• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.4
• /
• pp.257-270
• /
• 2022

In this paper, we design a smart factory risk improvement system and risk improvement method using AI edge devices. The smart factory risk improvement system collects, analyzes, prevents, and promptly responds to the worker's work performance process in the smart factory using AI edge devices, and can reduce the risk that may occur during work with improving the defect rate when workers perfom jobs. In particular, based on worker image information, worker biometric information, equipment operation information, and quality information of manufactured products, it is possible to set an abnormal risk condition, and it is possible to improve the risk so that the work is efficient and for the accurate performance. In addition, all data collected from cameras and IoT sensors inside the smart factory are processed by the AI edge device instead of all data being sent to the cloud, and only necessary data can be transmitted to the cloud, so the processing speed is fast and it has the advantage that security problems are low. Additionally, the use of AI edge devices has the advantage of reducing of data communication costs and the costs of data transmission bandwidth acquisition due to decrease of the amount of data transmission to the cloud.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.241-251
• /
• 2022

Diagnosis and management of customer's skin condition is an important essential function in the cosmetics and beauty industry. As the social media environment spreads and generalizes to all fields of society, the interaction of questions and answers to various and delicate concerns and requirements regarding the diagnosis and management of skin conditions is being actively dealt with in the social media community. However, since social media information is very diverse and atypical big data, an intelligent skin condition diagnosis system that combines appropriate skin condition information analysis and artificial intelligence technology is necessary. In this paper, we developed the skin condition diagnosis system SCDIS to intelligently diagnose and manage the skin condition of customers by processing the text analysis information of social media into learning data. In SCDIS, an artificial neural network model, AnnTFIDF, that automatically diagnoses skin condition types using artificial neural network technology, a deep learning machine learning method, was built up and used. The performance of the artificial neural network model AnnTFIDF was analyzed using test sample data, and the accuracy of the skin condition type diagnosis prediction value showed a high performance of about 95%. Through the experimental and performance analysis results of this paper, SCDIS can be evaluated as an intelligent tool that can be used efficiently in the skin condition analysis and diagnosis management process in the cosmetic and beauty industry. And this study can be used as a basic research to solve the new technology trend, customized cosmetics manufacturing and consumer-oriented beauty industry technology demand.

• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.115-127
• /
• 2021

With the development of science and technology around the world, the realm of cyberspace, following land, sea, air, and space, is also recognized as a battlefield area. Accordingly, it is necessary to design and establish various elements such as definitions, systems, procedures, and plans for not only physical operations in land, sea, air, and space but also cyber operations in cyberspace. In this research, the importance of cyber targets that can be considered when prioritizing the list of cyber targets selected through intermediate target development in the target development and prioritization stage of targeting processing of cyber operations was selected as a factor to be considered. We propose a method to calculate the score for the cyber target and use it as a part of the cyber target prioritization score. Accordingly, in the cyber target prioritization process, the cyber target importance category is set, and the cyber target importance concept and reference item are derived. We propose a TIR (Target Importance Rank) algorithm that synthesizes parameters such as Event Prioritization Framework based on PageRank algorithm for score calculation and synthesis for each derived standard item. And, by constructing the Stuxnet case-based network topology and scenario data, a cyber target importance score is derived with the proposed algorithm, and the cyber target is prioritized to verify the proposed algorithm.

• Journal of Korean Society of Disaster and Security
• /
• v.15 no.3
• /
• pp.79-88
• /
• 2022

Cable-supported bridges, as important large infrastructures, require a long-term and systematic maintenance strategy. In particular, various methods have been proposed to secure safety for the bridges, such as installing various types of sensor on members in the bridges, and setting management thresholds. It is evidently necessary to propose a strategic plan to efficiently manage increasing number of cable-supported bridges and data collected from a number of sensors. This study aims to develop an analysis tool that can automatically remove abnormal signals and calculate statistical results for the purpose of efficiently analyzing a wide range of data collected from a long span bridge measurement system. To develop the tool, basic information such as the types and quantity of sensors installed in long span bridges and signal characteristics of the collected data were analyzed. Thereafter, the Humpel filtering method was used to determine the presence or absence of an abnormality in the signal and then filtered. The statistical results with filtered data were shown. Finally, one cable-stayed bridge and one suspension bridge currently in use were chosen as the target bridges to verify the performance of the developed tool. Signal processing and statistical analysis with the tool were performed. The results are similar to the results reported in the existing work.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.8
• /
• pp.249-258
• /
• 2022

Since the advent of Bitcoin, various virtual assets have been actively traded through virtual asset services of virtual asset exchanges. Recently, security accidents have frequently occurred in virtual asset exchanges, so the government is obligated to obtain information security management system (ISMS) certification to strengthen information protection of virtual asset exchanges, and 56 additional specialized items have been established. In this paper, we compared the domain importance of ISMS and CryptoCurrency Security Standard (CCSS) which is a set of requirements for all information systems that make use of cryptocurrencies, and analyzed the results after mapping them to gain insight into the characteristics of each certification system. Improvements for 4 items of High Level were derived by classifying the priorities for improvement items into 3 stages: High, Medium, and Low. These results can provide priority for virtual asset and information system security, support method and systematic decision-making on improvement of certified items, and contribute to vitalization of virtual asset transactions by enhancing the reliability and safety of virtual asset services.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.39 no.4
• /
• pp.348-352
• /
• 1994

