• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.645-652
• /
• 2016

The statistical modeling of input random variables is necessary in reliability analysis, reliability-based design optimization, and statistical validation and calibration of analysis models of mechanical systems. In statistical modeling methods, there are the Akaike Information Criterion (AIC), AIC correction (AICc), Bayesian Information Criterion, Maximum Likelihood Estimation (MLE), and Bayesian method. Those methods basically select the best fitted distribution among candidate models by calculating their likelihood function values from a given data set. The number of data or parameters in some methods are considered to identify the distribution types. On the other hand, the engineers in a real field have difficulties in selecting the statistical modeling method to obtain a statistical model of the experimental data because of a lack of knowledge of those methods. In this study, commonly used statistical modeling methods were compared using statistical simulation tests. Their advantages and disadvantages were then analyzed. In the simulation tests, various types of distribution were assumed as populations and the samples were generated randomly from them with different sample sizes. Real engineering data were used to verify each statistical modeling method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.41 no.3
• /
• pp.247-255
• /
• 2021

Individual passenger transfer information is not included in Seoul metropolitan subway Automatic Fare Collection (AFC) data. Currently, basic data such as travel time and distance are allocated based on the TagIn terminal ID data records of AFC data. As such, knowledge of the actual path taken by passengers is constrained by the fact that transfers are not applied, resulting in overestimation of the transport index. This research proposes a method by which a transit path that connects the TagIn and TagOut terminal IDs in AFC data is determined and applied to the transit index. The method embodies the concept that a passenger's line of travel also accounts for transfers, and can be applied to the transit index. The path selection model for the passenger calculates the line of transit based on travel time minimization, with in-vehicle time, transfer walking time, and vehicle intervals all incorporated into the travel time. Since the proposed method can take into account estimated passenger movement trajectories, transport-related data of each subway organization included in the trajectories can be accurately explained. The research results in a calculation of 1.47 times the values recorded, and this can be evaluated directly in its ability to better represent the transportation policy index.

• The Korean Journal of Franchise Management
• /
• v.12 no.1
• /
• pp.35-44
• /
• 2021

Purpose: This study examines the opportunism moderating effect by the startup experience in the relationship between franchisor and franchisees. In the case of a franchise system that has a continuous relational exchange transaction, relationship management is a very important activity because the relationship management between franchisor and franchisees improves the quality of the relationship. Nevertheless, there is insufficient of research on opportunism, which is a negative factor in managing the relationship between franchisor and franchisees in continuous relationship. Research design, data and methodology: This study, we explore the cause of opportunism based on transaction cost theory through prior research and establish a research model based by goal incongruity, uncertainty, information asymmetry, transaction specific assets, the relevance to determinant of opportunism and the startup experienced which is a moderating variable. To verify several hypotheses, the data were collected from 300 out of 1,760 domestic franchisees and analyzed using multiple regression analysis with SPSS program. Results: The findings are as follows. Goal incongruity did not affect opportunism. Opportunism increased as uncertainty increased, and as information asymmetry increased, opportunism increased. An opportunism decreased as transaction specific assets increased. Moreover, the findings show that startup experience only plays a moderating role in the relationship between information asymmetry and opportunism. Therefore, 4 out of 8 hypotheses were supported. Conclusions: The findings show that uncertainty, information asymmetry, and transaction specific assets are the determinants of opportunism. In addition, the results of the analysis of the moderating role of startup experience show that the less entrepreneurial experience, the greater the influence of information asymmetry on opportunism. Our findings mean that maintaining a successful relationship between franchisors and franchisees is possible when franchisors provide knowledge sharing, goal sharing, environmental sharing, and management information sharing to franchisees. In addition, the findings of this study shows that the contract content and management should be changed according to the entrepreneurial experience. In other words, the franchisors must share and integrate the accumulated franchisees' and franchisors' experience with the franchisees to create a synergy that can lead to successful bilateral relationship maintenance, which in turn reduces opportunism.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.19 no.4
• /
• pp.459-467
• /
• 2021

In the majority of countries, the upper limit of buffer temperature in a repository is set to below 100℃ due to the possible illitization. This smectite-to-illite transformation is expected to be detrimental to the swelling functions of the buffer. However, if the upper limit is increased while preventing illitization, the disposal density and cost-effectiveness for the repository will dramatically increase. Thus, understanding the characteristics and creating a database related to the buffer under the elevated temperature conditions is crucial. In this study, a strategy to investigate the bentonite found in Korea under the elevated temperatures from a mineral transformation and radionuclides retardation perspective was proposed. Certain long-term hydrothermal reactions generated the bentonite samples that were utilized for the investigation of their mineral transformation and radionuclide retardation characteristics. The bentonite samples are expected to be studied using in-situ synchrotron-based X-Ray Diffraction (XRD) technique to determine the smectite-to-illite transformation. Simultaneously, the 'high-temperature and high-pressure mineral alteration measurement system' based on the Diamond Anvil Cell (DAC) will control and provide the elevated temperature and pressure conditions during the measurements. The kinetic models, including the Huang and Cuadros model, are expected to predict the time and manner in which the illitization will become detrimental to the performance and safety of the repository. The sorption reactions planned for the bentonite samples to evaluate the effects on retardation will provide the information required to expand the current knowledge of repository optimization.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.30-37
• /
• 2022

Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.

