• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1215-1225
• /
• 2021

Although Artificial Intelligence (AI) techniques have shown impressive performance in various fields, they are vulnerable to adversarial examples which induce misclassification by adding human-imperceptible perturbations to the input. Previous studies to defend the adversarial examples can be classified into three categories: (1) model retraining methods; (2) input transformation methods; and (3) adversarial examples detection methods. However, even though the defense methods against adversarial examples have constantly been proposed, there is no research to classify the type of adversarial attack. In this paper, we proposed an adversarial attack family classification method based on dimensionality reduction and clustering. Specifically, after extracting adversarial perturbation from adversarial example, we performed Linear Discriminant Analysis (LDA) to reduce the dimensionality of adversarial perturbation and performed K-means algorithm to classify the type of adversarial attack family. From the experimental results using MNIST dataset and CIFAR-10 dataset, we show that the proposed method can efficiently classify five tyeps of adversarial attack(FGSM, BIM, PGD, DeepFool, C&W). We also show that the proposed method provides good classification performance even in a situation where the legitimate input to the adversarial example is unknown.

• 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 Industrial Convergence
• /
• v.20 no.9
• /
• pp.99-107
• /
• 2022

This study was conducted to empirically analyze the effect of life behavior and socio-environmental satisfaction on life satisfaction of the elderly with or without hearing loss. To this end, 3,071 elderly people of 「the Survey on the Actual Condition of the Elderly」 in 2020 were set as the subjects. After controlling for their demographic variables, the multiple regression model showed that the elderly with hearing loss had different factors of life behavior and socio-environment satisfaction that affected their life satisfaction compared to those without. As a result, the sub-factors of life behavior in the elderly with hearing loss, such as economic activities, social group activities, the use of the center, and the sub-factors of social environment satisfaction, such as family satisfaction and environmental satisfaction, had a positive (+) effect on life satisfaction. Especially, the elderly with hearing loss had more limitations in both the area of living behavior and the area of social environment satisfaction than the elderly without hearing loss. Therefore, in order to improve the life satisfaction of the elderly with hearing loss, it is suggested that the government and local governments should simultaneously supplement welfare policies and facilities for the elderly with hearing loss.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.555-562
• /
• 2022

This study measured and analyzed the propagation characteristics at frequencies 6, 10, and 17 GHz to discover the new propagation demands in a semi-basement indoor corridor environment for meeting the 4th industrial revolution requirements. The measured indoor environment is a straight corridor consisting of three lecture rooms and glass windows on the outside. The measurement scenario development and measurement system were constructed to match this environment. The transmitting antenna was fixed, and the frequency domain and time domain propagation characteristics were measured and analyzed in the line-of-sight environment based on the distance of the receiving antenna location. In the frequency domain, reliability was determined by the parameters of the floating intercept (FI) path loss model and an R-squared value of 0.5 or more. In the time domain, the root mean square (RMS) delay spread and the cumulative probability of K-factor were used to determine that 6 GHz had high propagation power and 17 GHz had low propagation power. These research results will be effective in providing ultra-connection and ultra-delay artificial intelligence services for WIFI 6, 5G, and future systems in a semi-basement indoor corridor environment.

• 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.

• Knowledge Management Research
• /
• v.24 no.1
• /
• pp.31-49
• /
• 2023

TikTok, as a leading short video platform, has attracted many users, and the resulting attention generates immense business value as a platform to diffuse knowledge. As a qualitative and explorative approach, this study reviews the knowledge payment industry and discusses the influential factors of users' payment decisions regarding knowledge products on TikTok. By conducting in-depth interviews with ten participants and observing 95 knowledge providers' videos, we find that TikTok has significant business potential in the knowledge payment industry. By using the ATLAS. ti software to code the data collected from these interviews, this study finds that demander characteristics (personal needs), product characteristics (product quality), provider characteristics (the key opinion leader effect), and platform characteristics (platform management) are the four core categories that influence users' payment decisions regarding knowledge products on TikTok. A theoretical model consisting of the ten variables of emotional needs, professional needs, quality, price, helpfulness, value, charisma, user trust, service guarantee, and scarcity is proposed based on the grounded theory. The theoretical and practical implications of the study findings are also discussed.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.3
• /
• pp.35-42
• /
• 2022

