• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.123-132
• /
• 2023

Git's commit messages manage the history of source changes during project progress or operation. By utilizing this historical data, project risks and project status can be identified, thereby reducing costs and improving time efficiency. A lot of research related to this is in progress, and among these research areas, there is research that classifies commit messages as a type of software maintenance. Among published studies, the maximum classification accuracy is reported to be 95%. In this paper, we began research with the purpose of utilizing solutions using the commit classification model, and conducted research to remove the limitation that the model with the highest accuracy among existing studies can only be applied to programs written in the JAVA language. To this end, we designed and implemented an additional step to standardize source change data into natural language using GPT. This text explains the process of extracting commit messages and source change data from Git, standardizing the source change data with GPT, and the learning process using the DistilBERT model. As a result of verification, an accuracy of 91% was measured. The proposed model was implemented and verified to ensure accuracy and to be able to classify without being dependent on a specific program. In the future, we plan to study a classification model using Bard and a management tool model helpful to the project using the proposed classification model.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3543-3548
• /
• 2023

Shutdown chemistry evolution is performed in nuclear power plants at each refueling outage (RFO) to establish safe conditions to open system and minimize inventory of corrosion products in the reactor coolant system (RCS). After hydrogen peroxide is added to RCS during shutdown chemistry evolution, corrosion products are released and are removed by filters and ion exchange resins in the chemical volume control system (CVCS). Shutdown chemistry evolution including RCS clean-up time to remove released corrosion products impacts the critical path schedule during RFOs. The estimation of clean-up time prior to RFO can provide more reliable actions for RCS clean-up operations and transients to operators during shutdown chemistry. Electric Power Research Institute (EPRI) shutdown calculator (SDC) enables to provide clean-up time by Co-58 peak activity through operational data from nuclear power plants (NPPs). In this study, we have investigated the results of EPRI SDC by shutdown chemistry data of Co-58 activity using NPP data from previous cycles and modeled the estimated clean-up time by EPRI SDC using average Co-58 activity of the NPP. We selected two RFO data from the NPP to evaluate EPRI SDC results using the purification time to reach to 1.3 mCi/cc of Co-58 after hydrogen peroxide addition. Comparing two RFO data, the similar purification time between actual and computed data by EPRI SDC, 0.92 and 1.74 h respectively, was observed with the deviation of 3.7-7.2%. As the modeling the estimated clean-up time, we calculated average Co-58 peak concentration for normal cycles after cycle 10 and applied two-sigma (2σ, 95.4%) for predicted Co-58 peak concentration as upper and lower values compared to the average data. For the verification of modeling, shutdown chemistry data for RFO 17 was used. Predicted RCS clean-up time with lower and upper values was between 21.05 and 27.58 h, and clean-up time for RFO 17 was 24.75 h, within the predicted time band. Therefore, our calculated modeling band was validated. This approach can be identified that the advantage of the modeling for clean-up time with SDC is that the primary prediction of shutdown chemistry plans can be performed more reliably during shutdown chemistry. This research can contribute to improving the efficiency and safety of shutdown chemistry evolution in nuclear power plants.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.9
• /
• pp.263-272
• /
• 2023

Industrial Internet of Things (IIoT) is an important factor in increasing production efficiency in industrial sectors, along with data collection, exchange and analysis through large-scale connectivity. However, as traffic increases explosively due to the recent spread of IIoT, an allocation method that can efficiently process traffic is required. In this thesis, I propose a two-stage task offloading decision method to increase successful task throughput in an IIoT environment. In addition, I consider a hybrid offloading system that can offload compute-intensive tasks to a mobile edge computing server via a cellular link or to a nearby IIoT device via a Device to Device (D2D) link. The first stage is to design an incentive mechanism to prevent devices participating in task offloading from acting selfishly and giving difficulties in improving task throughput. Among the mechanism design, McAfee's mechanism is used to control the selfish behavior of the devices that process the task and to increase the overall system throughput. After that, in stage 2, I propose a multi-armed bandit (MAB)-based task offloading decision method in a non-stationary environment by considering the irregular movement of the IIoT device. Experimental results show that the proposed method can obtain better performance in terms of overall system throughput, communication failure rate and regret compared to other existing methods.

