• Journal of the Korean Recycled Construction Resources Institute
• /
• v.10 no.4
• /
• pp.539-546
• /
• 2022

The current ｢Detailed guidelines for the safety and maintenance of facilities (performance Evaluation)｣ prescribes that the durability of surface concrete is evaluated by comparing the measuring the surface rebound value between sound parts and non-sound parts that have surface damage due to winter rain or leakage on concrete. However, this evaluation method was proposed by analyzing the correlation with an experimental DB obtained under freeze-thaw simulation promoting the environment without reviewing on-site applicability. Therefore, this study reviewed on-site application appropriateness of the concrete freeze-thaw damage evaluation method for the 21 concrete bridges in Korea. From the results, it was clearly confirmed that there was a difference in the surface rebound value between the sound part and the non-sound on the concrete surface; the current evaluation method is considered appropriate for application at the site. In addition, the necessity of adding a specific method and a measurement position of surface rebound value were also analyzed, and the effectiveness of the current evaluation method was also analyzed when targeting the entire concrete bridge, not the evaluation of some sections.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1137-1144
• /
• 2022

In this study, an artificial intelligence(AI) was developed to help with facial expression practice in order to express emotions. The developed AI used multimodal inputs consisting of sentences and facial images for deep neural networks (DNNs). The DNNs calculated similarities between the emotions predicted by the sentences and the emotions predicted by facial images. The user practiced facial expressions based on the situation given by sentences, and the AI provided the user with numerical feedback based on the similarity between the emotion predicted by sentence and the emotion predicted by facial expression. ResNet34 structure was trained on FER2013 public data to predict emotions from facial images. To predict emotions in sentences, KoBERT model was trained in transfer learning manner using the conversational speech dataset for emotion classification opened to the public by AIHub. The DNN that predicts emotions from the facial images demonstrated 65% accuracy, which is comparable to human emotional classification ability. The DNN that predicts emotions from the sentences achieved 90% accuracy. The performance of the developed AI was evaluated through experiments with changing facial expressions in which an ordinary person was participated.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.9
• /
• pp.305-316
• /
• 2022

With the flood of digital data owing to the Internet of Things and big data, cloud service providers that process and store vast amount of data from multiple users can apply duplicate data elimination technique for efficient data management. The user experience can be improved as the notion of edge computing paradigm is introduced as an extension of the cloud computing to improve problems such as network congestion to a central cloud server and reduced computational efficiency. However, the addition of a new edge device that is not entirely reliable in the edge computing may cause increase in the computational complexity for additional cryptographic operations to preserve data privacy in duplicate identification and elimination process. In this paper, we propose an efficiency-improved duplicate data elimination protocol while preserving data privacy with an optimized user-edge-cloud communication framework by utilizing a trusted execution environment. Direct sharing of secret information between the user and the central cloud server can minimize the computational complexity in edge devices and enables the use of efficient encryption algorithms at the side of cloud service providers. Users also improve the user experience by offloading data to edge devices, enabling duplicate elimination and independent activity. Through experiments, efficiency of the proposed scheme has been analyzed such as up to 78x improvements in computation during data outsourcing process compared to the previous study which does not exploit trusted execution environment in edge computing architecture.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.2
• /
• pp.65-85
• /
• 2023

The use of TBM (Tunnel boring machine) has increased worldwide due to its performance together with the benefit of being safely and environmentally friendly compared to conventional tunneling. In particular, EPB (Earth Pressure Balanced) TBM is widely used because it can be applied to various grounds compared to Open TBM. Also EPB TBM has a simple mechanical structure and advantages in cost, requires less ground area than Slurry TBM. EPB TBM has advantages in soft ground, and more importantly, can extend its applicability by use of appropriate soil conditioning, which improves mechanical and hydrological properties of excavated soil and increases the excavation performance of EPB TBM. Various studies suggested the proper mixing ratio and injection ratio, but almost they are limited to laboratory test under atmospheric pressure such as slump test. Actual field conditions may differ depending on the ground and mechanical condition. In this study, first the amount of used soil conditioning used in the field with various grounds from hard rock to soft ground was estimated through laboratory tests and compared with the estimate in design stage. And also it was compared with the amount used during actual excavation. In addition, experience of soil conditioning for the problems of cutter head clogging and groundwater inrush that occurred during excavation is discussed. Finally, lesson learned for the use of soil conditioning in difficult ground condition such as mixed ground are reviewed.