The N-value from the Standard Penetration Test (SPT), which is one of the representative in-situ test, is an important index that provides basic geological information and the depth of the bearing layer for the design of geotechnical structures. In the aspect of time and cost-effectiveness, there is a need to carry out a representative sampling test. However, the various variability and uncertainty are existing in the soil layer, so it is difficult to grasp the characteristics of the entire field from the limited test results. Thus the spatial interpolation techniques such as Kriging and IDW (inverse distance weighted) have been used for predicting unknown point from existing data. Recently, in order to increase the accuracy of interpolation results, studies that combine the geotechnics and deep learning method have been conducted. In this study, based on the SPT results of about 22,000 holes of ground survey, a comparative study was conducted to predict the depth of the bearing layer using deep learning methods and IDW. The average error among the prediction results of the bearing layer of each analysis model was 3.01 m for IDW, 3.22 m and 2.46 m for fully connected network and PointNet, respectively. The standard deviation was 3.99 for IDW, 3.95 and 3.54 for fully connected network and PointNet. As a result, the point net deep learing algorithm showed improved results compared to IDW and other deep learning method.

• Convergence Security Journal
• /
• v.22 no.5
• /
• pp.69-80
• /
• 2022

Now that climate change and food resource security are becoming issues around the world, smart farms are emerging as an alternative to solve them. In addition, changes in the production environment in the primary industry are a major concern for people engaged in all primary industries (agriculture, livestock, fishery), and the resulting food shortage problem is an important problem that we all need to solve. In order to solve this problem, in the primary industry, efforts are made to solve the food shortage problem through productivity improvement by introducing smart farms using the 4th industrial revolution such as ICT and BT and IoT big data and artificial intelligence technologies. This is done through the public and private sectors.This paper intends to consider the minimum requirements for the smart farm data collection system for the development and utilization of smart farms, the establishment of a sustainable agricultural management system, the sequential system construction method, and the purposeful, efficient and usable data collection system. In particular, we analyze and improve the problems of the data collection system for building a Korean smart farm standard model, which is facing limitations, based on in-depth investigations in the field of livestock and livestock (pig farming) and analysis of various cases, to establish an efficient and usable big data collection system. The goal is to propose a method for collecting big data.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.3
• /
• pp.166-178
• /
• 2023

This study aims to introduce and assess CNN Deep Learning methods to analyze visual landscape images on social media with embedded user perceptions and experiences. This study analyzed visual landscape images by focusing on a healing place. For the study, seven adjectives related to healing were selected through text mining and consideration of previous studies. Subsequently, 50 evaluators were recruited to build a Deep Learning image. Evaluators were asked to collect three images most suitable for 'healing', 'healing landscape', and 'healing place' on portal sites. The collected images were refined and a data augmentation process was applied to build a CNN model. After that, 15,097 images of 'healing' and 'healing landscape' on portal sites were collected and classified to analyze the visual landscape of a healing place. As a result of the study, 'quiet' was the highest in the category except 'other' and 'indoor' with 2,093 (22%), followed by 'open', 'joyful', 'comfortable', 'clean', 'natural', and 'beautiful'. It was found through research that CNN Deep Learning is an analysis method that can derive results from visual landscape image analysis. It also suggested that it is one way to supplement the existing visual landscape analysis method, and suggests in-depth and diverse visual landscape analysis in the future by establishing a landscape image learning dataset.

• Korean Journal of Ecology and Environment
• /
• v.56 no.3
• /
• pp.268-279
• /
• 2023

Nowadays, artificial intelligence model approaches such as machine and deep learning have been widely used to predict variations of water quality in various freshwater bodies. In particular, many researchers have tried to predict the occurrence of cyanobacterial blooms in inland water, which pose a threat to human health and aquatic ecosystems. Therefore, the objective of this study were to: 1) review studies on the application of machine learning models for predicting the occurrence of cyanobacterial blooms and its metabolites and 2) prospect for future study on the prediction of cyanobacteria by machine learning models including deep learning. In this study, a systematic literature search and review were conducted using SCOPUS, which is Elsevier's abstract and citation database. The key results showed that deep learning models were usually used to predict cyanobacterial cells, while machine learning models focused on predicting cyanobacterial metabolites such as concentrations of microcystin, geosmin, and 2-methylisoborneol (2-MIB) in reservoirs. There was a distinct difference in the use of input variables to predict cyanobacterial cells and metabolites. The application of deep learning models through the construction of big data may be encouraged to build accurate models to predict cyanobacterial metabolites.