An Explainable Prediction for Dietary-Related Diseases via Language Models.

Our study harnesses the power of natural language processing (NLP) to explore the relationship between dietary patterns and metabolic health outcomes among Korean adults using data from the Seventh Korea National Health and Nutrition Examination Survey (KNHANES VII). Using Latent Dirichlet Allocation (LDA) analysis, we identified three distinct dietary patterns: "Traditional and Staple", "Communal and Festive", and "Westernized and Convenience-Oriented". These patterns reflect the diversity of dietary preferences in Korea and reveal the cultural and social dimensions influencing eating habits and their potential implications for public health, particularly concerning obesity and metabolic disorders. Integrating NLP-based indices, including sentiment scores and the identified dietary patterns, into our predictive models significantly enhanced the accuracy of obesity and dyslipidemia predictions. This improvement was consistent across various machine learning techniques-XGBoost, LightGBM, and CatBoost-demonstrating the efficacy of NLP methodologies in refining disease prediction models. Our findings underscore the critical role of dietary patterns as indicators of metabolic diseases. The successful application of NLP techniques offers a novel approach to public health and nutritional epidemiology, providing a deeper understanding of the diet-disease nexus. This study contributes to the evolving field of personalized nutrition and emphasizes the potential of leveraging advanced computational tools to inform targeted nutritional interventions and public health strategies aimed at mitigating the prevalence of metabolic disorders in the Korean population.

Enhancing Exchange-Traded Fund Price Predictions: Insights from Information-Theoretic Networks and Node Embeddings.

This study presents a novel approach to predicting price fluctuations for U.S. sector index ETFs. By leveraging information-theoretic measures like mutual information and transfer entropy, we constructed threshold networks highlighting nonlinear dependencies between log returns and trading volume rate changes. We derived centrality measures and node embeddings from these networks, offering unique insights into the ETFs' dynamics. By integrating these features into gradient-boosting algorithm-based models, we significantly enhanced the predictive accuracy. Our approach offers improved forecast performance for U.S. sector index futures and adds a layer of explainability to the existing literature.

Improving data efficiency for analyzing global exchange rate fluctuations based on nonlinear causal network-based clustering.

This study used information theory and network theory to predict the fluctuations of currency values of the machine learning model. For experiments, we calculate the causal relationships between currencies using loarithmic return (log-return) and entropic value-at-risk (EVaR) values of gold price per troy ounce in 48 currencies over 25 years. To quantify the causal relationships, we used the concept of transfer entropy. After quantifying their information flow, we modeled and analyzed those nonlinear causal relationships as a network. The network analysis results confirmed that information flow-based nonlinear causal relationships differed from the commonly-known key currency order. Then, we classified currencies using hierarchical clustering methods based on the configured networks. We predicted fluctuations in currency values using machine learning algorithms based on network topology-based information. As a result, we show that using the data columns in the same communities based on statistically significant nonlinear causal relationships can improve most machine-learning-based fluctuations of currency values for various countries from the perspective of data efficiency.

Dietary Pattern Extraction Using Natural Language Processing Techniques.

In this study, we observed the changes in dietary patterns among Korean adults in the previous decade. We evaluated dietary intake using 24-h recall data from the fourth (2007-2009) and seventh (2016-2018) Korea National Health and Nutrition Examination Survey. Machine learning-based methodologies were used to extract these dietary patterns. Particularly, we observed three dietary patterns from each survey similar to the traditional and Western dietary patterns in 2007-2009 and 2016-2018, respectively. Our results reveal a considerable increase in the number of Western dietary patterns compared with the previous decade. Thus, our study contributes to the use of novel methods using natural language processing (NLP) techniques for dietary pattern extraction to obtain more useful dietary information, unlike the traditional methodology.

Detecting and Analyzing Politically-Themed Stocks Using Text Mining Techniques and Transfer Entropy-Focus on the Republic of Korea's Case.

Politically-themed stocks mainly refer to stocks that benefit from the policies of politicians. This study gave the empirical analysis of the politically-themed stocks in the Republic of Korea and constructed politically-themed stock networks based on the Republic of Korea's politically-themed stocks, derived mainly from politicians. To select politically-themed stocks, we calculated the daily politician sentiment index (PSI), which means politicians' daily reputation using politicians' search volume data and sentiment analysis results from politician-related text data. Additionally, we selected politically-themed stock candidates from politician-related search volume data. To measure causal relationships, we adopted entropy-based measures. We determined politically-themed stocks based on causal relationships from the rates of change of the PSI to their abnormal returns. To illustrate causal relationships between politically-themed stocks, we constructed politically-themed stock networks based on causal relationships using entropy-based approaches. Moreover, we experimented using politically-themed stocks in real-world situations from the schematized networks, focusing on politically-themed stock networks' dynamic changes. We verified that the investment strategy using the PSI and politically-themed stocks that we selected could benchmark the main stock market indices such as the KOSPI and KOSDAQ around political events.