• Journal of Practical Engineering Education
• /
• v.14 no.2
• /
• pp.351-359
• /
• 2022

In this paper, this app is an online learning tool web application that helps learners learn efficiently. It discusses how learners can improve their learning efficiency in these three aspects: retrieval practice, systematization, metacognition. Through this web service, learners can proceed with learning with a flash card-based retrieval practice. In this case, a method of managing a flash card in a form similar to a directory-file system using a composite pattern is described. Learners can systematically organize their knowledge by converting flash cards into a mind map. The color of the mind map varies according to the learner's learning progress, and learners can easily recognize what they know and what they do not know through color. In this case, it is proposed to build a deep learning model to improve the accuracy of an algorithm for determining and predicting learning progress.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.374-376
• /
• 2021

For the diagnosis of cancer-related diseases in clinical practice, pathological examination using biopsy is essential after basic diagnosis using imaging equipment. In order to proceed with such a biopsy, the assistance of an oncologist, clinical pathologist, etc. with specialized knowledge and the minimum required time are essential for confirmation. In recent years, research related to the establishment of a system capable of automatic classification of cancer cells using artificial intelligence is being actively conducted. However, previous studies show limitations in the type and accuracy of cells based on a limited algorithm. In this study, we propose a method to identify a total of 4 cancer cells through a convolutional neural network, a kind of deep learning. The optical images obtained through cell culture were learned through EfficientNet after performing pre-processing such as identification of the location of cells and image segmentation using OpenCV. The model used various hyper parameters based on EfficientNet, and trained InceptionV3 to compare and analyze the performance. As a result, cells were classified with a high accuracy of 96.8%, and this analysis method is expected to be helpful in confirming cancer.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.91-102
• /
• 2022

As artificial intelligence develops, AI chatbot systems are actively taking place. For example, in public institutions, the use of chatbots is expanding to work assistance and professional knowledge services in civil complaints and administration, and private companies are using chatbots for interactive customer response services. In this study, we propose a scenario-based AI voice chatbot system to reduce museum operating costs and provide interactive guidance services to visitors. The implemented voice chatbot system consists of a watcher object that detects the user's voice by monitoring a specific directory in real-time, and an event handler object that outputs AI's response voice by performing inference by model sequentially when a voice file is created. And Including a function to prevent duplication using thread and a deque, GPU operations are not duplicated during inference in a single GPU environment.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.55-67
• /
• 2023

Lightweight face recognition models, as one of the most popular and long-standing topics in the field of computer vision, has achieved vigorous development and has been widely used in many real-world applications due to fewer number of parameters, lower floating-point operations, and smaller model size. However, few surveys reviewed lightweight models and reimplemented these lightweight models by using the same calculating resource and training dataset. In this survey article, we present a comprehensive review about the recent research advances on the end-to-end efficient lightweight face recognition models and reimplement several of the most popular models. To start with, we introduce the overview of face recognition with lightweight models. Then, based on the construction of models, we categorize the lightweight models into: (1) artificially designing lightweight FR models, (2) pruned models to face recognition, (3) efficient automatic neural network architecture design based on neural architecture searching, (4) Knowledge distillation and (5) low-rank decomposition. As an example, we also introduce the SqueezeFaceNet and EfficientFaceNet by pruning SqueezeNet and EfficientNet. Additionally, we reimplement and present a detailed performance comparison of different lightweight models on the nine different test benchmarks. At last, the challenges and future works are provided. There are three main contributions in our survey: firstly, the categorized lightweight models can be conveniently identified so that we can explore new lightweight models for face recognition; secondly, the comprehensive performance comparisons are carried out so that ones can choose models when a state-of-the-art end-to-end face recognition system is deployed on mobile devices; thirdly, the challenges and future trends are stated to inspire our future works.

• Journal of Advanced Navigation Technology
• /
• v.26 no.6
• /
• pp.528-535
• /
• 2022

Although the domestic aviation industry has made rapid progress with the development of aircraft manufacturing and transportation technologies, aviation safety accidents continue to occur. The supervisory agency classifies hazards and risks based on risk-based aviation safety data, identifies safety trends for each air transportation operator, and conducts pre-inspections to prevent event and accidents. However, the human classification of data described in natural language format results in different results depending on knowledge, experience, and propensity, and it takes a considerable amount of time to understand and classify the meaning of the content. Therefore, in this journal, the fine-tuned KoBERT model was machine-learned over 5,000 data to predict the classification value of new data, showing 79.2% accuracy. In addition, some of the same result prediction and failed data for similar events were errors caused by human.