• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.29-35
• /
• 2023

CCTV is used for various purposes such as crime prevention, public safety reinforcement, and traffic management. However, as the range and resolution of the camera improve, there is a risk of exposing personal information in the video. Therefore, there is a need for new technologies that can identify individuals while protecting personal information in images. In this paper, we propose histogram-based singular value decomposition for object identification and tracking. The proposed method distinguishes different objects present in the image using color information of the object. For object recognition, YOLO and DeepSORT are used to detect and extract people present in the image. Color values are extracted with a black-and-white histogram using location information of the detected person. Singular value decomposition is used to extract and use only meaningful information among the extracted color values. When using singular value decomposition, the accuracy of object color extraction is increased by using the average of the upper singular value in the result. Color information extracted using singular value decomposition is compared with colors present in other images, and the same person present in different images is detected. Euclidean distance is used for color information comparison, and Top-N is used for accuracy evaluation. As a result of the evaluation, when detecting the same person using a black-and-white histogram and singular value decomposition, it recorded a maximum of 100% to a minimum of 74%.

• Industry Promotion Research
• /
• v.8 no.4
• /
• pp.267-276
• /
• 2023

Based on the tourism input-output data of five provinces and cities in China's Bohai Rim region from 2015~2021, this study analyzes the efficiency of regional tourism using DEA-BCC and DEA-Malmquist index, as well as its contribution to regional economic efficiency, and identifies factors influencing the comprehensive efficiency. The research results indicate that the comprehensive efficiency of the tourism industry in the China Bohai Sea region has reached an optimal level of 88.9%, but there is still room for improvement, with overall fluctuations. The overall productivity of the tourism industry exhibits a "U"-shaped fluctuating pattern, with growth mainly driven by technological advancements. Due to the impact of the COVID-19 pandemic, the region experienced a nearly 50% decrease in total factor productivity in 2019~2020. However, in 2021, with the implementation of various government stimulus policies, the tourism efficiency rapidly recovered to 80% of pre-pandemic levels. In terms of the impact of the tourism industry on the regional economy in the China Bohai Sea region, Hebei Province stands out as a significant contributor. Based on the aforementioned research findings, the following recommendations are proposed in three aspects: optimizing the supply structure, increasing innovation investment, and strengthening internal collaboration. These recommendations provide valuable insights for enhancing regional tourism efficiency and promoting regional synergy.

• Journal of Korea Water Resources Association
• /
• v.56 no.11
• /
• pp.815-822
• /
• 2023

Organic pollution is one of the most common forms of water contamination. Under the Water Quality Conservation Act, indicators for measuring organic substances include BOD, COD, and TOC. Analysis of BOD and COD is labor-intensive, and in the case of organic substances where biological decomposition is not feasible or toxic substances are present, the accuracy is often low. Therefore, the Ministry of Environment is shifting towards TOC-centric management. With advancements in sensor technology today, various parameters can be monitored using sensors. In this study, digital monitoring of river TOC using a spectrophotometer called Spectro::lyser V3 was conducted. Initially, experiments were carried out at the Andong River Experiment Center to assess the applicability of the measurement equipment. Subsequently, data collected at the confluence of the Nakdong River was analyzed for the spatial distribution of TOC using the Kriging technique. This research proposes the utilization of sensors for river TOC monitoring and spatial distribution analysis. Real-time monitoring of changes in river TOC concentration can serve as fundamental data for pollution monitoring and response. Sensor-based river monitoring offers advantages in terms of temporal resolution and real-time data acquisition. When various spatial information interpretation methods are applied, it is expected to contribute to diverse studies such as aquatic ecological health, river water source selection, and stratification analysis in the future.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.6
• /
• pp.543-551
• /
• 2023

As climate change continues to prompt an increasing demand for advancements in disaster and safety management technologies to address abnormal high water temperatures, typhoons, floods, and droughts, sea surface temperature has emerged as a pivotal factor for swiftly assessing the impacts of summer harmful algal blooms in the seas surrounding Korean Peninsula and the formation and dissipation of cold water along the East Coast of Korea. Therefore, this study sought to gauge predictive performance by leveraging statistical methods and deep learning algorithms to harness sea surface temperature data effectively for marine anomaly research. The sea surface temperature data employed in the predictions spans from 2018 to 2022 and originates from the Heuksando Tidal Observatory. Both traditional statistical ARIMA methods and advanced deep learning models, including long short-term memory (LSTM) and gated recurrent unit (GRU), were employed. Furthermore, prediction performance was evaluated using the attention LSTM technique. The technique integrated an attention mechanism into the sequence-to-sequence (s2s), further augmenting the performance of LSTM. The results showed that the attention LSTM model outperformed the other models, signifying its superior predictive performance. Additionally, fine-tuning hyperparameters can improve sea surface temperature performance.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.534-546
• /
• 2023

