the video record of 360-minute length. The difference between automatic and manual measurements for outgoing and incoming scores were 3.98% and 4.43% respectively. These differences are relatively lower than previous analogues, which inspires a vision that the tested system is a good candidate to use in precise apicultural industry, scientific research and education.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1379-1391
• /
• 2020

UAV in the agricultural application are capable of collecting ultra-high resolution image. It is possible to obtain timeliness images for phenological phases of the crop. However, the UAV uses a variety of sensors and multi-temporal images according to the environment. Therefore, it is essential to use normalized image data for time series image application for crop monitoring. This study analyzed the variability of UAV reflectance and vegetation index according to Aviation Image Making Environment to utilize the UAV multispectral image for agricultural monitoring time series. The variability of the reflectance according to environmental factors such as altitude, direction, time, and cloud was very large, ranging from 8% to 11%, but the vegetation index variability was stable, ranging from 1% to 5%. This phenomenon is believed to have various causes such as the characteristics of the UAV multispectral sensor and the normalization of the post-processing program. In order to utilize the time series of unmanned aerial vehicles, it is recommended to use the same ratio function as the vegetation index, and it is recommended to minimize the variability of time series images by setting the same time, altitude and direction as possible.

• Journal of Korean Society of Archives and Records Management
• /
• v.21 no.4
• /
• pp.137-162
• /
• 2021

This study aimed to examine the perception and experience of researchers in the field of mechanical engineering on research data creation and management, and suggest implications for research data management and services in the field. Research data management and services of domestic and foreign research institutes were investigated, and in-depth interviews were conducted with researchers belonging to domestic mechanical engineering research institutes to analyze the perception and conduction of research data creation and management according to four major categories: "research data, accountable conducting of research and compliance with research ethics, utility and effectiveness of research data management, and the value of sharing research data." To ensure effective research data management and services in mechanical engineering, it is necessary to conduct a data investigation on the process, type, and form of production to collect explicit metadata and implicit contextual information. It is also necessary to propose a plan to recognize research results using the publication of data journals and to prepare infrastructure such as a cloud-based system that supports safe data management and communication between researchers. In addition, it suggests that it is important for various officials in the research field to allocate roles and responsibilities for research data management and services at the organizational level.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.101-125
• /
• 2022

Recently, with the development of computing technology and the improvement of the cloud environment, deep learning technology has developed, and attempts to apply deep learning to various fields are increasing. A typical example is anomaly detection, which is a technique for identifying values or patterns that deviate from normal data. Among the representative types of anomaly detection, it is very difficult to detect a contextual anomaly that requires understanding of the overall situation. In general, detection of anomalies in image data is performed using a pre-trained model trained on large data. However, since this pre-trained model was created by focusing on object classification of images, there is a limit to be applied to anomaly detection that needs to understand complex situations created by various objects. Therefore, in this study, we newly propose a two-step pre-trained model for detecting abnormal situation. Our methodology performs additional learning from image captioning to understand not only mere objects but also the complicated situation created by them. Specifically, the proposed methodology transfers knowledge of the pre-trained model that has learned object classification with ImageNet data to the image captioning model, and uses the caption that describes the situation represented by the image. Afterwards, the weight obtained by learning the situational characteristics through images and captions is extracted and fine-tuning is performed to generate an anomaly detection model. To evaluate the performance of the proposed methodology, an anomaly detection experiment was performed on 400 situational images and the experimental results showed that the proposed methodology was superior in terms of anomaly detection accuracy and F1-score compared to the existing traditional pre-trained model.

