• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.6
• /
• pp.509-517
• /
• 2001

To deal with non-linearities and time-varying characteristics of hydraulic systems, in this paper, the neuro-fuzzy controller has been introduced. This controller does not require and accurate mathematical model for the nonlinear factor. In order to solve general fuzzy inference problems, the input membership function and fuzzy reasoning rules are used for determining the controller parameters. These parameters are determined by using the learning algorithm. The control performance of the neuro-fuzzy controller is evaluated through a series of experiments for the various types of inputs while applying disturbances to the hydraulic system. The performance of this controller was compared with those of PID and PD controllers. From these results, We observe be said that the position tracking performance of neuro-fuzzy is better those of PID and PD controllers.

• International Journal of Advanced Culture Technology
• /
• v.6 no.4
• /
• pp.309-316
• /
• 2018

The main purpose of this study is to understand how cognitive factors influence the way people interact with information/information systems, by conducting comprehensive and in-depth literature reviews and a theoretical synthesis of related research. Adaptive systems have been built around an individual user's characteristics, such as interests, preferences, knowledge and goals. Individual differences in the ability to use new information and communication technology have been an important issue in all fields. Performance differences in utilizing new information and communication technology are sufficiently predictable that we can begin to coordinate them. Therefore, it is necessary to understand cognitive mechanisms to explain differences between individuals as well as the levels of performance. The theoretical synthesis from this study can be applied to design intelligent (i.e., human friendly) systems in our everyday lives. Further research should explore optimization design for user, by integrating user's individual traits (such as emotion and intent) and system modules to improve the interactions of human-system in data-driven environments.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.83-91
• /
• 2011

Much research has been conducted on the e-learning systems for recommending a learning content to a student based on the difficulty of it. The difficulty is one of the most important factors for selecting a learning content. In the existing learning content recommendation systems, the difficulty of a learning content is determined by the creator. Therefore, it is not easy to apply a standard rule to the difficulty as it is determined by a subjective method. In this paper, we propose an ontology-based method for determining the difficulty of a learning content in order to provide an objective measurement. Previously, ontologies and knowledge maps have been used to recommend a learning content. However, their methods have the same problem because the difficulty is also determined by the creator. In this research, we use an ontology representing the IS-A relationships between words. The difficulty of a learning content is the sum of the weighted path lengths of the words in the learning content. By using this kind of difficulty, we can provide an objective measurement and recommend the proper learning content most suitable for the student's current level.

• The Journal of Society for e-Business Studies
• /
• v.23 no.3
• /
• pp.189-206
• /
• 2018

As the era of $4^{th}$ Industrial Revolution has arrived, education systems are changing in order to prepare for the changes on technological environment. Recently in the education field, flipped learning, which focus on learner-centered with an active communication is suggested, rather than the existing teaching method, which had the characteristic of simply delivering a knowledge. In this research, case study of analyzing a learning effect done by applying a flipped learning on the study of Industrial Security which has the characteristics of timeliness and can accordingly reflect the characteristics of $4^{th}$ Industrial Revolution. In detail, the concept of the study of Industrial Security and flipped learning was arranged, analyzed a current state of education on the study of Industrial Security and exemplary of flipped learning applied class and designed the methodology of flipped learning of this research. Nextly, designed flipped learning method was applied in the actual class of the study of Industrial Security. Lastly, survey and interview was conducted targeting a learner and deducted an implications. The results of survey showed that class participation has increased through active interactions between learners, and flexible learning environments was created which is appropriate for the characteristics of industrial security, which is in need of timeliness response against to diverse security threats of $4^{th}$ Industrial Revolution, and regarded a flipped learning to be appropriate for the study of Industrial security.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• pp.65-76
• /
• 2022

Recently, not only traditional statistical techniques but also machine learning algorithms have been used to make more accurate bankruptcy predictions. But the insolvency rate of companies dealing with financial institutions is very low, resulting in a data imbalance problem. In particular, since data imbalance negatively affects the performance of artificial intelligence models, it is necessary to first perform the data imbalance process. In additional, as artificial intelligence algorithms are advanced for precise decision-making, regulatory pressure related to securing transparency of Artificial Intelligence models is gradually increasing, such as mandating the installation of explanation functions for Artificial Intelligence models. Therefore, this study aims to present guidelines for eXplainable Artificial Intelligence-based corporate bankruptcy prediction methodology applying SMOTE techniques and LIME algorithms to solve a data imbalance problem and model transparency problem in predicting corporate bankruptcy. The implications of this study are as follows. First, it was confirmed that SMOTE can effectively solve the data imbalance issue, a problem that can be easily overlooked in predicting corporate bankruptcy. Second, through the LIME algorithm, the basis for predicting bankruptcy of the machine learning model was visualized, and derive improvement priorities of financial variables that increase the possibility of bankruptcy of companies. Third, the scope of application of the algorithm in future research was expanded by confirming the possibility of using SMOTE and LIME through case application.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2831-2845
• /
• 2022

