• Clean Technology
• /
• v.29 no.2
• /
• pp.87-94
• /
• 2023

The recovery of valuable metals from waste lithium-based secondary batteries is very important in terms of efficiently utilizing earth's limited number of resources. Currently, the cathode material of a LiFePO₄ battery, a type of battery which is widely used in automobiles, contains approximately 5% lithium. After use, the lithium in these batteries can be used again as a raw material for new batteries through lithium recycling. In this study, low-concentration sulfuric acid, a commonly used type of inorganic acid, was used to selectively leach the lithium contained in a waste LiFePO₄ cathode material powder. In addition, in order to compare and analyze the leaching efficiency and separation efficiency of each component, the optimalleaching conditions were derived by applying a two-step leaching process with pulp density being used as a variable during leaching. When leaching with pulp density as a variable, it was confirmed that at a pulp density of 200 g/L, the separation efficiency was approximately 200 times higher than at other pulp densities because the iron and phosphorus components were hardly leached at this pulp density. Accordingly, the pulp density of 200 g/L was used tooptimize the leaching conditions for the selective leaching and recovery of lithium.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.129-148
• /
• 2023

Bitcoin is a blockchain technology-based digital currency that has been recognized as a representative cryptocurrency and a financial investment asset. Due to its highly volatile nature, Bitcoin has gained a lot of attention from investors and the public. Based on this popularity, numerous studies have been conducted on price and trend prediction using machine learning and deep learning. This study employed LSTM (Long Short Term Memory) and CNN (Convolutional Neural Networks), which have shown potential for predictive performance in the finance domain, to enhance the classification accuracy in Bitcoin price trend prediction. XAI(eXplainable Artificial Intelligence) techniques were applied to the predictive model to enhance its explainability and interpretability by providing a comprehensive explanation of the model. In the empirical experiment, CNN was applied to technical indicators and Google trend data to build a Bitcoin price trend prediction model, and the CNN model using both technical indicators and Google trend data clearly outperformed the other models using neural networks, SVM, and LSTM. Then SHAP(Shapley Additive exPlanations) was applied to the predictive model to obtain explanations about the output values. Important prediction drivers in input variables were extracted through global interpretation, and the interpretation of the predictive model's decision process for each instance was suggested through local interpretation. The results show that our proposed research framework demonstrates both improved classification accuracy and explainability by using CNN, Google trend data, and SHAP.

• Clean Technology
• /
• v.29 no.2
• /
• pp.109-117
• /
• 2023

The purpose of this study is to develop a method for separating antioxidants and sugars from grape skin extract. The extract was first mixed with a variety of organic solvents to investigate whether the separation was feasible. When employing acetone, ethanol, dimethylsulfoxide, or dimethylformamide, the organic solvent-extract combination formed a single phase. However, when benzene, ethyl acetate, or n-hexane was added to the extract, the mixture separated into an organic and an aqueous phase and the pigments remained in the aqueous phase. On the other hand, when polyethylene glycol-2,000 (PEG-2000) and sodium citrate were added to the extract, the mixture was separated into three layers, with the majority of the flavonoids migrating to the top layer and 53% of the extract's glucose migrating to the bottom layer. The top layer had significant antioxidant activity, whereas the bottom layer showed no antioxidant activity. The glucose recovery in the bottom layer increased as the molecular weight of PEG increased and the highest recovery (67%) was observed when PEG-8,000 was added. The highest flavonoid separation was observed with PEG-2,000, followed by PEG-8,000 and PEG-400. The flavonoid separation when PEG-2,000 was added resulted in a flavonoid recovery of 48% and 0.2% from the top and bottom layers, respectively. Examining the effect of the separated solution using the agar disc diffusion method on yeast cell growth confirmed that the addition of the extract, the top, and the bottom layer did not inhibit cell growth.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.189-217
• /
• 2023