• Journal of Industrial Convergence
• /
• v.20 no.6
• /
• pp.27-35
• /
• 2022

The purpose of this study is to analyze the metaverse-related issues in the news big data from an educational perspective, explore their characteristics, and provide implications for the educational applicability of the metaverse and future education. To this end, 41,366 cases of metaverse-related data searched on portal sites were collected, and weight values of all extracted keywords were calculated and ranked using TF-IDF, a representative term weight model, and then word cloud visualization analysis was performed. In addition, major topics were analyzed using topic modeling(LDA), a sophisticated probability-based text mining technique. As a result of the study, topics such as platform industry, future talent, and extension in technology were derived as core issues of the metaverse from an educational perspective. In addition, as a result of performing secondary data analysis under three key themes of technology, job, and education, it was found that metaverse has issues related to education platform innovation, future job innovation, and future competency innovation in future education. This study is meaningful in that it analyzes a vast amount of news big data in stages to draw issues from an education perspective and provide implications for future education.

• Korean Journal of Community Nutrition
• /
• v.27 no.3
• /
• pp.177-191
• /
• 2022

Objectives: Recent epidemiological data reported that young adults in their 20 ~ 30s are a vulnerable population with unhealthy dietary practices and a few signs of deteriorated health indicators. However, there are no dietary guidelines that are specifically developed for the young adult population. This study introduces some data collection tools that are mostly used in the service design field, and demonstrates how these tools can be used in nutrition research for developing dietary guidelines for specific target groups. Methods: To understand the context of food choices among young people, 39 people were enrolled to complete a probes booklet. Thematic analysis and word cloud were performed to capture the main themes from the probes and a persona was developed based on the findings. Results: Data from the probes enabled us to grasp the various contextual meanings of eating practices among young people. Most participants understand what a healthy diet is and often have a willingness to practice it. However, there were very few participants who were following the practices. We created four types of persona for developing dietary guidelines: healthy eating, emotional eating, convenient eating, and trendy eating. Conclusions: Probes and persona were used in order to understand the lives of young adults and develop targeted messages. We hope that this introduction will be helpful to researchers who are looking for new ways of understanding their target population in the field of community nutrition.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.5
• /
• pp.689-699
• /
• 2022

Recently, high productivity capabilities have been improved due to the application of advanced technologies in various industries, but in the construction industry, productivity improvements have been relatively low. Research on advanced technology for the construction industry is being conducted quickly to overcome the current low productivity. Among advanced technologies, 3D scan technology is widely used for creating 3D digital terrain models at construction sites. In particular, the 3D digital terrain model provides basic data for construction automation processes, such as earthwork machine guidance and control. The quality of the 3D digital terrain model has a lot of influence not only on the performance and acquisition environment of the 3D scanner, but also on the denoising, registration and merging process, which is a preprocessing process for creating a 3D digital terrain model after acquiring terrain scan data. Therefore, it is necessary to improve the terrain scan data processing performance. This study seeks to solve the problem of density inhomogeneity in terrain scan data that arises during the pre-processing step. The study suggests a 'pixel-based point cloud comparison algorithm' and verifies the performance of the algorithm using terrain scan data obtained at an actual earthwork site.

• Journal of Bio-Environment Control
• /
• v.31 no.1
• /
• pp.1-7
• /
• 2022

Strawberry is a stand-out cultivating fruit in Korea. The optimum production of strawberry is highly dependent on growing environment. Smart farm technology, and automatic monitoring and control system maintain a favorable environment for strawberry growth in greenhouses, as well as play an important role to improve production. Moreover, physiological parameters of strawberry plant and it is surrounding environment may allow to give an idea on production of strawberry. Therefore, this study intends to build a machine learning model to predict strawberry's yield, cultivated in greenhouse. The environmental parameter like as temperature, humidity and CO₂ and physiological parameters such as length of leaves, number of flowers and fruits and chlorophyll content of 'Seolhyang' (widely growing strawberry cultivar in Korea) were collected from three strawberry greenhouses located in Sacheon of Gyeongsangnam-do during the period of 2019-2020. A predictive model, Lasso regression was designed and validated through 5-fold cross-validation. The current study found that performance of the Lasso regression model is good to predict the number of flowers and fruits, when the MAPE value are 0.511 and 0.488, respectively during the model validation. Overall, the present study demonstrates that using AI based regression model may be convenient for farms and agricultural companies to predict yield of crops with fewer input attributes.