• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.4
• /
• pp.318-329
• /
• 2022

Plant phenology including flowering, leaf unfolding, and leaf coloring in a forest is important to understand the forest ecosystem. Temperature rise due to recent climate change, however, can lead to plant phenology change as well as snowfall in winter season. Therefore, accurate monitoring of forest environment changes such as plant phenology and snow cover is essential to understand the climate change effect on forest management. These changes can monitor using a digital camera system. This paper introduces the detection methods for plant phenology and snow cover at the mountain region using an unmanned camera system that is a way to monitor the change of forest environment. In this study, the Automatic Mountain Meteorology Stations (AMOS) operated by Korea Forest Service (KFS) were selected as the testbed sites in order to systematize the plant phenology and snow cover detection in complex mountain areas. Multi-directional Internet Protocol (IP) camera system that is a kind of unmanned camera was installed at AMOS located in Seoul, Pyeongchang, Geochang, and Uljin. To detect the forest plant phenology and snow cover, the Red-Green-Blue (RGB) analysis based on the IP camera imagery was developed. The results produced by using image analysis captured from IP camera showed good performance in comparison with in-situ data. This result indicates that the utilization technique of IP camera system can capture the forest environment effectively and can be applied to various forest fields such as secure safety, forest ecosystem and disaster management, forestry, etc.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.41-46
• /
• 2023

Human urine is a process of excreting waste products in the blood, and it is easy to collect and contains various substances. Urinalysis is used to check for diseases, health conditions, and urinary tract infections. There are three methods of urinalysis: physical property test, chemical test, and microscopic test, and chemical test results can be easily confirmed using urine test strips. A variety of items can be tested on the urine test strip, through which various diseases can be identified. Recently, with the spread of smart phones, research on reading urine test strips using smart phones is being conducted. There is a method of detecting and reading the color change of a urine test strip using a smartphone. This method uses the RGB values and the color difference formula to discriminate. However, there is a problem in that accuracy is lowered due to various environmental factors. This paper applies a deep learning model to solve this problem. In particular, color discrimination of a urine test strip is improved in a smartphone using a lightweight CNN (Convolutional Neural Networks) model. CNN is a useful model for image recognition and pattern finding, and a lightweight version is also available. Through this, it is possible to operate a deep learning model on a smartphone and extract accurate urine test results. Urine test strips were taken in various environments to prepare deep learning model training images, and a urine test service application was designed using MobileNet V3.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.38 no.4
• /
• pp.196-203
• /
• 2022

Purpose: This study aimed to evaluate the accuracy and clinical usability of an identification model using deep learning for 79 dental implant types. Materials and Methods: A total of 45396 implant fixture images were collected through panoramic radiographs of patients who received implant treatment from 2001 to 2020 at 30 dental clinics. The collected implant images were 79 types from 18 manufacturers. EfficientNet and Meta Pseudo Labels algorithms were used. For EfficientNet, EfficientNet-B0 and EfficientNet-B4 were used as submodels. For Meta Pseudo Labels, two models were applied according to the widen factor. Top 1 accuracy was measured for EfficientNet and top 1 and top 5 accuracy for Meta Pseudo Labels were measured. Results: EfficientNet-B0 and EfficientNet-B4 showed top 1 accuracy of 89.4. Meta Pseudo Labels 1 showed top 1 accuracy of 87.96, and Meta pseudo labels 2 with increased widen factor showed 88.35. In Top5 Accuracy, the score of Meta Pseudo Labels 1 was 97.90, which was 0.11% higher than 97.79 of Meta Pseudo Labels 2. Conclusion: All four deep learning algorithms used for implant identification in this study showed close to 90% accuracy. In order to increase the clinical applicability of deep learning for implant identification, it will be necessary to collect a wider amount of data and develop a fine-tuned algorithm for implant identification.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.27-35
• /
• 2023