If the disc cutter is excessively worn or damaged, it becomes incapable of rotating and efficiently cutting rockmass. Therefore, it is important to appropriately manage the replacement cycle of the disc cutter based on its degree of wear. In general, the replacement cycle is determined based on the results of manual inspection. However, the manual measurements has issues related to worker safety and may lead to inaccurate measurement results. For these reasons, some foreign countries are developing the real-time measurement system of disc cutter wear by using different sensors. The ultrasonic sensors, eddy current sensors, magnetic sensors, and others are utilized for measuring the wear amount of disc cutters. In this study, the applicability of eddy current sensors for real-time measurement of wear amount in TBM disc cutters was evaluated. The distance measurement accuracy of the eddy current sensor was assessed through laboratory tests. In particular, the accuracy of eddy-current sensor was evaluated in various environmental conditions within the cutterhead chamber. In addition, the measurement accuracy of the eddy current sensor was validated using a 17-inch disc cutter.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.33 no.6
• /
• pp.216-225
• /
• 2023

This paper describes the finite element analysis and die design change of cold heading punching process to increase the cold forging tool life and reduce the tool wear and stress concentration. Through this study, the optimization of punch tool design has been studied by an analysis of tool stress and wear distribution to improve the tool life. Plastic deformation analysis was carried out in order to understand the cold heading process between tool and workpiece stress distribution. Cold heading punch die design was set up to each process with different four types analysis progressing, the cold heading punch dies shapes with combination of point angle and punch edge corner radius shapes of cold forging dies, punch die material properties and frictional coefficient. The design parameters of point angle and corner radius of punch die geometry, die material properties and frictional coefficient were selected to apply optimization with the DoE (design of experiment) and Taguchi method. DoE and Taguchi method was performed to optimize the cold heading punch die design parameters optimization for bolt head cold forging process, it was possible to expect an reduce the cold heading punch die wear to the 37 % compared with current using cold heading punch in the shop floor.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.17 no.6
• /
• pp.71-88
• /
• 2022

The purpose of this study is to develop the competencies to help micro entrepreneurs who have experienced failure to successfully re-challenge. To this end, relevant literature published from 1977 to 2022 was analyzed, behavioral event interviews (BEI) were conducted with 7 successful micro entrepreneurs, and focus group interviews (FGI) were conducted three times by inviting competency development and HRD experts. Based on these research activities, the draft about competencies for micro entrepreneurs who had have failure was derived. And then inviting 12 experts in related field for Delphi Analysis, the final competency model that helps micro entrepreneurs successfully recover were developed as follows : Competency Groups(small business owners, recovery from failure), 8 detailed competencies(seize business opportunities, business planning, business differentiation, operation management, market exploration, research and development of products and services, positive self-regulation, overcoming and coping with failure experiences), 22 competency factors, and 72 behavioral indicators. This study has an academic significance in that it developed the competencies required for micro entrepreneurs recovering from failure. In addition, the results of this study can be used to develop a competency-based education program for micro entrepreneurs and to select suitable candidates for support programs.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.105-123
• /
• 2022

Thanks to the remarkable success of Artificial Intelligence (A.I.) techniques, a new possibility for its application on the real-world problem has begun. One of the prominent applications is the bankruptcy prediction model as it is often used as a basic knowledge base for credit scoring models in the financial industry. As a result, there has been extensive research on how to improve the prediction accuracy of the model. However, despite its impressive performance, it is difficult to implement machine learning (ML)-based models due to its intrinsic trait of obscurity, especially when the field requires or values an explanation about the result obtained by the model. The financial domain is one of the areas where explanation matters to stakeholders such as domain experts and customers. In this paper, we propose a novel approach to incorporate financial domain knowledge into local rule generation to provide explanations for the bankruptcy prediction model at instance level. The result shows the proposed method successfully selects and classifies the extracted rules based on the feasibility and information they convey to the users.

• Analytical Science and Technology
• /
• v.37 no.3
• /
• pp.166-173
• /
• 2024

Steroids have a temporary skin improvement and whitening effect by controlling vasodilation, but they also cause side effects when used for a long time. Therefore, steroids were designated and managed as raw materials that cannot be used in cosmetics in Korea. However, steroids are continuously being detected in cosmetics, causing social issues. In this study, we developed a certified reference material (CRM) for the determination of steroids such as hydrocortisone in cosmetics. A cream-type cosmetic CRM was manufactured and subsequently certified following the guidelines outlined in ISO Guide 35. Homogeneity, short-term stability, and long-term stability were evaluated using isotope dilution mass spectrometry (ID-MS). The certified values were determined by using NIST's primary reference material to ensure traceability. From now on, we intend to supply the certified reference material as a cosmetic CRM to national and international companies, as well as research institutes after certification as certified reference material from KOLAS and registering on COMAR.