• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.542-549
• /
• 2023

Since the growing interest in surrogate modeling, there has been continuous research aimed at simulating nonlinear chemical processes using data-driven machine learning. However, the opaque nature of machine learning models, which limits their interpretability, poses a challenge for their practical application in industry. Therefore, this study aims to analyze chemical processes using Explainable Artificial Intelligence (XAI), a concept that improves interpretability while ensuring model accuracy. While conventional sensitivity analysis of chemical processes has been limited to calculating and ranking the sensitivity indices of variables, we propose a methodology that utilizes XAI to not only perform global and local sensitivity analysis, but also examine the interactions among variables to gain physical insights from the data. For the ammonia synthesis process, which is the target process of the case study, we set the temperature of the preheater leading to the first reactor and the split ratio of the cold shot to the three reactors as process variables. By integrating Matlab and Aspen Plus, we obtained data on ammonia production and the maximum temperatures of the three reactors while systematically varying the process variables. We then trained tree-based models and performed sensitivity analysis using the SHAP technique, one of the XAI methods, on the most accurate model. The global sensitivity analysis showed that the preheater temperature had the greatest effect, and the local sensitivity analysis provided insights for defining the ranges of process variables to improve productivity and prevent overheating. By constructing alternative models for chemical processes and using XAI for sensitivity analysis, this work contributes to providing both quantitative and qualitative feedback for process optimization.

• International Commerce and Information Review
• /
• v.17 no.3
• /
• pp.29-57
• /
• 2015

The purpose of this study is to find the factors of Social Network Games of continuous game flow and addiction. This study analyzes the significant factors of the addiction of SNGs from three categories. It also seeks to find out what relation between continuous game flow and addiction in SNGs. The model consists of three categories (SNG characteristic, User characteristic, and Environmental characteristic). The research model was conducted through the structural equation modeling(SEM) approach, and tested using 374 questionnaires. The results indicated that SNG characteristic(accessibility, enjoyment, feedback), User characteristic(self-control), Environmental characteristic(social interaction, subjective norm) have a positive effect on continuous game flow. The findings also that continuous game flow plays a moderation role that affects addiction. Finally, we discussed the research results and offered relevant suggestions for schools, firms, and future studies

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.6
• /
• pp.983-990
• /
• 2009

Campus dormitories function as residence halls, which are quarters or entire buildings for residents to conveniently sleep, eat, and study in. And these functions lead us to refer to dormitories as quarters providing residence, food, and an academic atmosphere. Yet, of these functions, the restaurant service acts on dormitory applicants' and their parents' choice of dormitories as strongly as the others do. It is not optional for the residents but compulsory. All residents are required to eat at the restaurants attached to their dormitories. Therefore, when most of the dormitory applicants and their parents look for their favorite dormitories, they won't miss looking into how good the restaurant service is. Considering this tendency, this research, which takes samples of residents as subjects of investigation, aims to survey the service quality of the dormitory restaurants and to find how to enhance the service quality. The result, which is measured and analyzed on the basis of statistical methods, indicates that the responsiveness and empathy to the restaurant service are statistically the significant factors for dormitory applicants and their parents in choosing their favorite dormitories.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.1
• /
• pp.149-156
• /
• 2014

NGE(Nested Generalized Exemplar Method) can increase the performance of the noisy data at the same time, can reduce the size of the model. It is the optimal distance-based classification method using a matching rule. NGE cross or overlap hyperrectangles generated in the learning has been noted to inhibit the factors. In this paper, We propose the DHGen(Dominant Hyperrectangle Generation) algorithm which avoids the overlapping and the crossing between hyperrectangles, uses interval weights for mixed hyperrectangles to be splited based on the mutual information. The DHGen improves the classification performance and reduces the number of hyperrectangles by processing the training set in an incremental manner. The proposed DHGen has been successfully shown to exhibit comparable classification performance to k-NN and better result than EACH system which implements the NGE theory using benchmark data sets from UCI Machine Learning Repository.

