Predicting the daily number of patients for allergic diseases using PM10 concentration based on spatiotemporal graph convolutional networks.

Air pollution causes and exacerbates allergic diseases including asthma, allergic rhinitis, and atopic dermatitis. Precise prediction of the number of patients afflicted with these diseases and analysis of the environmental conditions that contribute to disease outbreaks play crucial roles in the effective management of hospital services. Therefore, this study aims to predict the daily number of patients with these allergic diseases and determine the impact of particulate matter (PM10) on each disease. To analyze the spatiotemporal correlations between allergic diseases (asthma, atopic dermatitis, and allergic rhinitis) and PM10 concentrations, we propose a multi-variable spatiotemporal graph convolutional network (MST-GCN)-based disease prediction model. Data on the number of patients were collected from the National Health Insurance Service from January 2013 to December 2017, and the PM10 data were collected from Airkorea during the same period. As a result, the proposed disease prediction model showed higher performance (R2 0.87) than the other deep-learning baseline methods. The synergic effect of spatial and temporal analyses improved the prediction performance of the number of patients. The prediction accuracies for allergic rhinitis, asthma, and atopic dermatitis achieved R2 scores of 0.96, 0.92, and 0.86, respectively. In the ablation study of environmental factors, PM10 improved the prediction accuracy by 10.13%, based on the R2 score.

Simultaneous Treatment of 5-Aminosalicylic Acid and Treadmill Exercise More Effectively Improves Ulcerative Colitis in Mice.

Ulcerative colitis (UC) is characterized by continuous mucosal ulceration of the colon, starting in the rectum. 5-Aminosalicylic acid (5-ASA) is the main therapy for ulcerative colitis; however, it has side effects. Physical exercise effectively increases the number of anti-inflammatory and anti-immune cells in the body. In the current study, the effects of simultaneous treatment of treadmill exercise and 5-ASA were compared with monotherapy with physical exercise or 5-ASA in UC mice. To induce the UC animal model, the mice consumed 2% dextran sulfate sodium dissolved in drinking water for 7 days. The mice in the exercise groups exercised on a treadmill for 1 h once a day for 14 days after UC induction. The 5-ASA-treated groups received 5-ASA by enema injection using a 200 µL polyethylene catheter once a day for 14 days. Simultaneous treatment improved histological damage and increased body weight, colon weight, and colon length, whereas the disease activity index score and collagen deposition were decreased. Simultaneous treatment with treadmill exercise and 5-ASA suppressed pro-inflammatory cytokines and apoptosis following UC. The benefits of this simultaneous treatment may be due to inhibition on nuclear factor-κB/mitogen-activated protein kinase signaling activation. Based on this study, simultaneous treatment of treadmill exercise and 5-ASA can be considered as a new therapy of UC.

Evaluation of exhaust emissions of agricultural tractors using portable emissions measurement system in Korean paddy field.

Recently, diesel engine emissions have been designated as a first-class carcinogen by the World Health Organization (WHO). As such, problems with diesel engine emissions continue to increase around the world. This study aimed to analyze the emissions (CO, NOx, PM) of agricultural tractors during farming operations in order to build a reliable national inventory of air pollutant emissions. Emission data were collected using a portable emission measurement system during actual agricultural operation. The load factor (LF) of the engine was calculated using the collected engine information, the emission factor was analyzed using the LF and the measured emission. The LF was significantly different from the current standard value of 0.48, which is used in Korea to calculate exhaust emissions. The deviation ratio of the emission factor was 0.039 ~ 56.59 compared to Tier-4 emission regulation standards. Under many conditions, the calculated emission factor was higher than the emission limit. Thus, this study provides useful information for emission inventory construction through emission calculation under actual conditions and suggests the need to realize the currently applied emission factor.

Fragment molecular orbital-based variational quantum eigensolver for quantum chemistry in the age of quantum computing.