In this paper, we propose a process of increasing productivity by applying a deep learning-based defect detection and classification system to the prepreg fiber manufacturing process, which is in high demand in the field of producing composite materials. In order to apply it to toe prepreg manufacturing equipment that requires a solution due to the occurrence of a large amount of defects in various conditions, the optimal environment was first established by selecting cameras and lights necessary for defect detection and classification model production. In addition, data necessary for the production of multiple classification models were collected and labeled according to normal and defective conditions. The multi-classification model is made based on CNN and applies pre-learning models such as VGGNet, MobileNet, ResNet, etc. to compare performance and identify improvement directions with accuracy and loss graphs. Data augmentation and dropout techniques were applied to identify and improve overfitting problems as major problems. In order to evaluate the performance of the model, a performance evaluation was conducted using the confusion matrix as a performance indicator, and the performance of more than 99% was confirmed. In addition, it checks the classification results for images acquired in real time by applying them to the actual process to check whether the discrimination values are accurately derived.

• The Journal of Society for e-Business Studies
• /
• v.22 no.3
• /
• pp.57-74
• /
• 2017

The Electronic Shelf Label (ESL) is an alternative to the paper price label attached to merchandise shelves and is attracting attention as a retail IoT infrastructure that will lead the innovation of offline retail outlets. In general, when introducing a substitute product, the company tends to consider the financial factors such as the efficiency of the investment cost compared to the existing product or the reduction of the operating cost. However, considering only financial factors in the decision-making process, it may not properly reflect the various values associated with corporate strategy and the requirements of stakeholders. In this study, 8 evaluation items (Investment Cost, Operating Cost, Quality Level, Customer Management, Job Efficiency, Maintenance, Functional Expandability, and Store Image) based on BSC's 4 perspectives (Financial, Customer, Internal Business Process, Learning & Growth), and using AHP (Analytic Hierarchy Process) to measure the priorities of evaluation items for domestic small supermarket employees. As a result of the research, priority was given in order of Customer, Learning & Growth, Internal Business Process, and Financial aspects among the evaluation items for adopting the price label, and the electronic price label was supported with higher importance than the paper price label. In contrast to the priorities of the financial aspects of most prior studies, the items of Learning & growth and customer perspectives have relatively high priorities. In particular, respondents classified by job group, The priorities of the 8 evaluation items were different among the groups. These results are expected to provide implications for both companies (retail outlets) and ESL providers (manufacturers and service providers) who are considering the introduction of ESL.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.485-494
• /
• 2014

Traffic Sign Recognition(TSR) is an important element in an Advanced Driver Assistance System(ADAS). However, many studies related to TSR approaches only in normal daytime environment because a sign's unique color doesn't appear in poor environment such as night time, snow, rain or fog. In this paper, we propose a new TSR algorithm based on machine learning for daytime as well as poor environment. In poor environment, traditional methods which use RGB color region doesn't show good performance. So we extracted sign characteristics using HoG extraction, and detected signs using a Support Vector Machine(SVM). The detected sign is recognized by a decision tree based on 25 reference points in a Normalized RGB system. The detection rate of the proposed system is 96.4% and the recognition rate is 94% when applied in poor environment. The testing was performed on an Intel i5 processor at 3.4 GHz using Full HD resolution images. As a result, the proposed algorithm shows that machine learning based detection and recognition methods can efficiently be used for TSR algorithm even in poor driving environment.

• Journal of the Korean School Mathematics Society
• /
• v.14 no.3
• /
• pp.355-375
• /
• 2011

This paper was designed for the purpose of helping the functional comprehension on the concept of a circumcenter and an incenter of triangle and offering the help for teaching-learning process on their definitions. We analysed the characteristic of the definition on a circumcenter and an incenter of triangle and studied the context, mean and purpose on the definition. The definition focusing on the construction is the definition stressed on the consistency of the concept through the fact that it is possible to draw figure of the concept. And this definition is the thing that consider the extend of the concept from triangle to polygon. Meanwhile this definition can be confused because the concept is not connected with the terminology. The definition focusing on the meaning is easy to memorize the concept because the concept is connected with the terminology but is difficult to search for the concept truth. And this definition is the thing that has the grounds on the occurrence but is taught in a made-knowledge. The definition focusing on both the construction and meaning is the definition that the starting point is vague in the logical proof process. We hope that the results are used to improve the understanding the concept of a circumcenter and an incenter of triangle in the field of mathematical education.

