Search

Abstract Daphnia magna is an important organism in ecotoxicity studies because it is sensitive to toxic substances and easy to culture in laboratory conditions. Its locomotory responses as a biomarker are highlighted in many studies. Over the last several years, multiple high-throughput video tracking systems have been developed to measure the locomotory responses of Daphnia magna. These high-throughput systems, used for high-speed analysis of multiple organisms, are essential for efficiently testing ecotoxicity. However, existing systems are lacking in speed and accuracy. Specifically, speed is affected in the biomarker detection stage. This study aimed to develop a faster and better high-throughput video tracking system using machine learning methods. The video tracking system consisted of a constant temperature module, natural pseudo-light, multi-flow cell, and an imaging camera for recording videos. To measure Daphnia magna movements, we developed a tracking algorithm for automatic background subtraction using k-means clustering, Daphnia classification using machine learning methods (random forest and support vector machine), and tracking each Daphnia magna location using the simple online real-time tracking algorithm. The proposed tracking system with random forest performed the best in terms of identification (ID) precision, ID recall, ID F1 measure, and ID switches, with scores of 79.64%, 80.63%, 78.73%, and 16, respectively. Moreover, it was faster than existing tracking systems such as Lolitrack and Ctrax. We conducted an experiment to observe the impact of toxicants on behavioral responses. Toxicity was measured manually in the laboratory and automatically using the high-throughput video tracking system. The median effective concentration of Potassium dichromate measured in the laboratory and using the device was 1.519 and 1.414, respectively. Both measurements conformed to the guideline provided by the Environmental Protection Agency of the United States; therefore, our method can be used for water quality monitoring. Finally, we observed Daphnia magna behavioral responses in different concentrations after 0, 12, 18, and 24 h and found that there was a difference in movement according to the concentration at all hours.

Amaranth is a nutritionally valuable crop, as it contains phenolic acids and flavonoids, yielding diverse plant secondary metabolites (PSMs) like phytosterol, tocopherols, and carotenoids. This study explored the variations in the contents of seventeen polyphenolic compounds within the leaves of one hundred twenty Amaranthus accessions representing nine Amaranthus species. The investigation entailed the analysis of phenolic content across nine Amaranthus species, specifically A. hypochondriacus, A. cruentus, A. caudatus, A. tricolor, A. dubius, A. blitum, A. crispus, A. hybridus, and A. viridis, utilizing ultra performance liquid chromatography with photodiode array detection (UPLC-PDA). The results revealed significant differences in polyphenolic compounds among accessions in which rutin content was predominant in all Amaranthus species in both 2018 and 2019. Among the nine Amaranthus species, the rutin content ranged from 95.72 ± 199.17 μg g−1 (A. dubius) to 1485.09 ± 679.51 μg g−1 (A. viridis) in 2018 and from 821.59 ± 709.95 μg g−1 (A. tricolor) to 3166.52 ± 1317.38 μg g−1 (A. hypochondriacus) in 2019. Correlation analysis revealed, significant positive correlations between rutin and kaempferol-3-O-β-rutinoside (r = 0.93), benzoic acid and ferulic acid (r = 0.76), and benzoic acid and kaempferol-3-O-β-rutinoside (r = 0.76), whereas gallic acid showed consistently negative correlations with each of the 16 phenolic compounds. Wide variations were identified among accessions and between plants grown in the two years. The nine species and one hundred twenty Amaranthus accessions were clustered into six groups based on their seventeen phenolic compounds in each year. These findings contribute to expanding our understanding of the phytochemical traits of accessions within nine Amaranthus species, which serve as valuable resources for Amaranthus component breeding and functional material development.