Quantum computers offer significant potential for complex system analysis, yet their application in large systems is hindered by limitations such as qubit availability and quantum hardware noise. While the variational quantum eigensolver (VQE) was proposed to address these issues, its scalability remains limited. Many efforts, including new ansätze and Hamiltonian modifications, have been made to overcome these challenges. In this work, we introduced the novel Fragment Molecular Orbital/Variational Quantum Eigensolver (FMO/VQE) algorithm. This method combines the fragment molecular orbital (FMO) approach with VQE and efficiently utilizes qubits for quantum chemistry simulations. Employing the UCCSD ansatz, the FMO/VQE achieved an absolute error of just 0.053 mHa with 8 qubits in a [Formula: see text] system using the STO-3G basis set, and an error of 1.376 mHa with 16 qubits in a [Formula: see text] system with the 6-31G basis set. These results indicated a significant advancement in scalability over conventional VQE, maintaining accuracy with fewer qubits. Therefore, our FMO/VQE method exemplifies how integrating fragment-based quantum chemistry with quantum algorithms can enhance scalability, facilitating more complex molecular simulations and aligning with quantum computing advancements.

Survival Prediction Model for Patients with Hepatocellular Carcinoma and Extrahepatic Metastasis Based on XGBoost Algorithm.

Purpose: Accurate estimation of survival is of utmost importance in patients with hepatocellular carcinoma (HCC) and extrahepatic metastasis. This study aimed to develop a survival prediction model using real-world data. Patients and Methods: A total of 993 patients with treatment-naïve HCC and extrahepatic metastasis were included from 13 Korean hospitals between 2013 and 2018. Patients were randomly divided into a training set (70.0%) and a test set (30.0%). The eXtreme Gradient Boosting (XGBoost) algorithm was applied to predict survival at 3, 6, and 12 months. Results: The mean age of the patients was 60.8 ± 12.3 years, and 85.4% were male. During the study period, 96.1% died, and median survival duration was 4.0 months. In multivariate analysis, Child-Pugh class, number and size of tumors, presence of vascular or bile duct invasion, lung or bone metastasis, serum AFP, and primary anti-HCC treatment were associated with survival. We constructed a model for survival prediction based on the relevant variables, which is available online (https://metastatic-hcc.onrender.com/form). Our model demonstrated high performance, with areas under the receiver operating characteristic curves of 0.778, 0.794, and 0.784 at 3, 6, and 12 months, respectively. Feature importance analysis indicated that the primary anti-HCC treatment had the highest importance. Conclusion: We developed a model to predict the survival of patients with HCC and extrahepatic metastasis, which demonstrated good discriminative ability. Our model would be helpful for personalized treatment and for improving the prognosis.

CLAMS: A Cluster Ambiguity Measure for Estimating Perceptual Variability in Visual Clustering.

Visual clustering is a common perceptual task in scatterplots that supports diverse analytics tasks (e.g., cluster identification). However, even with the same scatterplot, the ways of perceiving clusters (i.e., conducting visual clustering) can differ due to the differences among individuals and ambiguous cluster boundaries. Although such perceptual variability casts doubt on the reliability of data analysis based on visual clustering, we lack a systematic way to efficiently assess this variability. In this research, we study perceptual variability in conducting visual clustering, which we call Cluster Ambiguity. To this end, we introduce CLAMS, a data-driven visual quality measure for automatically predicting cluster ambiguity in monochrome scatterplots. We first conduct a qualitative study to identify key factors that affect the visual separation of clusters (e.g., proximity or size difference between clusters). Based on study findings, we deploy a regression module that estimates the human-judged separability of two clusters. Then, CLAMS predicts cluster ambiguity by analyzing the aggregated results of all pairwise separability between clusters that are generated by the module. CLAMS outperforms widely-used clustering techniques in predicting ground truth cluster ambiguity. Meanwhile, CLAMS exhibits performance on par with human annotators. We conclude our work by presenting two applications for optimizing and benchmarking data mining techniques using CLAMS. The interactive demo of CLAMS is available at clusterambiguity.dev.

Classes are not Clusters: Improving Label-based Evaluation of Dimensionality Reduction.

A common way to evaluate the reliability of dimensionality reduction (DR) embeddings is to quantify how well labeled classes form compact, mutually separated clusters in the embeddings. This approach is based on the assumption that the classes stay as clear clusters in the original high-dimensional space. However, in reality, this assumption can be violated; a single class can be fragmented into multiple separated clusters, and multiple classes can be merged into a single cluster. We thus cannot always assure the credibility of the evaluation using class labels. In this paper, we introduce two novel quality measures-Label-Trustworthiness and Label-Continuity (Label-T&C)-advancing the process of DR evaluation based on class labels. Instead of assuming that classes are well-clustered in the original space, Label-T&C work by (1) estimating the extent to which classes form clusters in the original and embedded spaces and (2) evaluating the difference between the two. A quantitative evaluation showed that Label-T&C outperform widely used DR evaluation measures (e.g., Trustworthiness and Continuity, Kullback-Leibler divergence) in terms of the accuracy in assessing how well DR embeddings preserve the cluster structure, and are also scalable. Moreover, we present case studies demonstrating that Label-T&C can be successfully used for revealing the intrinsic characteristics of DR techniques and their hyperparameters.

