• The Korean Journal of Applied Statistics
• /
• v.35 no.3
• /
• pp.407-419
• /
• 2022

The semiconductor fabrication process is complex and time-consuming. There are sometimes errors in the process, which results in defective die on the wafer bin map (WBM). We can detect the faulty WBM by finding some patterns caused by dies. When one manually seeks the failure on WBM, it takes a long time due to the enormous number of WBMs. We suggest a two-step approach to discover the probable pattern on the WBMs in this paper. The first step is to separate the normal WBMs from the defective WBMs. We adapt a hierarchical clustering for de-noising, which nicely performs this work by wisely tuning the number of minimum points and the cutting height. Once declared as a faulty WBM, then it moves to the next step. In the second step, we classify the patterns among the defective WBMs. For this purpose, we extract features from the WBM. Then machine learning algorithm classifies the pattern. We use a real WBM data set (WM-811K) released by Taiwan semiconductor manufacturing company.

• Science of Emotion and Sensibility
• /
• v.24 no.4
• /
• pp.117-128
• /
• 2021

In this work, we study smart gloves that can prevent carpal tunnel syndrome when using a mouse. Because the left and right wrist movements are fine, a tensile fabric sensor with a large gauge factor and low hysteresis was required before the study. A universal testing machine was used to calculate each gauge rate on four different fabrics, and the fabric with the least hysteresis was selected. In addition, three attachment methods were analyzed using Arduino to select a method with a large sensor value change. For prototypes made by attaching to the selected fabric, data patterns were analyzed using Arduino. The first method identifies only one sensor (A sensor), and the second identifies two sensors (A and B sensors). When the wrist is bent to the right, tensile fabric sensors are attached to both the left (A sensor) and right (B sensor) sides of the wrist, the A sensor is strained, increasing the △sensor value, and the B sensor is relaxed, decreasing the △sensor value. However, when the wrist was bent to the left, the pattern was analyzed in the opposite direction. Through this study, we examined smart gloves to prevent carpal tunnel syndrome with an algorithm that turns on the LED when the wrist is bent, and based on the results of this study, we will directly use mice on 10 people to identify problems and solve problems when used.

• Knowledge Management Research
• /
• v.23 no.1
• /
• pp.89-109
• /
• 2022

Due to COVID-19 and soaring participation of individual investors, large-scale transactions exceeding system capacity limits have been reported frequently in the capital market. The capital market IT systems, which the impact of system failure is very critical, have encountered unexpectedly tremendous transactions in 2020, resulting in a sharp increase in system failures. Despite the fact that many companies maintained large-scale system capacity planning policies, recent transaction influx suggests that a new approach to capacity planning is required. Therefore, this study developed capital market IT system capacity planning models using machine learning techniques and analyzed those performances. In addition, the performance of the best proposed model was improved by using sentiment index that can promptly reflect the behavior of investors. The model uses empirical data including the COVID-19 period, and has high performance and stability that can be used in practice. In practical significance, this study maximizes the cost-efficiency of a company, but also presents optimal parameters in consideration of the practical constraints involved in changing the system. Additionally, by proving that the sentiment index can be used as a major variable in system capacity planning, it shows that the sentiment index can be actively used for various other forecasting demands.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.339-346
• /
• 2022

Recently, the resource depletion and climate change problem caused by the massive usage of fossil fuels for electric power generation has become a critical issue worldwide. According to this issue, interest in renewable energy resources that can replace fossil fuels is increasing. Especially, photovoltaic power has gaining much attention because there is no risk of resource exhaustion compared to other energy resources and there are low restrictions on installation of photovoltaic system. In order to use the power generated by the photovoltaic system efficiently, a more accurate photovoltaic power forecasting model is required. So far, even though many machine learning and deep learning-based photovoltaic power forecasting models have been proposed, they showed limited success in terms of interpretability. Deep learning-based forecasting models have the disadvantage of being difficult to explain how the forecasting results are derived. To solve this problem, many studies are being conducted on explainable artificial intelligence technique. The reliability of the model can be secured if it is possible to interpret how the model derives the results. Also, the model can be improved to increase the forecasting accuracy based on the analysis results. Therefore, in this paper, we propose an explainable photovoltaic power forecasting scheme based on BiLSTM (Bidirectional Long Short-Term Memory) and SHAP (SHapley Additive exPlanations).

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.93-108
• /
• 2023

In manufacturing productivity analysis, understanding the intricate interplay among factors like facility performance, layout design, and workforce allocation within the production line is imperative. This paper introduces a simulation-based methodology tailored to food manufacturing, progressively expanding scenarios to analyze production enhancement. The target system is a food processing plant, encompassing production processes, including warehousing, processing, subdivision, packaging, inspection, loading, and storage. First, we analyze the target system and design a simulation model according to the actual layout arrangement of equipment and workers. Then, we validate the developed model reflecting the real data obtained from the target system, such as the workers' working time and the equipment's processing time. The proposed model aims to identify optimal factor values for productivity gains through incremental scenario comparisons. To this end, three stages of simulation experiments were conducted by extending the equipment and worker models of the subdivision and packaging processes. The simulation experiments have shown that productivity depends on the placement of skilled workers and the performance of the packaging machine. The proposed method in this study will offer combinations of factors for the specific production requirements and support optimal decision-making in the real-world field.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.869-875
• /
• 2009