Compared to the significant approach of project-based learning research, a data-driven design project-based learning has not reached a meaningful consensus regarding the most valid and reliable method for assessing design creativity. This article proposes an advanced information data-interactive learning system for creative design using a service design process that combines a design thinking. We propose a service framework to improve the convergence design process between students and advanced information data analysis, allowing students to participate actively in the data visualization and research using patent data. Solving a design problem by discovery and interpretation process, the Advanced information-interactive learning framework allows the students to verify the creative idea values or to ideate new factors and the associated various feasible solutions. The student can perform the patent data according to a business intelligence platform. Most of the new ideas for solving design projects are evaluated through complete patent data analysis and visualization in the beginning of the service design process. In this article, we propose to adapt advanced information data to educate the service design process, allowing the students to evaluate their own idea and define the problems iteratively until satisfaction. Quantitative evaluation results have shown that the advanced information data-driven learning system approach can improve the design project - based learning results in terms of design creativity. Our findings can contribute to data-driven project-based learning for advanced information data that play a crucial role in convergence design in related standards and other smart educational fields that are linked.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.33 no.4
• /
• pp.130-137
• /
• 2010

This paper analyzes the main factors affecting user selection of a small-sum electronic payment system using survey data of 396 users. Several findings emerge. First, users consider three pillars and eight factors in adopting a new system : system features(stability, security, and flexibility), transaction cost(payment commission and settlement period), and financial capability of provider(stability of financial structure, risk management capability, and funding capability). Second, the stability of the financial structure of the system provider is the most important factor to user acceptance of a new e-payment system. Users tend to consider uncertainty risk more seriously than transaction cost. This reflects the reality that electronic payment system service industry has not fully fledged yet. Third, some moderating effects exist according to payment methods and business usages. As for payment methods, speedy settlement cycle for wired/wireless phone payment, system stability for credit card and account transfer payment, and security for advance payment means are crucial factors. As for business usages, the stability of financial structure for online game content, system stability for music and video content, proxy payment commission for e-learning content, flexibility of the payment system for digital adult content, and security for public services are decisive ones.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.4
• /
• pp.1424-1440
• /
• 2015

It is a challenging problem to search the intended images from a large number of candidates. Content based image retrieval (CBIR) is the most promising way to tackle this problem, where the most important topic is to measure the similarity of images so as to cover the variance of shape, color, pose, illumination etc. While previous works made significant progresses, their adaption ability to dataset is not fully explored. In this paper, we propose a similarity learning method on the basis of probabilistic generative model, i.e., probabilistic latent semantic analysis (PLSA). It first derives Fisher kernel, a function over the parameters and variables, based on PLSA. Then, the parameters are determined through simultaneously maximizing the log likelihood function of PLSA and the retrieval performance over the training dataset. The main advantages of this work are twofold: (1) deriving similarity measure based on PLSA which fully exploits the data distribution and Bayes inference; (2) learning model parameters by maximizing the fitting of model to data and the retrieval performance simultaneously. The proposed method (PLSA-FK) is empirically evaluated over three datasets, and the results exhibit promising performance.

• Smart Structures and Systems
• /
• v.29 no.4
• /
• pp.589-598
• /
• 2022

Timber structures are susceptible to structural damages caused by variations in moisture content (MC), inducing severe durability deterioration and safety issues. Therefore, it is of great significance to detect MC levels in timber structures. Compared to current methods for timber MC detection, which are time-consuming and require bulky equipment deployment, Lead Zirconate Titanate (PZT)-enabled stress wave sensing combined with statistic machine learning classification proposed in this paper show the advantage of the portable device and ease of operation. First, stress wave signals from different MC cases are excited and received by PZT sensors through active sensing. Subsequently, two non-baseline features are extracted from these stress wave signals. Finally, these features are fed to a statistic machine learning classifier (i.e., naïve Bayesian classification) to achieve MC detection of timber structures. Numerical simulations validate the feasibility of PZT-enabled sensing to perceive MC variations. Tests referring to five MC cases are conducted to verify the effectiveness of the proposed method. Results present high accuracy for timber MC detection, showing a great potential to conduct rapid and long-term monitoring of the MC level of timber structures in future field applications.