MoNetExplorer: A Visual Analytics System for Analyzing Dynamic Networks with Temporal Network Motifs.

Partitioning a dynamic network into subsets (i.e., snapshots) based on disjoint time intervals is a widely used technique for understanding how structural patterns of the network evolve. However, selecting an appropriate time window (i.e., slicing a dynamic network into snapshots) is challenging and time-consuming, often involving a trial-and-error approach to investigating underlying structural patterns. To address this challenge, we present MoNetExplorer, a novel interactive visual analytics system that leverages temporal network motifs to provide recommendations for window sizes and support users in visually comparing different slicing results. MoNetExplorer provides a comprehensive analysis based on window size, including (1) a temporal overview to identify the structural information, (2) temporal network motif composition, and (3) node-link-diagram-based details to enable users to identify and understand structural patterns at various temporal resolutions. To demonstrate the effectiveness of our system, we conducted a case study with network researchers using two real-world dynamic network datasets. Our case studies show that the system effectively supports users to gain valuable insights into the temporal and structural aspects of dynamic networks.

Effect of aging on the formation and growth of colonic epithelial organoids by changes in cell cycle arrest through TGF-ß-Smad3 signaling.

BACKGROUND: This study aimed to investigate how aging alters the homeostasis of the colonic intestinal epithelium and regeneration after tissue injury using organoid models and to identify its underlying molecular mechanism. METHODS: To investigate aging-related changes in the colonic intestinal epithelium, we conducted organoid cultures from old (older than 80 weeks) and young (6-10 weeks) mice and compared the number and size of organoids at day 5 of passage 0 and the growth rate of organoids between the two groups. RESULTS: The number and size of organoids from old mice was significantly lower than that from young mice (p < 0.0001) at day 5 of passage 0. The growth rate of old-mouse organoids from day 4 to 5 of passage 0 was significantly slower than that of young-mouse organoids (2.21 times vs. 1.16 times, p < 0.001). RNA sequencing showed that TGF-ß- and cell cycle-associated genes were associated with the aging effect. With regard to mRNA and protein levels, Smad3 and p-Smad3 in the old-mouse organoids were markedly increased compared with those in the young-mouse organoids. Decreased expression of ID1, increased expression of p16INK4a, and increased cell cycle arrest were observed in the old mouse-organoids. Treatment with SB431542, a type I TGF-ß receptor inhibitor, significantly increased the formation and growth of old-mouse organoids, and TGF-ß1 treatment markedly suppressed the formation of young-mouse organoids. In the acute dextran sulfate sodium-colitis model and its organoid experiments, the colonic epithelial regeneration after tissue injury in old mice was significantly decreased compared with young mice. CONCLUSIONS: Aging reduced the formation ability and growth rate of colonic epithelial organoids by increasing cell cycle arrest through TGF-ß-Smad3-p16INK4a signaling.

Lacticaseibacillus Casei IDCC 3451 Strengthen Digestibility of Plant-based Proteins in Mice.

The demand for plant-based proteins as alternative meat sources continues to increase because of environmental concerns, animal welfare, and religious reasons. However, plant-based proteins have low digestibility than real meat, which should be overcome. In the present study, the effect of co-administration of legumin protein mixture and the probiotic strain on plasma concentration of amino acids was investigated as a strategy of enhancement in protein digestion. First, the proteolytic activity of the four probiotic strains was compared. As a result, Lacticaseibacillus casei IDCC 3451 was identified as an optimal probiotic strain that efficiently digested the legumin protein mixture by forming the largest halo produced by proteolysis. Next, to investigate whether the co-administration of legumin protein mixture and L. casei IDCC 3451 could synergically improve digestibility, mice were fed either a high-protein diet or a high-protein diet with L. casei IDCC 3451 for 8 weeks. Compared to only in the high-protein diet only group, the concentrations of branched chain amino acids and essential amino acids were 1.36 and 1.41 times higher in the co-administered group, respectively. Therefore, co-supplementation of plant-based proteins with L. casei IDCC 3451 can be suggested to improve protein digestibility based on the this study.