Safety is a big issue in the construction sites. For safe and secure management, tracking locations of construction resources such as labors, materials, machineries, vehicles and so on is important. The materials, machineries and vehicles could be controlled by computer, whereas the movement of labors does not have fixed pattern. So, the location and movement of labors need to be monitored continuously for safety. In general, Global Positioning System(GPS) is an opt solution to obtain the location information in outside environments. But it cannot be used for indoor locations as it requires a clear Line-Of-Sight(LOS) to satellites Therefore, indoor location monitoring system could be a convenient alternative for environments such as tunnel and indoor building construction sites. This paper presents a case study to investigate feasibility of Wi-Fi based indoor location monitoring system in construction site. The system is developed by using fingerprint map of gathering Received Signal Strength Indication(RSSI) from each Access Point(AP). The signal information is gathered by Radio Frequency Identification (RFID) tags, which are attached on a helmet of labors to track their locations, and is sent to server computer. Experiments were conducted in a shield tunnel construction site at Guangzhou, China. This study consists of three phases as follows: First, we have a tracking test in entrance area of tunnel construction site. This experiment was performed to find the effective geometry of APs installation. The geometry of APs installation was changed for finding effective locations, and the experiment was performed using one and more tags. Second, APs were separated into two groups, and they were connected with LAN cable in tunnel construction site. The purpose of this experiment was to check the validity of group separating strategy. One group was installed around the entrance and the other one was installed inside the tunnel. Finally, we installed the system inner area of tunnel, boring machine area, and checked the performance with varying conditions (the presence of obstacles such as train, worker, and so on). Accuracy of this study was calculated from the data, which was collected at some known points. Experimental results showed that WiFi-based indoor location system has a level of accuracy of a few meters in tunnel construction site. From the results, it is inferred that the location tracking system can track the approximate location of labors in the construction site. It is able to alert the labors when they are closer to dangerous zones like poisonous region or cave-in..

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.1
• /
• pp.24-35
• /
• 2023

Rapid industrialization and urbanization have led to severe marine pollution. A Water Quality Index (WQI) has been developed to allow the effective management of marine pollution. However, the WQI suffers from problems with loss of information due to the complex calculations involved, changes in standards, calculation errors by practitioners, and statistical errors. Consequently, research on the use of artificial intelligence techniques to predict the marine and coastal WQI is being conducted both locally and internationally. In this study, six techniques (RF, XGBoost, KNN, Ext, SVM, and LR) were studied using marine environmental measurement data (2000-2020) to determine the most appropriate artificial intelligence technique to estimate the WOI of five ecoregions in the Korean seas. Our results show that the random forest method offers the best performance as compared to the other methods studied. The residual analysis of the WQI predicted score and actual score using the random forest method shows that the temporal and spatial prediction performance was exceptional for all ecoregions. In conclusion, the RF model of WQI prediction developed in this study is considered to be applicable to Korean seas with high accuracy.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.3
• /
• pp.71-79
• /
• 2023

It is not efficient to install a maintenance system that measures seismic acceleration and displacement on all bridges and buildings to evaluate the safety of structures after an earthquake occurs. In order to maintain this, an on-site investigation is conducted. Therefore, it takes a lot of time when the scope of the investigation is wide. As a result, secondary damage may occur, so it is necessary to predict the safety of individual structures quickly. The method of estimating earthquake damage of a structure includes a finite element analysis method using approved seismic information and a structural analysis model. Therefore, it is necessary to predict the seismic information generated at arbitrary location in order to quickly determine structure damage. In this study, methods to predict the ground response spectrum and acceleration time history at arbitrary location using linear estimation methods, and artificial neural network learning methods based on seismic observation data were proposed and their applicability was evaluated. In the case of the linear estimation method, the error was small when the locations of nearby observatories were gathered, but the error increased significantly when it was spread. In the case of the artificial neural network learning method, it could be estimated with a lower level of error under the same conditions.

• Journal of Technology Innovation
• /
• v.30 no.1
• /
• pp.57-104
• /
• 2022

The government has supported the innovation of private firms by intervening the market for various purposes, such as preventing market failure, alleviating information asymmetry, and allocating resources efficiently. Although the government's R&D budget increased rapidly in the 2000s, it is not clear whether the government intervention has made desirable impact on the market. To address this, the current study attempts to explore this issue by doing a systematic literature review on foreign and domestic papers in an integrated way. In total, 168 studies are analyzed using contents analysis approach and various lens, such as policy additionality, policy tools, firm size, unit of analysis, data and method, are adopted for analysis. Overlapping policy target, time lag between government intervention and policy effects, non-linearity of financial supports, interference between different polices, and out-dated R&D tax incentive system are reported as factors hampering the effect of the government intervention. Many policy prescriptions, such as program evaluation indices reflecting behavioral additionality, an introduction of policy mix and evidence-based policy using machine learning, are suggested to improve these hurdles.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.85-100
• /
• 2023

Corporate ESG performance (environmental, social, and corporate governance) reflecting a company's strategic sustainability has emerged as one of the main factors in today's investment decisions. The traditional ESG performance rating process is largely performed in a qualitative and subjective manner based on the institution-specific criteria, entailing limitations in reliability, predictability, and timeliness when making investment decisions. This study attempted to predict the corporate ESG rating through automated machine learning based on quantitative and disclosed corporate financial information. Using 12 types (21,360 cases) of market-disclosed financial information and 1,780 ESG measures available through the Korea Institute of Corporate Governance and Sustainability during 2019 to 2021, we suggested a deep neural network prediction model. Our model yielded about 86% of accurate classification performance in predicting ESG rating, showing better performance than other comparative models. This study contributed the literature in a way that the model achieved relatively accurate ESG rating predictions through an automated process using quantitative and publicly available corporate financial information. In terms of practical implications, the general investors can benefit from the prediction accuracy and time efficiency of our proposed model with nominal cost. In addition, this study can be expanded by accumulating more Korean and international data and by developing a more robust and complex model in the future.