• Explosives and Blasting
• /
• v.37 no.4
• /
• pp.26-35
• /
• 2019

In designing a gravity-type anchorage of earth-anchored suspension bridge, the contact friction between a blasted rock mass and the concrete anchorage plays a key role in the stability of the entire anchorage. Therefore, it is vital to understand the shear behavior of the interface between the blasted rock mass and concrete. In this study, a portable 3D LiDAR scanner was utilized to scan the blasted bottom surfaces, and rock surface roughness was quantitatively analyzed from the scanned profiles to apply to 3D FEM modelling. In addition, based on the 3D FEM model, a three-dimensional dynamic fracture process analysis (DFPA-3D) technique was applied to study on the shear behavior of the interface between blasted rock and concrete through direct shear tests, which was analyzed under constant normal load (CNL). The effects of normal stress and the joint roughness on shear failure behavior are also analyzed.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.8
• /
• pp.189-196
• /
• 2020

In this paper, we propose a study on the purchasing intent of the new e-commerce consumer, the coronavirus may once again drive the structural change of China's economy, and the new online marketing model will be noticed during the epidemic. Through 438 questionnaires collected on the Internet, frequency analysis, element analysis, reliability analysis and structural equation analysis were performed using SPSS V22.0 and AMOS V22.0 methods. Study the validation of hypotheses in the model to reveal the reasons why consumers in the new e-business are exposed. The results show that e-commerce features of Internet celebrities and individual characteristics of Internet celebrities can only enhance consumers' satisfaction. Quasi social relationships only increase consumer satisfaction without generating the will to purchase directly. Consumer satisfaction is the core foundation that dominates long-term consumption. E-commerce should focus on the ability of online celebrities to sell their expertise and the adaptability of value and product characteristics when conducting online celebrity marketing.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.8
• /
• pp.47-54
• /
• 2020

Developmental disorders are impairments of brain and/or central nervous system and refer to a disorder of brain function that affects languages, communication skills, perception, sociality and so on. In diagnosis of developmental disorders, behavioral response such as expressing emotions in proper situation is one of observable indicators that tells whether or not individual has the disorders. However, diagnosis by observation can allow subjective evaluation that leads erroneous conclusion. This research presents the technological environment and data acquisition system for AI based screening of autism disorder. The environment was built considering activities for two screening protocols, namely Autism Diagnostic Observation Schedule (ADOS) and Behavior Development Screening for Toddler (BeDevel). The activities between therapist and baby during the screening are fully recorded. The proposed software in this research was designed to support recording, monitoring and data tagging for learning AI algorithms.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.4
• /
• pp.131-142
• /
• 2018

In Korea, for the past 50 years, industrial parks have played an important role in economic growth as a cluster of national key industries. However, due to various problems of these old industrial parks, they are weakening competitiveness. It is necessary to be converted into a model for the management and fostering of high-tech industrial complex park by classifying them into development plans, management plans, and support plans according to types and characteristics of industrial parks. For this purpose, we propose CIPs (Connected-Industrial parks) using new technologies such as Cloud Computing, RFID, WSN, CPS, and Big Data analysis based on IoT. It is a hub that supports various services in transportation, warehousing and manufacturing fields while possessing and operating physical assets as concept. each CIP (Connected-Industrial park) is connected and expanded Through such CIPs, network-type collaborative manufacturing and intelligent logistics innovation enables cost reduction, delivery shortening, quality improvement.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.4
• /
• pp.159-168
• /
• 2018

In recent, mobile augmented reality game which has been attracting high attention is considered to be an good approach to increase immersion. In conventional augmented reality-based games that recognize target objects using a mobile camera and show the matching game characters, touch-based interaction is mainly used. In this paper, we propose an intuitive interaction method which manipulates a deformable game object by moving a target image of augmented reality in order to enhacne the immersion of the game. In the proposed method, the deformable object is intuitively manipulated by calculating the distance and direction between the target images and by adjusting the external force applied to the deformable object using them. In this paper, we focus on the cloth deformable object which is widely used for natural object animation in game contents and implement natural cloth simulation interacting with game objects represented by wind and rigid objects. In the experiments, we compare the previous commercial cloth model with the proposed method and show the proposed method can represent cloth animation more realistically.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.5
• /
• pp.487-494
• /
• 2019

A Small-Sat Power System Design and Development should be depend on space environment such as solar wind with Electromagnetic field by hurdle of techniques. It is surmount solution of trend that will unitize and converge with power module in these days. The level of modularize means that applying Universal Middleware for payload power module requirements. The scope of target system is a main power provider module and operational subunit that can be implemented with the final power module distribution loads to consume for continuous process. A Universal Middleware strengthen to build power module from satellite power system should be accuracy and consuming data. A Power Service Module and dynamic system drive interactive management between power distribution and consumer module by Range Control. Consequently, suggesting evaluation, unexpecting payload system power consumer that makes fine variable resources in the development design process and efficiency.