Ensemble learning-based radiomics with multi-sequence magnetic resonance imaging for benign and malignant soft tissue tumor differentiation.

Many previous studies focused on differentiating between benign and malignant soft tissue tumors using radiomics model based on various magnetic resonance imaging (MRI) sequences, but it is still unclear how to set up the input radiomic features from multiple MRI sequences. Here, we evaluated two types of radiomics models generated using different feature incorporation strategies. In order to differentiate between benign and malignant soft tissue tumors (STTs), we compared the diagnostic performance of an ensemble of random forest (R) models with single-sequence MRI inputs to R models with pooled multi-sequence MRI inputs. One-hundred twenty-five STT patients with preoperative MRI were retrospectively included and consisted of training (n = 100) and test (n = 25) sets. MRI included T1-weighted (T1-WI), T2-weighted (T2-WI), contrast-enhanced (CE)-T1-WI, diffusion-weighted images (DWIs, b = 800 sec/mm2) and apparent diffusion coefficient (ADC) maps. After tumor segmentation on each sequence, 100 original radiomic features were extracted from each sequence image and divided into three-feature sets: T features from T1- and T2-WI, CE features from CE-T1-WI, and D features from DWI and ADC maps. Four radiomics models were built using Lasso and R with four combinations of three-feature sets as inputs: T features (R-T), T+CE features (R-C), T+D features (R-D), and T+CE+D features (R-A) (Type-1 model). An ensemble model was built by soft voting of five, single-sequence-based R models (Type-2 model). AUC, sensitivity, specificity, and accuracy of each model was calculated with five-fold cross validation. In Type-1 model, AUC, sensitivity, specificity, and accuracy were 0.752, 71.8%, 61.1%, and 67.2% in R-T; 0.756, 76.1%, 70.4%, and 73.6% in R-C; 0.750, 77.5%, 63.0%, and 71.2% in R-D; and 0.749, 74.6%, 61.1%, and 68.8% R-A models, respectively. AUC, sensitivity, specificity, and accuracy of Type-2 model were 0.774, 76.1%, 68.5%, and 72.8%. In conclusion, an ensemble method is beneficial to incorporate features from multi-sequence MRI and showed diagnostic robustness for differentiating malignant STTs.

Potential of Bifidobacterium lactis IDCC 4301 isolated from breast milk-fed infant feces as a probiotic and functional ingredient.

Probiotics provide important health benefits to the host by improving intestinal microbial balance and have been widely consumed as dietary supplements. In this study, we investigated whether Bifidobacterium lactis IDCC 4301 (BL), isolated from feces of breast milk-fed infants, is safe to consume. Based on the guidelines established by the European Food Safety Authority (EFSA), safety tests such as antibiotic susceptibility, hemolysis, toxic compound formation (i.e., biogenic amine and d-lactate), single-dose acute oral toxicity, and extracellular enzymatic activities were performed. In addition, toxigenic genes, antibiotic resistance genes, and mobile genetic elements were investigated by analyzing the genome sequence of BL. BL was susceptible to eight antibiotics except for vancomycin and the absence of transferable resistance in the genome of this strain implied that vancomycin resistance is likely to be intrinsic. With regard to phenotypic characteristics, there was no concern of toxicity of this strain. Furthermore, BL utilized various carbohydrates and their conjugates through the activity of various endogenous carbohydrate-utilizing enzymes. Interestingly, the supernatant of the BL showed strong antipathogenic activity against various infectious pathogens. Therefore, we suggest that BL should be a safe probiotic and can be used as a functional ingredient in the food, cosmetic, and pharmaceutical industries.

Graph Representation Learning and Its Applications: A Survey.

Graphs are data structures that effectively represent relational data in the real world. Graph representation learning is a significant task since it could facilitate various downstream tasks, such as node classification, link prediction, etc. Graph representation learning aims to map graph entities to low-dimensional vectors while preserving graph structure and entity relationships. Over the decades, many models have been proposed for graph representation learning. This paper aims to show a comprehensive picture of graph representation learning models, including traditional and state-of-the-art models on various graphs in different geometric spaces. First, we begin with five types of graph embedding models: graph kernels, matrix factorization models, shallow models, deep-learning models, and non-Euclidean models. In addition, we also discuss graph transformer models and Gaussian embedding models. Second, we present practical applications of graph embedding models, from constructing graphs for specific domains to applying models to solve tasks. Finally, we discuss challenges for existing models and future research directions in detail. As a result, this paper provides a structured overview of the diversity of graph embedding models.