Many researchers have used sound sensors to record audio data from insects, and used these data as inputs of machine learning algorithms to classify insect species. In image classification, the convolutional neural network (CNN), a well-known deep learning algorithm, achieves better performance than any other machine learning algorithm. This performance is affected by the characteristics of the convolution filter (ConvFilter) learned inside the network. Furthermore, CNN performs well in sound classification. Unlike image classification, however, there is little research on suitable ConvFilters for sound classification. Therefore, we compare the performances of three convolution filters, 1D-ConvFilter, 3×1 2D-ConvFilter, and 3×3 2D-ConvFilter, in two different network configurations, when classifying mosquitoes using audio data. In insect sound classification, most machine learning researchers use only audio data as input. However, a classification model, which combines other information such as activity circadian rhythm, should intuitively yield improved classification results. To utilize such relevant additional information, we propose a method that defines this information as a priori probabilities and combines them with CNN outputs. Of the networks, VGG13 with 3×3 2D-ConvFilter showed the best performance in classifying mosquito species, with an accuracy of 80.8%. Moreover, adding activity circadian rhythm information to the networks showed an average performance improvement of 5.5%. The VGG13 network with 1D-ConvFilter achieved the highest accuracy of 85.7% with the additional activity circadian rhythm information.

The economic burden of Type 2 Diabetes (T2D) on society has increased over time. Early prediction of diabetes and prediabetes can reduce treatment cost and improve intervention. The development of (pre)diabetes is associated with various health conditions that can be monitored by routine health checkups. This study aimed to develop amachine learning-based model for predicting (pre)diabetes. Our frameworks were based on 22,722 patient samples collected from 2013 to 2020 in ageneral hospital in Korea. The disease progression was divided into three categories based on fasting blood glucose: normal, prediabetes, and T2D. The risk factors at each stage were identified and compared. Based on the area under the curve, the support vector machine appeared to have optimal performance. At the normal and prediabetes stages, fasting blood glucose and HbA1c are prevalent risk features for the suggested models. Interestingly, HbA1c had the highest odds ratio among the features even in the normal stage (FBG is less than 100). In addition, factors related to liver function, such as gamma-glutamyl transpeptidase can be used to predict progression from normal to prediabetes, while factors related to renal function, such as blood urea nitrogen and creatinine, are prediction factors of T2D development.

Rice paddies are dynamic areas for microbe-mediated nitrogen cycling and this could be driven by the long-term alteration of paddy soil edaphic factors. The objective of this study is to evaluate the lasting impact of long-term compost fertilization on the soil chemical properties of paddy fields, determining the size of the microbial guilds involved in nitrification and denitrification. Soil sampling was done on paddy fields without fertilizer, with NPK + compost, and with compost application, and the soil chemical properties of the fields were determined from 2018 to 2021. The abundance of genes related to nitrogen cycling was measured using quantitative PCR (qPCR). Annual analyses showed that the studied soils have attained stable, baseline chemical properties with significantly increased phosphorus (P2O5), potassium (K), SOM, and total nitrogen (TN) due to decades of fertilization with NPK + compost and compost. Consequently, the genes related to bacterial amoA, nosZI, and nosZII were significantly increased in Com- and NPKCom-amended soils compared to the NF paddy field. The nirK gene abundance was unaffected after long-term amendment with compost. A positive correlation was found between the archaeal amoA gene abundance and DOC, while SOM and TN were consistently positively correlated with the abundances of bacterial amoA, nosZI, and nosZII genes, in addition to interactions with potassium and DOC. Principal component analysis (PCA) indicated soil variabilities across treatments, where the unfertilized paddy field contained lower SOM and nutrient contents with a characteristic nirK gene abundance. Similar variabilities in terms of the SOM, TN, K, nosZI, and nosZII gene abundances were observed in the Com and NPKCom paddy fields. Long-term amendment with NPK + compost and compost created soil paddy fields with stable soil chemical properties with higher SOM and nutrient contents, which established higher abundances of genes associated with denitrification and nitrification that were observed during the fallow period.

Odor is a very serious problem worldwide. Thus, odor prediction research has been conducted consistently to help prevent odor. Odor substances that are complex odors are known, but complex odors and odor substances do not have a linear dependence. In addition, depending on the combination of odor substances, the causal relationships, such as synergy and antagonism, are different for complex odors. Research is needed to know this, but the situation is incomplete. Therefore, in this study, research was conducted through data-based research. The complex odor was predicted using various machine learning methods, and the effect of odor substances on the complex odor was verified using an explainable artificial intelligence method. In this study, according to the Malodor Prevention Act in Korea, complex odors are divided into two categories: acceptable and unacceptable. Analysis of variance and correlation analysis were used to determine the relationships between variables. Six machine learning methods (k-nearest neighbor, support vector classification, random forest, extremely randomized tree, eXtreme gradient boosting, and light gradient boosting machine) were used as predictive classification models, and the best predictive method was chosen using various evaluation metrics. As a result, the support vector machine that performed best in five out of six evaluation metrics was selected as the best model (f1-score = 0.7722, accuracy = 0.8101, sensitivity = 0.7372, specificity = 0.8656, positive predictive value = 0.8196, and negative predictive value = 0.8049). In addition, the partial dependence plot method from explainable artificial intelligence was used to understand the influence and interaction effects of odor substances.