• Korean Chemical Engineering Research
• /
• v.61 no.3
• /
• pp.479-486
• /
• 2023

In this study, we investigated the effect of the Ce_xZr_1-xO₂ (CZ) addition onto Ni/Al₂O₃ catalysts on the catalytic performance in methane steam reforming. In the reaction results, the CZ-added Ni/Al₂O₃ catalyst showed higher CH₄ conversion and H₂ yield under the same reaction conditions than Ni/Al₂O₃. From the characterization data, the two catalysts had similar support porosity and Ni dispersion, confirming that the two properties could not determine the catalytic performance. However, the oxygen vacancy over the CZ-added Ni/Al₂O₃ catalyst induced an efficient steam activation at low reaction temperatures, resulting in an increase in the catalytic activity and H₂ yield.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.7
• /
• pp.303-314
• /
• 2023

Voice conversion, a technology that allows an individual's speech data to be regenerated with the acoustic properties(tone, cadence, gender) of another, has countless applications in education, communication, and entertainment. This paper proposes an approach based on the StarGAN-VC model that generates realistic-sounding speech without requiring parallel utterances. To overcome the constraints of the existing StarGAN-VC model that utilizes one-hot vectors of original and target speaker information, this paper extracts feature vectors of target speakers using a pre-trained version of Rawnet3. This results in a latent space where voice conversion can be performed without direct speaker-to-speaker mappings, enabling an any-to-any structure. In addition to the loss terms used in the original StarGAN-VC model, Wasserstein distance is used as a loss term to ensure that generated voice segments match the acoustic properties of the target voice. Two Time-Scale Update Rule (TTUR) is also used to facilitate stable training. Experimental results show that the proposed method outperforms previous methods, including the StarGAN-VC network on which it was based.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.2A
• /
• pp.401-409
• /
• 2006

This study presents basic information on the mechanical properties and long-term deformations of high-strength steel fiber reinforced concrete(HSFRC). The Influence of steel fiber on modulus of elasticity, compressive, splitting tensile and flexural strength, and drying shrinkage and creep of HSFRC are investigated, and flexural fracture toughness is evaluated. Test results show that Test results show that the effect of steel fibers on the compressive strength is negligible, and the modulus of elasticity of HSFRC increased with the increase of fiber volume fraction. And the effect of fiber volume fraction($V_f$) and aspect ratio($l_f/d_f$) on tensile strength, flexural strength and toughness is extremely prominent. It is observed that the flexural deflection corresponded to ultimate load increased with the increase of $V_f$ and $l_f/d_f$, and due to fiber arresting cracking, the shape of the descending branch of load-deflection tends towards gently. Also, the effect of addition of various amounts of fiber on the creep and shrinkage is obvious. Especially, the effect of adding fibers to high-strength concrete is more pronounced in reducing the drying shrinkage than the creep.

• Phonetics and Speech Sciences
• /
• v.15 no.4
• /
• pp.109-118
• /
• 2023

Cardiac arrest is a critical medical emergency where immediate response is essential for patient survival. This is especially true for Out-of-Hospital Cardiac Arrest (OHCA), for which the actions of emergency medical services in the early stages significantly impact outcomes. However, in Korea, a challenge arises due to a shortage of dispatcher who handle a large volume of emergency calls. In such situations, the implementation of a machine learning-based OHCA detection program can assist responders and improve patient survival rates. In this study, we address this challenge by developing a machine learning-based OHCA detection program. This program analyzes transcripts of conversations between responders and callers to identify instances of cardiac arrest. The proposed model includes an automatic transcription module for these conversations, a text-based cardiac arrest detection model, and the necessary server and client components for program deployment. Importantly, The experimental results demonstrate the model's effectiveness, achieving a performance score of 79.49% based on the F1 metric and reducing the time needed for cardiac arrest detection by 15 seconds compared to dispatcher. Despite working with a limited dataset, this research highlights the potential of a cardiac arrest detection program as a valuable tool for responders, ultimately enhancing cardiac arrest survival rates.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.403-421
• /
• 2023

