• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.5
• /
• pp.1-11
• /
• 2022

With the development of deep learning technology, various research and development are underway to estimate preference rankings through learning, and it is used in various fields such as web search, gene classification, recommendation system, and image search. Approximation algorithms are used to estimate deep learning-based preference ranking, which builds more than k comparison sets on all comparison targets to ensure proper accuracy, and how to build comparison sets affects learning. In this paper, we propose a k-disjoint comparison set generation algorithm and a k-chain comparison set generation algorithm, a novel algorithm for generating paired comparison sets for crowd-sourcing-based deep learning affinity measurements. In particular, the experiment confirmed that the k-chaining algorithm, like the conventional circular generation algorithm, also has a random nature that can support stable preference evaluation while ensuring connectivity between data.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.9-16
• /
• 2023

In the IoT environment, various objects mutually interactive, and various services can be composed based on this environment. In the previous study, we have developed a resource collaboration system to provide services by substituting limited resources in the user's personal device using resource collaboration. However, in the preceding system, when the number of resources and situations increases, the inference time increases exponentially. To solve this problem, this study proposes a method of classifying users and resources by applying the BIG5 user type classification model. In this paper, we propose a method to reduce the inference time by filtering the user's preferred resources through BIG5 type-based preprocessing and using the filtered resources as an input to the recommendation system. We implement the proposed method as a prototype system and show the validation of our approach through performance and user satisfaction evaluation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.729-738
• /
• 2022

Existing wardrobes have been used only for storing simple clothes. Since it has a function to store clothes, there is only one way to control the environment such as humidity or temperature, and there is only one way to purchase and store items such as a desiccant. In this paper, by increasing the convenience in the existing wardrobe, automatic temperature and humidity control and various convenient functions were added. In line with the smart home market and smart phone application market that have grown over the past several years, along with the development of a wardrobe with sensors, the temperature and humidity control function and other functions inside the wardrobe through Bluetooth pairing between the wardrobe and the smartphone can be customized to the user using a smartphone. Through the clothing selection function and the weather data in the application, we want to implement convenient functions such as the function of recommending clothes in the closet to match the weather.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.2
• /
• pp.313-320
• /
• 2023

The cumulative registration status of dogs is from 1.07 million in 2016 to 2.32 million in 2020. Animal registration is increasing by more than 10% every year, and accordingly, a name must be decided when registering a dog. We want to give a name that fits the characteristics of a dog's appearance, but there are many difficulties in naming it. This paper explains the development of a system for recognizing dog images and recommends dog names based on similar objects or food. This system extracts similarities with dogs' images through models that learn images of various objects and foods, and recommends dog names based on similarities. In addition, by recommending additional related words based on the image data of the result value, it was possible to provide users with various options, increase convenience, and increase interest and fun. Through this system, it is expected that users will be able to solve their concerns about naming their dogs, check names that suit their dogs comfortably, and give them various options through various recommended names to increase satisfaction.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.209-216
• /
• 2023

In this paper, artificial intelligence agents ChatGPT and Stable Diffusion were used to explore the possibility of educational use by implementing a program to recommend picture materials for teaching and learning according to the class topic entered by teachers. The average time spent recommending all picture materials is about 6 minutes. In general, pictures related to keywords were recommended, and the letters in the recommended pictures could only know the intention to represent the letters, and the letters could not be recognized and the meaning could not be known. However, further research seems to be needed on the fact that the type or content of the recommended picture depends entirely on the response of ChatGPT and that it is not possible to accurately recommend the picture for all keywords. In addition, it was concluded that it is true that the recommended picture is related to the keyword, but the evaluation of whether it has educational value is the subject of discussion that should be left to the judgment of human teachers.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.463-468
• /
• 2022