Abstract Diverse artificial synapse structures and materials are widely proposed for neuromorphic hardware systems beyond von Neumann architecture owing to their capability to mimic complex information processing tasks such as image recognition, natural language processing, and learning. Nevertheless, temporal and spatial randomness in the movement of ion and electron particles that exist in materials usually prevents the solid‐state‐based synaptic devices from enabling the reliable modulation of synaptic plasticity. An aluminum nanoparticle (Al NP)‐embedded indium gallium zinc oxide (IGZO) synaptic transistor whose spike peak level and conductance change can be precisely modulated by the density of Al NPs within the IGZO channel is demonstrated. Essential synaptic functions including excitatory or inhibitory postsynaptic current, paired pulse facilitation, and short‐term potentiation or depression are also thoroughly emulated in the synaptic transistor device with the most optimized Al NP density: IGZO:Al NPs (6 nm). Moreover, controllable switching from short‐term to long‐term memory regimes essential for a learning task is demonstrated. Simulation results prove that this transistor can provide a decent recognition accuracy for neuromorphic computing. Indeed, the integrated IGZO:Al NP synaptic circuit with the effective synaptic plasticity will facilitate the implementation of a reconfigurable neuromorphic computing system.

Maintaining rice yield, soil function, and fertility are essential components of long-term compost fertilization. However, paddy fields are major sources of anthropogenic methane emissions. The aim of the study is to evaluate the changes in soil chemical properties and their concurrent impact on the abundance of methanogenesis (mcrA) and methane oxidation (pmoA) related genes among compost (Com), NPK+Compost (NPKCom), and unfertilized (NF) fallow paddy fields under long-term compost fertilization. Results showed that compost and NPK+Compost fertilization altered the soil chemical properties of paddy fields with a significant increase in the functional gene abundance potentially associated with Methanobacteriaceae for mcrA (1.23 × 106 to 3.84 × 106 copy number g−1 dry soil) and methane oxidizing bacteria such as Methylomonas and Methylobacter for pmoA (1.65 × 106 to 4.3 × 106 copy number g−1 dry soil). Ordination plots visualized these changes, where treatments clustered distinctly indicating that Com and NPKCom treatments were characterized by paddy soils with elevated OM, TN, K and P content and higher abundances of methanogenesis and methane oxidation related genes. The study showed that long-term compost fertilization resulted in paddy fields with high nutrient content and high gene abundance, attributed to methanogens and methane oxidizing bacteria that responded well with compost fertilization. These results indicated the potential of these fallow paddy fields for methane emission and methane oxidation and that they are ‘primed’, potentially influencing subsequent paddy field responses to long-term compost application.

The aim of this study is to ascertain the most suitable model for predicting complex odors using odor substance data that has a small number of data and a large number of missing data. First, we compared the data removal and imputation methods, and the method of imputing missing data was found to be more effective. Then, in order to recommend a suitable model, we created a total of 126 models (missing imputation: single imputation, multiple imputations, K-nearest neighbor imputation; data preprocessing: standardization, principal component analysis, partial least square; and predictive method: multiple regression, machine learning, deep learning) and compared them using R2 and mean absolute error (MAE) values. Finally, we investigated variable importance using the best prediction model. The results identified the best model as a combination of multivariate imputation using Bayesian ridge as the missing imputation method, standardization for data preprocessing, and an extremely randomized tree as the predictive method. Among the odor compounds, Methyl mercaptan, acetic acid, and dimethyl sulfide were identified as the most important odor compounds in predicting complex odors.