As the number of underground structures has increased in recent decades, it has become crucial to predict geological hazards ahead of a tunnel face during tunnel construction. Consequently, this study developed a finite element (FE) numerical model to simulate electrical resistivity surveys in tunnel boring machine (TBM) operations for predicting mixed ground conditions in front of tunnel faces. The accuracy of the developed model was verified by comparing the numerical results not only with an analytical solution but also with experimental results. Using the developed model, a series of parametric studies were carried out to estimate the effect of geological conditions and sensor geometric configurations on electrical resistivity measurements. The results of these studies showed that both the interface slope and the difference in electrical resistivity between two different ground formations affect the patterns and variations in electrical resistivity observed during TBM excavation. Furthermore, it was revealed that selecting appropriate sensor spacing and optimizing the location of the electrode array were essential for enhancing the efficiency and accuracy of predictions related to mixed ground conditions. In conclusion, the developed model can serve as a powerful and reliable tool for predicting mixed ground conditions during TBM tunneling.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.95-112
• /
• 2021

In university education, the choice of major class plays an important role in students' careers. However, in line with the changes in the industry, the fields of major subjects by department are diversifying and increasing in number in university education. As a result, students have difficulty to choose and take classes according to their career paths. In general, students choose classes based on experiences such as choices of peers or advice from seniors. This has the advantage of being able to take into account the general situation, but it does not reflect individual tendencies and considerations of existing courses, and has a problem that leads to information inequality that is shared only among specific students. In addition, as non-face-to-face classes have recently been conducted and exchanges between students have decreased, even experience-based decisions have not been made as well. Therefore, this study proposes a recommendation system model that can recommend college major classes suitable for individual characteristics based on data rather than experience. The recommendation system recommends information and content (music, movies, books, images, etc.) that a specific user may be interested in. It is already widely used in services where it is important to consider individual tendencies such as YouTube and Facebook, and you can experience it familiarly in providing personalized services in content services such as over-the-top media services (OTT). Classes are also a kind of content consumption in terms of selecting classes suitable for individuals from a set content list. However, unlike other content consumption, it is characterized by a large influence of selection results. For example, in the case of music and movies, it is usually consumed once and the time required to consume content is short. Therefore, the importance of each item is relatively low, and there is no deep concern in selecting. Major classes usually have a long consumption time because they have to be taken for one semester, and each item has a high importance and requires greater caution in choice because it affects many things such as career and graduation requirements depending on the composition of the selected classes. Depending on the unique characteristics of these major classes, the recommendation system in the education field supports decision-making that reflects individual characteristics that are meaningful and cannot be reflected in experience-based decision-making, even though it has a relatively small number of item ranges. This study aims to realize personalized education and enhance students' educational satisfaction by presenting a recommendation model for university major class. In the model study, class history data of undergraduate students at University from 2015 to 2017 were used, and students and their major names were used as metadata. The class history data is implicit feedback data that only indicates whether content is consumed, not reflecting preferences for classes. Therefore, when we derive embedding vectors that characterize students and classes, their expressive power is low. With these issues in mind, this study proposes a Net-NeuMF model that generates vectors of students, classes through network analysis and utilizes them as input values of the model. The model was based on the structure of NeuMF using one-hot vectors, a representative model using data with implicit feedback. The input vectors of the model are generated to represent the characteristic of students and classes through network analysis. To generate a vector representing a student, each student is set to a node and the edge is designed to connect with a weight if the two students take the same class. Similarly, to generate a vector representing the class, each class was set as a node, and the edge connected if any students had taken the classes in common. Thus, we utilize Node2Vec, a representation learning methodology that quantifies the characteristics of each node. For the evaluation of the model, we used four indicators that are mainly utilized by recommendation systems, and experiments were conducted on three different dimensions to analyze the impact of embedding dimensions on the model. The results show better performance on evaluation metrics regardless of dimension than when using one-hot vectors in existing NeuMF structures. Thus, this work contributes to a network of students (users) and classes (items) to increase expressiveness over existing one-hot embeddings, to match the characteristics of each structure that constitutes the model, and to show better performance on various kinds of evaluation metrics compared to existing methodologies.