The prolonged of the Post Corona made many industry's paradigm. It's become very important In the industries products that customers directly touch and use. To cope with this situation, The Cosmetics industry has recently introduced various untact services. many customers would like to try these new services. Typically, online survey services recommend personalized products. but these services reached its limit later. This paper research how to recommend products and define skine type with AI Image diagnosis module combine with legacy survey system.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.557-561
• /
• 2021

A meatadata has become an essential element in order to recommend video content to users. However, it is passively generated by video content providers. In the paper, a method for automatically generating metadata was studied in the existing manual metadata input method. In addition to the method of extracting emotion tags in the previous study, a study was conducted on a method for automatically generating metadata for genre and country of production through movie audio. The genre was extracted from the audio spectrogram using the ResNet34 artificial neural network model, a transfer learning model, and the language of the speaker in the movie was detected through speech recognition. Through this, it was possible to confirm the possibility of automatically generating metadata through artificial intelligence.

• Tunnel and Underground Space
• /
• v.33 no.5
• /
• pp.373-387
• /
• 2023

Scientific exploration of extraterrestrial planets has gripped human imagination since the advent of space travel. Human missions to Mars could produce insight into the essential questions of how, when and where life began on Earth. Such missions would only be feasible using local space resources materials, a concept called in situ-resource utilization (ISRU). The purpose of this paper is to provide a thorough review of the currently available Mars soil simulants and to determine those with geotechnical properties most appropriate for vehicle mobility studies. Sourcing and processing are considered since full-scale studies require bulk quantities of material on the order of tens of tons. This review identifies the simulants with the highest fidelity to Mars wind drift soils. In addition, recommendation guide for mars soil simulant development made.

• Steel and Composite Structures
• /
• v.50 no.3
• /
• pp.319-336
• /
• 2024

Ultra-high-performance concrete (UHPC) has attracted increasing attention in prefabricated steel-concrete composite beams as achieving the onsite construction time savings and structural performance improvement. The inferior replacement and removal efficiency of conventional prefabricated steel-UHPC composite beams (PSUCBs) has thwarted its sustainable applications because of the widely used welded-connectors. Single embedded nut bolted shear connectors (SENBs) have recently introduced as an attempt to enhance demountability of PSUCBs. An in-depth exploration of the mechanical behavior of SENBs in UHPC is necessary to evidence feasibilities of corresponding PSUCBs. However, existing research has been limited to SENB arrangement impacts and lacked considerations on SENB geometric configuration counterparts. To this end, this paper performed twenty push-out tests and theoretical analyses on the shear performance and design recommendation of SENBs. Key test parameters comprised the diameter and grade of SENBs, degree and sequence of pretension, concrete casting method and connector type. Test results indicated that both diameters and grades of bolts exerted remarkable impacts on the SENB shear performance with respect to the shear and frictional responses. Also, there was limited influence of the bolt preload degrees on the shear capacity and ductility of SENBs, but non-negligible contributions to their corresponding frictional resistance and initial shear stiffness. Moreover, inverse pretension sequences or monolithic cast slabs presented slight improvements in the ultimate shear and slip capacity. Finally, design-oriented models with higher accuracy were introduced for predictions of the ultimate shear resistance and load-slip relationship of SENBs in PSUCBs.

• The Mathematical Education
• /
• v.63 no.1
• /
• pp.105-122
• /
• 2024

This study analyzed the research trends of 101 articles published in prominent international mathematics education journals over 24 years from 2000, when NCTM's recommendation emphasizing argumentation was released, until September 2023. We first examined the overall trend of argumentation research and then analyzed representative research topics. We found that students were the focus of the studies. However, several studies focused on teachers. More studies were examined in secondary school than in elementary school, and many were conducted in argumentation in classroom contexts. We also found that argumentation research is becoming increasingly popular in international journals. The representative research topics included 'teaching practice,' 'argumentation structure,' 'proof,' 'student understanding,' and 'student reasoning.' Based on our findings, we could categorize three perspectives on argumentation: formal, contextual, and purposeful. This paper concludes with implications on the meaning and role of argumentation in Korean mathematics education.