Hydraulic systems are advanced in function and level as they are used in various industrial fields. Furthermore, condition monitoring using internet of things (IoT) sensors is applied for system maintenance and management. In this study, meaningful features were identified through extraction and selection of various features, and classification evaluation metrics were presented through machine learning and deep learning to expand the diagnosis of abnormalities and defects in each component of the hydraulic system. Data collected from IoT sensor data in the time domain were divided into clusters in predefined sections. The shape and density characteristics were extracted by cluster. Among 2335 newly extracted features, related features were selected using correlation coefficients and the Boruta algorithm for each hydraulic component and used for model learning. Linear discriminant analysis (LDA), logistic regression, support vector classifier (SVC), decision tree, random forest, XGBoost, LightGBM, and multi-layer perceptron were used to calculate the true positive rate (TPR) and true negative rate (TNR) for each hydraulic component to detect normal and abnormal conditions. Valve condition, internal pump leakage, and hydraulic accumulator data showed TPR performance of 0.94 or more and a TNR performance of 0.84 or more. This study’s findings can help to determine the stable and unstable states of each component of the hydraulic system and form the basis for engineers’ judgment.

Artificial intelligence (AI) is being implemented in many areas of medicine, such as patient-customized diagnosis. Growth in the artificial intelligence medical device (AIMD) field is expected in the coming years. Major countries are currently establishing systems and policies to gain a leading position in the medical artificial intelligence market. The Republic of Korea has initiated the Act on Nurturing the Medical Devices Industry and Supporting Innovative Medical Devices for the development of AIMDs and is implementing it preemptively. As a result, the country has achieved an effective strategy for coping with the COVID-19 pandemic, an increase in the number of AIMD approvals (85 approved as of September 2021), and the creation of a document pertaining to internationally harmonized guidelines on AIMD-related terms and definitions. However, in order to develop and activate more AIMD products, it is necessary to improve post-market management such as product change and quality control in addition to approval. Here, we review the current regulatory status of AIMD in the Republic of Korea and what needs to be improved for AIMD to be more developed and activated.

Railway accidents are critical issues characterized by a large number of injuries and fatalities per accident due to massive public transport systems. This study proposes a new approach for evaluating the damages resulting from railway accidents using the two-part models (TPMs) such as the zero-inflated Poisson regression model (ZIP model) and the zero-inflated negative-binomial regression model (ZINB model) for the non-negative count measurements and the zero-inflated gamma regression model (ZIG model) and the zero-inflated log-normal regression model (ZILN model) for the semi-continuous measurements. The models are employed for the evaluation of the railway accidents on Korea Railroad, considering the accident damages, such as the train delay time, the number of trains delayed and the cost of considering the accident count responses, for the period 2008 to 2016. From the results obtained, we found that the human-related factors, the high-speed railway system or the Korea Train Express (KTX) and the number of casualties, are the main cost-escalating factors. The number of trains delayed and the amount of delay time tend to increase both the probability of incurring costs and the amount of cost. For better evaluation, the railway accident data should contain accurate information with less recurrence of zeros.

This study aims to compare the classification performance of statistical models on highly imbalanced kidney data. The health examination cohort database provided by the National Health Insurance Service in Korea is utilized to build models with various machine learning methods. The glomerular filtration rate (GFR) is used to diagnose chronic kidney disease (CKD). It is calculated using the Modification of Diet in Renal Disease method and classified into five stages (1, 2, 3A and 3B, 4, and 5). Different CKD stages based on the estimated GFR are considered as six classes of the response variable. This study utilizes two representative generalized linear models for classification, namely, multinomial logistic regression (multinomial LR) and ordinal logistic regression (ordinal LR), as well as two machine learning models, namely, random forest (RF) and autoencoder (AE). The classification performance of the four models is compared in terms of accuracy, sensitivity, specificity, precision, and F1-Measure. To find the best model that classifies CKD stages correctly, the data are divided into a 10-fold dataset with the same rate for each CKD stage. Results indicate that RF and AE show better performance in accuracy than the multinomial and ordinal LR models when classifying the response variable. However, when a highly imbalanced dataset is modeled, the accuracy of the model performance can distort the actual performance. This occurs because accuracy is high even if a statistical model classifies a minority class into a majority class. To solve this problem in performance interpretation, we not only consider accuracy from the confusion matrix but also sensitivity, specificity, precision, and F-1 measure for each class. To present classification performance with a single value for each model, we calculate the macro-average and micro-weighted values for each model. We conclude that AE is the best model classifying CKD stages correctly for all performance indices.