The metaverse is a virtual world where individuals engage in social, economic, and cultural activities using avatars, which represent an alternate version of oneself within the virtual realm. While the metaverse has garnered global attention recently, research exploring the identity manifested through avatars within the metaverse remains limited. This study investigates the influence of four IT artifact characteristics related to avatar usage in the metaverse-avatar representation, avatar copresence, avatar profiling, and avatar-space interaction-on perceived avatar identity verification. A survey was conducted with 196 experienced users of the Zepeto platform, and hypotheses were tested using structural equation modeling. The analysis results indicate that the use of IT artifacts enabling avatar representation, avatar copresence, and avatar-space interaction has a positive impact on perceived avatar identity verification. This achieved self-verification indirectly influences the satisfaction and subsequent intention to continue using the metaverse. This study contributes to the academic field by empirically verifying the metaverse technological factors that influence the projected identity onto avatars within the metaverse. Furthermore, it is expected to provide effective guidelines for metaverse platform companies in designing and implementing the metaverse.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.267-283
• /
• 2023

The COVID-19 pandemic, which began in December 2019 and continues to this day, has left the public needing information to help them cope with the pandemic. However, COVID-19-related fake news on social media seriously threatens the public's health. In particular, if fake news related to COVID-19 is massively spread with similar content, the time required for verification to determine whether it is genuine or fake will be prolonged, posing a severe threat to our society. In response, academics have been actively researching intelligent models that can quickly detect COVID-19-related fake news. Still, the data used in most of the existing studies are in English, and studies on Korean fake news detection are scarce. In this study, we collect data on COVID-19-related fake news written in Korean that is spread on social media and propose an intelligent fake news detection model using it. The proposed model utilizes the frequency information of parts of speech, one of the linguistic characteristics, to improve the prediction performance of the fake news detection model based on Doc2Vec, a document embedding technique mainly used in prior studies. The empirical analysis shows that the proposed model can more accurately identify Korean COVID-19-related fake news by increasing the recall and F1 score compared to the comparison model.

• International Journal of Oral Biology
• /
• v.48 no.2
• /
• pp.9-18
• /
• 2023

The rapid detection of bacteria in the oral cavity, its species identification, and bacterial count determination are important to diagnose oral diseases caused by pathogenic bacteria. The existing clinical microbial diagnosis methods are time-consuming as they involve observing patients' samples under a microscope or culturing and confirming bacteria using polymerase chain reaction (PCR) kits, making the process complex. Therefore, it is required to analyze the development status of substances and systems that can rapidly detect and analyze pathogenic microorganisms in the oral cavity. With research advancements, a close relationship between oral and systemic diseases has been identified, making it crucial to identify the changes in the oral cavity bacterial composition. Additionally, an early and accurate diagnosis is essential for better prognosis in periodontal disease. However, most periodontal disease-causing pathogens are anaerobic bacteria, which are difficult to identify using conventional bacterial culture methods. Further, the existing PCR method takes a long time to detect and involves complicated stages. Therefore, to address these challenges, the concept of point-of-care (PoC) has emerged, leading to the study and implementation of various chair-side test methods. This study aims to investigate the different PoC diagnostic methods introduced thus far for identifying pathogenic microorganisms in the oral cavity. These are classified into three categories: 1) microbiological tests, 2) microchemical tests, and 3) genetic tests. The microbiological tests are used to determine the presence or absence of representative causative bacteria of periodontal diseases, such as A. actinomycetemcomitans, P. gingivalis, P. intermedia, and T. denticola. However, the quantitative analysis remains impossible, and detecting pathogens other than the specific ones is challenging. The microchemical tests determine the activity of inflammation or disease by measuring the levels of biomarkers present in the oral cavity. Although this diagnostic method is based on increase in the specific biomarkers proportional to inflammation or disease progression in the oral cavity, its commercialization is limited due to low sensitivity and specificity. The genetic tests are based on the concept that differences in disease vulnerability and treatment response are caused by the patient's DNA predisposition. Specifically, the IL-1 gene is used in such tests. PoC diagnostic methods developed to date serve as supplementary diagnostic methods and tools for patient education, in addition to existing diagnostic methods, although they have limitations in diagnosing oral diseases alone. Research on various PoC test methods that can analyze and manage the oral cavity bacterial composition is expected to become more active, aligning with the shift from treatment-oriented to prevention-oriented approaches in healthcare.