Slurry Coating of Hydroxyapatite on Zirconia Substrate.

Zirconia dental implants require excellent biocompatibility and high bonding strength. In this study, we attempted to fabricate biocompatible zirconia ceramics through surface modification by hydroxyapatite (HA) slurry coating. A hydroxyapatite slurry for spin coating was prepared using two sizes of hydroxyapatite particles. The hydroxyapatite slurry was obtained by adjusting the solid loading, pH range, and dispersant content. The surface roughness of the HA-coated layers on the zirconia substrate depended on the change in microstructural evolution and coating thickness. With repeated coating, the coating thickness gradually increased for both small and large particles. The specimen with two coatings had the maximum surface roughness but displayed different values depending on the size of the HA particles. High surface roughness (Ra; 0.49 µm) could be obtained from the slurry of small particles compared with that of the large particles (Ra; 0.35 µm). During a 14 days in vitro experiment in SBF solution at pH 7.4, no changes were observed in the surface microstructure of the HA coating layer on the zirconia substrate.

Effect of Powder Characteristics on Slip Casting Fabrication of Dental Zirconia Implants.

Dense zirconia compacts were fabricated by slip casting and sintering of nanoscale zirconia powders, and the effect of the powder characteristics (crystallite size, specific surface area, yttria content, and agglomeration) on the slurry and sintered properties was investigated. Three types of commercial 3 mol% yttria-stabilized tetragonal zirconia polycrystals powders were used as the starting powders after the powder characteristic analysis. A zirconia slurry for slip casting was prepared by mixing zirconia powder (solid loading of 60, 65, and 70 wt.%), distilled water, and a dispersant of Darvan C. The green compacts obtained from slip casting were cold isostatic pressed to enhance the close packing and densified by sintering at 1450 °C for 2 h. Highly dense zirconia compacts with a relative density of 99.5% and grain size of 350 nm were obtained based on the powder type and solid loading in the slurry. The microstructure and mechanical hardness of the sintered specimen after slip casting were dependent on the yttria content in the 3 mol% yttria-stabilized tetragonal zirconia polycrystal powder and the solid loading within the slurry.

Effect of Solid Loading on the Sintered Properties of 3 mol% Yttria-Stabilized Tetragonal Zirconia Polycrystals (3Y-TZP) Ceramics via Slip Casting.

Dental zirconia implants fabricated by the mechanical machining and sintering of zirconia blocks have many surface cracks that lead to the deterioration of mechanical strength and the failure of the implant in the body. In this study, we attempted to manufacture an extremely dense and crack-free zirconia specimen by slip casting and pressureless sintering. After the preparation of zirconia slurry by control of its viscosity and by solid loading, highly dense zirconia specimens could be obtained by pressureless sintering at 1450 °C for 2 h. Slurry viscosity was controlled by adjusting the mixing ratio of 3Y-TZP powder, a dispersant, and a pH adjustment agent. Highly dense 3Y-TZP specimens with a relative density of 99% and small grain size of 200-400 nm could be obtained at a solid loading of 50-65 wt%. An optimally dense specimen was fabricated from zirconia slurry with 60 wt% solid loading that had the highest apparent density of 6.07 g/cm³ (99.5%).

A practical solution to improve the nutritional balance of Korean dine-out menus using linear programming.

OBJECTIVE: We analysed optimal nutrient levels using linear programming (LP) to reveal nutritional shortcomings of Korean dine-out meals and to stress the importance of fruits and dairy products for maintaining a healthy diet. DESIGN: LP models that minimize deviation from recommended nutrient values were formulated to analyse deficiency or excess of nutrients under the best situation. SETTING: Korean dine-out menus and nutritional information were taken from the nutrient composition tables for dine-out menus developed by the Ministry of Food and Drug Safety and the nutrient database from Computerized Analysis Program. Acceptable macronutrient distribution ranges of macronutrients such as carbohydrate, protein and fat, and recommended intake levels for energy, vitamins, minerals and cholesterol, by sex, were based on the Dietary Reference Intake for Koreans aged 30-49 years.ParticipantsOptimization was performed on selecting the optimal Korean meal combination. RESULTS: LP optimization models showed that it is unlikely to satisfy all nutrient recommendations with any combination of dine-out menus. Specifically, meal combinations of Korean dine-out menus had high levels of Na and cholesterol and low levels of vitamins and minerals. Four formulations were considered to compare the effects of controlling Na and including fruit and dairy products. The unbalanced diet was resolved with extra consumption of fruits and dairy products. CONCLUSIONS: The best meal combination in dine-out menus, even though the proportion and pairing of menus may be unrealistic, is not healthy, and thus one should consume fruits and dairy products to maintain a balanced diet.