• Composites Research
• /
• v.36 no.6
• /
• pp.454-460
• /
• 2023

Recently, regulations on greenhouse gas emissions have been strengthened, and the International Maritime Organization (IMO) has been strengthening greenhouse gas regulations with a goal of net 'zero' emissions by 2050. In addition, in the shipbuilding/offshore sector, it is important to reduce operating costs, such as improving propulsion efficiency and lightening structures. In this regard, research is currently being conducted on topology optimization using 3D printed composite materials to satisfy structural lightness and high rigidity. In this study, three topology shapes (hexagonal, square, and triangular) were applied to the interior of a rudder, a ship structure, using 3D printed composite materials. Structural analysis was performed to determine the appropriate shape for the rudder. CFD analysis was performed at 10° intervals from 0° to 30° for each rudder angle under the condition of 8 knots, and the load conditions were set based on the CFD analysis results. As a result of the structural analysis considering the internal topology shape of the rudder, it was confirmed that the triangular, square, and hexagonal topology shapes have excellent performance. The rudder with a square topology shape weighs 78.5% of the rudder with a triangular shape, and the square topology shape is considered to superior in terms of weight reduction.

• Journal of Powder Materials
• /
• v.31 no.2
• /
• pp.169-179
• /
• 2024

Colloidal quantum dot (QDs) have emerged as a crucial building block for LEDs due to their size-tunable emission wavelength, narrow spectral line width, and high quantum efficiency. Tremendous efforts have been dedicated to improving the performance of quantum dot light-emitting diodes (QLEDs) in the past decade, primarily focusing on optimization of device architectures and synthetic procedures for high quality QDs. However, despite these efforts, the commercialization of QLEDs has yet to be realized due to the absence of suitable large-scale patterning technologies for high-resolution devices., This review will focus on the development trends associated with transfer printing, photolithography, and inkjet printing, and aims to provide a brief overview of the fabricated QLED devices. The advancement of various quantum dot patterning methods will lead to the development of not only QLED devices but also solar cells, quantum communication, and quantum computers.

• Korean Journal of Radiology
• /
• v.23 no.5
• /
• pp.505-516
• /
• 2022

Objective: To evaluate whether artificial intelligence (AI) for detecting breast cancer on mammography can improve the performance and time efficiency of radiologists reading mammograms. Materials and Methods: A commercial deep learning-based software for mammography was validated using external data collected from 200 patients, 100 each with and without breast cancer (40 with benign lesions and 60 without lesions) from one hospital. Ten readers, including five breast specialist radiologists (BSRs) and five general radiologists (GRs), assessed all mammography images using a seven-point scale to rate the likelihood of malignancy in two sessions, with and without the aid of the AI-based software, and the reading time was automatically recorded using a web-based reporting system. Two reading sessions were conducted with a two-month washout period in between. Differences in the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and reading time between reading with and without AI were analyzed, accounting for data clustering by readers when indicated. Results: The AUROC of the AI alone, BSR (average across five readers), and GR (average across five readers) groups was 0.915 (95% confidence interval, 0.876-0.954), 0.813 (0.756-0.870), and 0.684 (0.616-0.752), respectively. With AI assistance, the AUROC significantly increased to 0.884 (0.840-0.928) and 0.833 (0.779-0.887) in the BSR and GR groups, respectively (p = 0.007 and p < 0.001, respectively). Sensitivity was improved by AI assistance in both groups (74.6% vs. 88.6% in BSR, p < 0.001; 52.1% vs. 79.4% in GR, p < 0.001), but the specificity did not differ significantly (66.6% vs. 66.4% in BSR, p = 0.238; 70.8% vs. 70.0% in GR, p = 0.689). The average reading time pooled across readers was significantly decreased by AI assistance for BSRs (82.73 vs. 73.04 seconds, p < 0.001) but increased in GRs (35.44 vs. 42.52 seconds, p < 0.001). Conclusion: AI-based software improved the performance of radiologists regardless of their experience and affected the reading time.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.135-144
• /
• 2024

In this study, we propose an automatic classification model for quantitative multidimensional analysis based on facet theory to understand public opinions and demands on major issues through big data analysis. Civil complaints, as a form of public feedback, are generated by various individuals on multiple topics repeatedly and continuously in real-time, which can be challenging for officials to read and analyze efficiently. Specifically, our research introduces a new classification framework that utilizes facet theory and political analysis models to analyze the characteristics of citizen complaints and apply them to the policy-making process. Furthermore, to reduce administrative tasks related to complaint analysis and processing and to facilitate citizen policy participation, we employ deep learning to automatically extract and classify attributes based on the facet analysis framework. The results of this study are expected to provide important insights into understanding and analyzing the characteristics of big data related to citizen complaints, which can pave the way for future research in various fields beyond the public sector, such as education, industry, and healthcare, for quantifying unstructured data and utilizing multidimensional analysis. In practical terms, improving the processing system for large-scale electronic complaints and automation through deep learning can enhance the efficiency and responsiveness of complaint handling, and this approach can also be applied to text data processing in other fields.