Red ginseng dietary fiber promotes probiotic properties of Lactiplantibacillus plantarum and alters bacterial metabolism.

Korean red ginseng has been widely used as an herbal medicine. Red ginseng dietary fiber (RGDF) is a residue of the processed ginseng product but still contains bioactive constituents that can be applied as prebiotics. In this study, we evaluated changes on fermentation profiles and probiotic properties of strains that belong to family Lactobacillaceae with RGDF supplementation. Metabolomic analyses were performed to understand specific mechanisms on the metabolic alteration by RGDF and to discover novel bioactive compounds secreted by the RGDF-supplemented probiotic strain. RGDF supplementation promoted short-chain fatty acid (SCFA) production, carbon source utilization, and gut epithelial adhesion of Lactiplantibacillus plantarum and inhibited attachment of enteropathogens. Intracellular and extracellular metabolome analyses revealed that RGDF induced metabolic alteration, especially associated with central carbon metabolism, and produced RGDF-specific metabolites secreted by L. plantarum, respectively. Specifically, L. plantarum showed decreases in intracellular metabolites of oleic acid, nicotinic acid, uracil, and glyceric acid, while extracellular secretion of several metabolites including oleic acid, 2-hydroxybutanoic acid, hexanol, and butyl acetate increased. RGDF supplementation had distinct effects on L. plantarum metabolism compared with fructooligosaccharide supplementation. These findings present potential applications of RGDF as prebiotics and bioactive compounds produced by RGDF-supplemented L. plantarum as novel postbiotic metabolites for human disease prevention and treatment.

Increased Amino Acid Absorption Mediated by Lacticaseibacillus rhamnosus IDCC 3201 in High-Protein Diet-Fed Mice.

The use of dietary protein products has increased with interests in health promotion, and demand for sports supplements. Among various protein sources, milk protein is one of the most widely employed, given its economic and nutritional advantages. However, recent studies have revealed that milk protein undergoes fecal excretion without complete hydrolysis in the intestines. To increase protein digestibility, heating and drying were implemented; however, these methods reduce protein quality by causing denaturation, aggregation, and chemical modification of amino acids. In the present study, we observed that Lacticaseibacillus rhamnosus IDCC 3201 actively secretes proteases that hydrolyze milk proteins. Furthermore, we showed that co-administration of milk proteins and L. rhamnosus IDCC 3201 increased the digestibility and plasma concentrations of amino acids in a high-protein diet mouse model. Thus, food supplementation of L. rhamnosus IDCC 3201 can be an alternative strategy to increase the digestibility of proteins.

Bifidobacterium lactis IDCC 4301 Exerts Anti-Obesity Effects in High-Fat Diet-Fed Mice Model by Regulating Lipid Metabolism.

SCOPE: Chronic hypernutrition promotes lipid accumulation in the body and excessive lipid accumulation leads to obesity. An increase in the number and size of adipocytes, a characteristic of obesity is closely associated with adipose dysfunction. Recent in vitro and in vivo studies have shown that probiotics may prevent this dysfunction by regulating lipid metabolism. However, the mechanisms of action of probiotics in obesity are not fully understood and their usage for treating obesity remains limited. METHODS AND RESULTS: Bifidobacterium lactis IDCC 4301 is selected for its anti-obesity potential after evaluating inhibitory activity of pancreatic lipase and cholesterol reducing activity. Next, this study investigates the roles of B. lactis IDCC 4301 on lipid metabolism in 3T3-L1 preadipocytes and high-fat diet (HFD)-fed mice. B. lactis IDCC 4301 inhibits cell differentiation and lipid accumulation by suppressing the expression of adipogenic enzymes in 3T3-L1 cells. Moreover, the administration of B. lactis IDCC 4301 decreases body and adipose tissue weight, improves serum lipid levels, and downregulates adipogenic mRNA expression in HFD-fed mice. Additionally, metabolomic analysis suggests that 2-ketobutyrate should be a possible target compound against obesity. CONCLUSIONS: B. lactis IDCC 4301 may be used as an alternative treatment for obesity.