• Economic and Environmental Geology
• /
• v.53 no.4
• /
• pp.479-489
• /
• 2020

A fault is a geological structure that can be a migration path or a cap rock of hydrocarbon such as oil and gas, formed from source rock. The fault is one of the main targets of seismic exploration to find reservoirs in which hydrocarbon have accumulated. However, conventional fault detection methods using lateral discontinuity in seismic data such as semblance, coherence, variance, gradient magnitude and fault likelihood, have problem that professional interpreters have to invest lots of time and computational costs. Therefore, many researchers are conducting various studies to save computational costs and time for fault interpretation, and machine learning technologies attracted attention recently. Among various machine learning technologies, many researchers are conducting fault interpretation studies using the support vector machine, multi-layer perceptron, deep neural networks and convolutional neural networks algorithms. Especially, researchers use not only their own convolution networks but also proven networks in image processing to predict fault locations and fault information such as strike and dip. In this paper, by investigating and analyzing these studies, we found that the convolutional neural networks based on the U-Net from image processing is the most effective one for fault detection and interpretation. Further studies can expect better results from fault detection and interpretation using the convolutional neural networks along with transfer learning and data augmentation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.15-23
• /
• 2017

The person Re-identification is the most challenging part of computer vision due to the significant changes in human pose and background clutter with occlusions. The picture from non-overlapping cameras enhance the difficulty to distinguish some person from the other. To reach a better performance match, most methods use feature selection and distance metrics separately to get discriminative representations and proper distance to describe the similarity between person and kind of ignoring some significant features. This situation has encouraged us to consider a novel method to deal with this problem. In this paper, we proposed an enhanced recurrent neural network with three-tier hierarchical network for person re-identification. Specifically, the proposed recurrent neural network (RNN) model contain an iterative expectation maximum (EM) algorithm and three-tier Hierarchical network to jointly learn both the discriminative features and metrics distance. The iterative EM algorithm can fully use of the feature extraction ability of convolutional neural network (CNN) which is in series before the RNN. By unsupervised learning, the EM framework can change the labels of the patches and train larger datasets. Through the three-tier hierarchical network, the convolutional neural network, recurrent network and pooling layer can jointly be a feature extractor to better train the network. The experimental result shows that comparing with other researchers' approaches in this field, this method also can get a competitive accuracy. The influence of different component of this method will be analyzed and evaluated in the future research.

• Information Systems Review
• /
• v.5 no.2
• /
• pp.241-256
• /
• 2003

This empirical study is to explain critical success factors for building effective regional IT cluster from the literature reviews which have some limitations, and is to suggest new key factors from the views of Regional Innovation System and Sectoral Systems of Innovation. For building successful cluster, the new key factors not only stress on regional networks, the spill-over of tacit knowledge through learning by interacting, institutions which contain regional custom, norms, established practices, culture, and characteristics from the Regional Innovation System, but also emphasize on heterogeneous agents who are interacting by each others from Sectoral Systems of Innovation. From these factors we suggest some strategies for building effective "Daegu IT Cluster" as following; making characterized IT brands which are selected and concentrated based on regional and IT sectoral characteristics, strengthening learning competence of tacit knowledge built in multiple heterogeneous agents network, establishing strong agent networks which are composed of universities, companies, institutes and government, and sharing the institution of mind-opening culture in order to correspond with environmental changes and link to other industrial clusters. By putting above strategies in force, the compatabilities of Daegu region are reinforced. Tacit knowledges spill over and the regional innovation competence are accumulated. Also IT cluster plays core role of employment in Daegu for long term. Especially, "Daegu IT Cluster" changes city's image from medium and small manufacturing city to new industrial city based on high technologies.