• Clean Technology
• /
• v.29 no.2
• /
• pp.151-159
• /
• 2023

The realization of carbon neutrality requires cooperation from various stakeholders and the utilization of a governance system. The criteria for participating members are crucial for the successful operation of governance, and it is especially necessary for experts who can provide scientific advice for policy implementation to share a framework for successful consensus. In this study, governance model theory and model structure, governance common success factors by case, and the application of governance cases in the climate and environmental sector of Seoul, were investigated and analyzed to derive common success factors in order to present the activity standards of the science and technology experts participating in governance. The study of the model theory suggested that the model structure is commonly composed of a basic condition-process-result structure, and it was confirmed that common success factors can be derived at the process stage which is the activity period of members. Through the case study of common success factors, overlapping factors were found to be reliability, accountability, transparency, networks, and related factors. The validity of the common success factors was verified using the analysis results of satisfaction survey data from Seoul Governance Committee participants. The results confirmed that reliability was the most valuable factor followed by networks, transparency, and responsibility, and it was found that the related factors were appropriately derived. The findings of this study are expected to be used as an activity factor for science and technology experts to increase the acceptability and effectiveness of carbon-neutral policies in the future.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.23-34
• /
• 2023

Wearable technology for military applications has received considerable attention as a means of personal status check and monitoring. Among many, an implementation to recognize specific motion states of a human is promising in that allows active management of troops by immediately collecting the operational status and movement status of individual soldiers. In this study, as an extension of military wearable application research, a new ankle wearable device is proposed that can glean the information of a soldier on the battlefield on which action he/she takes in which environment. Presuming a virtual situation, the soldier's upper limbs are easily exposed to uncertainties about circumstances. Therefore, a sensing module is attached to the ankle of the soldier that may always interact with the ground. The obtained data comprises 3-axis accelerations and 3-axis rotational velocities, which cannot be interpreted by hand-made algorithms. In this study, to discern the behavioral characteristics of a human using these dynamic data, a data-driven model is introduced; four features extracted from sliced data (minimum, maximum, mean, and standard deviation) are utilized as an input of the model to learn and classify eight primary military movements (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). As a result, the proposed device could recognize a movement status of a solider with 95.16% accuracy in an arbitrary test situation. This research is meaningful since an effective way of motion recognition has been introduced that can be furtherly extended to various military applications by incorporating wearable technology and artificial intelligence.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.35-56
• /
• 2023

With the development of information and communication technology, numerous reviews are continuously posted on websites, which causes information overload problems. Therefore, users face difficulty in exploring reviews for their decision-making. To solve such a problem, many studies on review helpfulness prediction have been actively conducted to provide users with helpful and reliable reviews. Existing studies predict review helpfulness mainly based on the features included in the review. However, such studies disable providing the reason why predicted reviews are helpful. Therefore, this study aims to propose a methodology for applying eXplainable Artificial Intelligence (XAI) techniques in review helpfulness prediction to address such a limitation. This study uses restaurant reviews collected from Yelp.com to compare the prediction performance of six models widely used in previous studies. Next, we propose an explainable review helpfulness prediction model by applying the XAI technique to the model with the best prediction performance. Therefore, the methodology proposed in this study can recommend helpful reviews in the user's purchasing decision-making process and provide the interpretation of why such predicted reviews are helpful.

• Informatization Policy
• /
• v.30 no.2
• /
• pp.46-67
• /
• 2023

There are criticisms that, despite the proactive government policy on open government data (hereinafter "open data"), certain highly demanded data remains restricted due to legal constraints. In this study, we aim to analyze the factors that limit the opening and utilization of open data, focusing on cases wherein requests for open data provision have been denied. We will explore possible approaches that are in harmony with the Open Data Law while examining the constitutional value of open data, considering the foundational Open Data Charter that underpins the government's data policy. We will also examine cases wherein requests for data provision have been denied for institutional reasons, with nearly half of these cases involving open data that includes personal information. It is necessary to explore the potential for improvement in these cases. Furthermore, considering the recent amendment to the Personal Information Protection Act, which allows for the processing of pseudonymous information without the consent of the data subject for limited purposes, it is an opportune time to consider the need for amending the Open Data Law to facilitate broader access and utilization of open data for the nation. Lastly, we will propose institutional improvement directions aligned with the opening and utilization of open data by examining the constraints of and need for improvement in the selected target laws.