Isolation, Characterization, and Safety Evaluation of the Novel Probiotic Strain Lacticaseibacillus paracasei IDCC 3401 via Genomic and Phenotypic Approaches.

This study aimed to explore the safety and properties of Lacticaseibacillus paracasei IDCC 3401 as a novel probiotic strain via genomic and phenotypic analyses. In whole-genome sequencing, the genes associated with antibiotic resistance and virulence were not detected in this strain. The minimum inhibitory concentration test revealed that L. paracasei IDCC 3401 was susceptible to all the antibiotics tested, except for kanamycin. Furthermore, the strain did not produce toxigenic compounds, such as biogenic amines and D-lactate, nor did it exhibit significant toxicity in a single-dose acute oral toxicity test in rats. Phenotypic characterization of carbohydrate utilization and enzymatic activities indicated that L. paracasei IDCC 3401 can utilize various nutrients, allowing it to grow in deficient conditions and produce health-promoting metabolites. The presence of L. paracasei IDCC 3401 supernatants significantly inhibited the growth of enteric pathogens (p < 0.05). In addition, the adhesion ability of L. paracasei IDCC 3401 to intestinal epithelial cells was found to be as superior as that of Lacticaseibacillus rhamnosus GG. These results suggest that L. paracasei IDCC 3401 is safe for consumption and provides health benefits to the host.

Automated cell-type classification combining dilated convolutional neural networks with label-free acoustic sensing.

This study aimed to automatically classify live cells based on their cell type by analyzing the patterns of backscattered signals of cells with minimal effect on normal cell physiology and activity. Our previous studies have demonstrated that label-free acoustic sensing using high-frequency ultrasound at a high pulse repetition frequency (PRF) can capture and analyze a single object from a heterogeneous sample. However, eliminating possible errors in the manual setting and time-consuming processes when postprocessing integrated backscattering (IB) coefficients of backscattered signals is crucial. In this study, an automated cell-type classification system that combines a label-free acoustic sensing technique with deep learning-empowered artificial intelligence models is proposed. We applied an one-dimensional (1D) convolutional autoencoder to denoise the signals and conducted data augmentation based on Gaussian noise injection to enhance the robustness of the proposed classification system to noise. Subsequently, denoised backscattered signals were classified into specific cell types using convolutional neural network (CNN) models for three types of signal data representations, including 1D CNN models for waveform and frequency spectrum analysis and two-dimensional (2D) CNN models for spectrogram analysis. We evaluated the proposed system by classifying two types of cells (e.g., RBC and PNT1A) and two types of polystyrene microspheres by analyzing their backscattered signal patterns. We attempted to discover cell physical properties reflected on backscattered signals by controlling experimental variables, such as diameter and structure material. We further evaluated the effectiveness of the neural network models and efficacy of data representations by comparing their accuracy with that of baseline methods. Therefore, the proposed system can be used to classify reliably and precisely several cell types with different intrinsic physical properties for personalized cancer medicine development.

Day-Ahead Hourly Solar Irradiance Forecasting Based on Multi-Attributed Spatio-Temporal Graph Convolutional Network.

Solar irradiance forecasting is fundamental and essential for commercializing solar energy generation by overcoming output variability. Accurate forecasting depends on historical solar irradiance data, correlations between various meteorological variables (e.g., wind speed, humidity, and cloudiness), and influences between the weather contexts of spatially adjacent regions. However, existing studies have been limited to spatiotemporal analysis of a few variables, which have clear correlations with solar irradiance (e.g., sunshine duration), and do not attempt to establish atmospheric contextual information from a variety of meteorological variables. Therefore, this study proposes a novel solar irradiance forecasting model that represents atmospheric parameters observed from multiple stations as an attributed dynamic network and analyzes temporal changes in the network by extending existing spatio-temporal graph convolutional network (ST-GCN) models. By comparing the proposed model with existing models, we also investigated the contributions of (i) the spatial adjacency of the stations, (ii) temporal changes in the meteorological variables, and (iii) the variety of variables to the forecasting performance. We evaluated the performance of the proposed and existing models by predicting the hourly solar irradiance at observation stations in the Korean Peninsula. The experimental results showed that the three features are synergistic and have correlations that are difficult to establish using single-aspect analysis.