Soybean seed consists of two major storage protein, the 7S and 11S globulins. For improving the quality of soybean seed protein, an increase of 11S/7S ratio would be a desirable objective because the 11S globulin contains much more the sulfur-containing amino acids than the 7S globulin. In this study, some soybean varieties were used to investigate the analyzing method for 7S and 11S globulins. 7S and 11S globulins couble be fractionated by their different solubilities in tris buffers. Adjusting the pH and tris concentration were major factors affecting the precipitation of the two globulins. And it was possible to screen the soybean genotypes having aberrant subunit compositions of the two globulins by an sodium dodecyl sulfate polyacrylamide gel electrophoresis (SDS-PAGE) of total soybean proteins. The ratio of 11S to 7S globulin ranged from 1.29 to 1.38. This paper also dealed with the contribution of protein components in soybean seeds to the physical properties of soycurd. It indicated that the soycurd from crude 11S was remarkably harder than that from crude 7S, and springiness and cohesiveness were slightly higher in soycurd having higher proportion of 11S. So, it may concluded that proportion of protein components in soybean seed can be important factor which controls the suitability for soycurd or other foods.

• Journal of Dairy Science and Biotechnology
• /
• v.41 no.1
• /
• pp.9-25
• /
• 2023

Yogurt fermentation is known to be beneficial because it provides a low pH and harsh environment for foodborne pathogens and improves organoleptic properties. Additionally, organic acids produced through fermentation have a good effect on the viscosity and gelling properties of yogurt. Several potential health benefits of probiotic and generally recognized as safe strains have been suggested. Yogurt is the preferred vehicle for delivering probiotics to health-conscious consumers. Therefore, manufacturers of probiotic beverages must comply with the relevant regulations. The development of probiotic yogurt begins with the selection of strains with safety and functional properties of probiotics. The selected probiotic strain should be technically suitable for viability and improve organoleptic quality while maintaining the number of bacteria above the standard value during processing and storage conditions. In addition, the efficacy of probiotic strains contained in yogurt should be investigated, confirmed, and approved according to well-designed clinical trials. Although various methods are used to detect probiotic strains, the recently widely used next generation sequencing method can be actively utilized. In the future, more research should be conducted with the latest methods to identify probiotic functions and accurately detect probiotic strains.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.41-49
• /
• 2023

A convolutional neural network (CNN) is a representative algorithm for implementing artificial neural networks. CNNs have improved on the issues of rapid increase in calculation amount and low object classification rates, which are associated with a conventional multi-layered fully-connected neural network (FNN). However, because of the rapid development of IT devices, the maximum resolution of images captured by current smartphone and tablet cameras has reached 108 million pixels (MP). Specifically, a traditional CNN algorithm requires a significant cost and time to learn and process simple, high-resolution images. Therefore, this study proposes an improved CNN algorithm for implementing an object classification learning model for simple, high-resolution images. The proposed method alters the adjacency matrix value of the pooling layer's max pooling operation for the CNN algorithm to reduce the high-resolution image learning model's creation time. This study implemented a learning model capable of processing 4, 8, and 12 MP high-resolution images for each altered matrix value. The performance evaluation result showed that the creation time of the learning model implemented with the proposed algorithm decreased by 36.26% for 12 MP images. Compared to the conventional model, the proposed learning model's object recognition accuracy and loss rate were less than 1%, which is within the acceptable error range. Practical verification is necessary through future studies by implementing a learning model with more varied image types and a larger amount of image data than those used in this study.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.27-40
• /
• 2023

With the increase in the spread of smart devices and the impact of COVID-19, the consumption of media contents through smart devices has significantly increased. Along with this trend, the amount of media contents viewed through OTT platforms is increasing, that makes contents recommendations on these platforms more important. Previous contents-based recommendation researches have mostly utilized metadata that describes the characteristics of the contents, with a shortage of researches that utilize the contents' own descriptive metadata. In this paper, various text data including titles and synopses that describe the contents were used to recommend similar contents. KLUE-RoBERTa-large, a Korean language model with excellent performance, was used to train the model on the text data. A dataset of over 20,000 contents metadata including titles, synopses, composite genres, directors, actors, and hash tags information was used as training data. To enter the various text features into the language model, the features were concatenated using special tokens that indicate each feature. The test set was designed to promote the relative and objective nature of the model's similarity classification ability by using the three contents comparison method and applying multiple inspections to label the test set. Genres classification and hash tag classification prediction tasks were used to fine-tune the embeddings for the contents meta text data. As a result, the hash tag classification model showed an accuracy of over 90% based on the similarity test set, which was more than 9% better than the baseline language model. Through hash tag classification training, it was found that the language model's ability to classify similar contents was improved, which demonstrated the value of using a language model for the contents-based filtering.