• Journal of Animal Science and Technology
• /
• v.66 no.2
• /
• pp.310-325
• /
• 2024

Glyconutrients help in the body's cell communication. Glyconutrients and synbiotics are promising options for improving immune function. Therefore, we hypothesized that combining synbiotics and glyconutrients will enhance pig nutrient utilization. 150 pigs (Landrace × Yorkshire × Duroc), initially weighing 58.85 ± 3.30 kg of live body weight (BW) were utilized to determine the effects of synbiotics-glyconutrients (SGN) on the pigs' performance, feed efficiency, gas emission, pork traits, and composition of fatty acids. The pigs were matched by BW and sex and chosen at random to 1 of 3 diet treatments: control = Basal diet; TRT1 = Basal diet + SGN 0.15%; TRT2 = Basal diet + SGN 0.30%%. The trials were conducted in two phases (weeks 1-5 and weeks 5-10). The average daily gain was increased in pigs fed a basal diet with SGN (p = 0.036) in weeks 5-10. However, the apparent total tract digestibility of dry matter, nitrogen, and gross energy did not differ among the treatments (p > 0.05). Dietary treatments had no effect on NH₃, H₂S, methyl mercaptans, acetic acids, and CO₂ emissions (p > 0.05). Improvement in drip loss on day 7 (p = 0.053) and tendency in the cooking loss were observed (p = 0.070) in a group fed basal diets and SGN at 0.30% inclusion level. The group supplemented with 0.30% of SGN had higher levels of palmitoleic acid (C16:1), margaric acid (C17:0), omega-3 fatty acid, omega-6 fatty acid, and ω-6: ω-3 ratio (p = 0.034, 0.020, 0.025, 0.007, and 0.003, respectively) in the fat of finishing pigs. Furthermore, group supplemented with 0.30% of SGN improved margaric acid (C17:0), linoleic acid (C18:2n6c), arachidic acid (C20:0), omega 6 fatty acid, omega-6 to omega-3 ratio, unsaturated fatty acid, and monounsaturated fatty acid (p = 0.037, 0.05, 0.0142, 0.036, 0.033, 0.020, and 0.045, respectively) in the lean tissues of finishing pigs compared to pigs fed with the control diets. In conclusion, the combination of probiotics, prebiotics, and glyconutrients led to higher average daily gain, improved the quality of pork, and more favorable fatty acid composition. Therefore, these results contributed to a better understanding of the potential of SGN combinations as a feed additive for pigs.

• Membrane Journal
• /
• v.34 no.1
• /
• pp.38-49
• /
• 2024

Wastewater treatment using membrane bioreactors has been extensively used to alleviate water shortage and pollution by improving the quality of the treated water discharged into the environment. However, membrane biofouling persistently holds back an MBR process by reducing the process efficiency. Herein, we synthesized carbon nanospheres (CNSs) with many hydrophilic oxygen groups and utilized them as an additive to prepare high-performance ultrafiltration (UF) membranes with hydrophilicity and porous pore structure. CNSs were found to form crescent-shaped pores on the membrane surface, increasing the mean surface pore size by about 40% without causing significant defects larger than bubble points, as the CNS content increased by 4.6 wt%. In addition, the porous pore structure of CNS composite membranes was also attributable to the CNS's isotropic morphologies and relatively low particle number density because the aforementioned properties contributed to preventing the polymer solution viscosity from soaring with the loading of CNS. However, too porous structure compromised the mechanical properties, such that CNS2.3 was the best from a comprehensive consideration including the pore structure and mechanical properties. As a result, CNS2.3 showed not only 2 times higher water permeability than CNS0 but also 5 times longer operation duration until membrane cleaning was required.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.23-43
• /
• 2021

Due to the recent transition to a non-face-to-face society, many organizations are quickly adapting to foster a smart work environment. The introduction of smart work does not simply end with incorporating ICT systems or solutions into business models since fundamental factors such as forms of employment and work styles need to be in line with the progression of technological advances. However, previous studies regarding smart work focus on improvements in productivity and efficiency from a technology acceptance perspective. Therefore, there is a lack of discussion on innovation resistance from employees and management control when ICT systems are introduced into the workplace. This study empirically analyzes the moderating effects of the organizational control method for employees and innovation resistance within a smart work environment. Additionally, this study aims to identify the structural characteristics that employees resist from an innovation resistance perspective when organizational innovation occurs. The empirical analysis of this study suggests that when smart work such as ICT technology is introduced into the workplace the level of innovation resistance decreases when there is a high level of relative advantage and self-efficacy, whereas the level of innovation resistance increases when there is a high level of use complexity. Moreover, this study revealed that the level of innovation resistance increases when the employees' behaviors were controlled. The results of this study intend to contribute to improving business management by suggesting factors worth considering when incorporating smart work into work places through a thorough case analysis.