The use of deep-learning-based artificial intelligence (AI) is emerging in ophthalmology, with AI-mediated differential diagnosis of neovascular age-related macular degeneration (AMD) and dry AMD a promising methodology for precise treatment strategies and prognosis. Here, we developed deep learning algorithms and predicted diseases using 399 images of fundus. Based on feature extraction and classification with fully connected layers, we applied the Visual Geometry Group with 16 layers (VGG16) model of convolutional neural networks to classify new images. Image-data augmentation in our model was performed using Keras ImageDataGenerator, and the leave-one-out procedure was used for model cross-validation. The prediction and validation results obtained using the AI AMD diagnosis model showed relevant performance and suitability as well as better diagnostic accuracy than manual review by first-year residents. These results suggest the efficacy of this tool for early differential diagnosis of AMD in situations involving shortages of ophthalmology specialists and other medical devices.

Hard shoulder running (HSR) has been increasingly used as a sustainable and viable way to increase road capacity. This study investigated the safety effect of HSR on freeways in South Korea using the empirical Bayes method. This study found an increase in the total number of crashes. In terms of crash severity, a higher proportion of crashes (25.3%) on 2(3)-lane sections were found to be serious (involving injuries and/or fatalities) compared to those on 4(5)-lane sections (3.6%). Also, a positive relationship was found between the length of the hard shoulder running and changes in crash frequencies. Thus, hard shoulder running on lengthy 2(3)-lane freeways should be avoided.

Identifying algae in water is important for managing algal blooms which have great impact on drinking water supply systems. There have been various microscopic approaches developed for algae classification. Many of them are based on the morphological features of algae. However, there have seldom been mathematical frameworks for comparing the shape of algae, represented as a planar continuous curve obtained from an image. In this work, we describe a recent framework for computing shape distance between two different algae based on the elastic metric and a novel functional representation called the square root velocity function (SRVF). We further introduce statistical procedures for multiple shapes of algae including computing the sample mean, the sample covariance, and performing the principal component analysis (PCA). Based on the shape distance, we classify six algal species in watersheds experiencing algal blooms, including three cyanobacteria (Microcystis, Oscillatoria, and Anabaena), two diatoms (Fragilaria and Synedra), and one green algae (Pediastrum). We provide and compare the classification performance of various distance-based and model-based methods. We additionally compare elastic shape distance to non-elastic distance using the nearest neighbor classifiers. [ABSTRACT FROM AUTHOR]

The effects of hydrodynamics and alum dose on particle growth were investigated by monitoring particle counts in a rapid mixing process. Experiments were performed to measure the particle growth and breakup under various conditions. The rapid mixing scheme consisted of the following operating parameters: Velocity gradient (G) (200-300 s-1), alum dose (10-50 mg/L) and mixing time (30-180 s). The Poisson regression model was applied to assess the effects of the doses and velocity gradient with mixing time. The mechanism for the growth and breakup of particles was elucidated. An increase in alum dose was found to accelerate the particle count reduction. The particle count at a G value of 200 s-1 decreased more rapidly than those at 300 s-1. The growth and breakup of larger particles were more clearly observed at higher alum doses. Variations of particles due to aggregation and breakup of micro-flocs in rapid mixing step were interactively affected by G, mixing time and alum dose. Micro-flocculation played an important role in a rapid mixing process. [ABSTRACT FROM AUTHOR]

Copulas are useful devices to explain the dependence structure among variables by eliminating the influence of marginals. In this paper, we propose a new class of bivariate copulas to quantify dependency and incorporate it into various iterated copula families. We investigate properties of the new class of bivariate copulas and derive the measure of association, such as Spearman's ρ, Kendall's τ, and the regression function for the new class. We also provide the concept of directional dependence in bivariate regression setting by using copulas. [ABSTRACT FROM AUTHOR]

Atmospheric Dispersion Models (ADMs) are routinely used in environmental impact assessment, risk analysis, and source apportionment studies. There are a variety of such computational ADMs, but these models usually only provide deterministic predictions or estimation of uncertainty. By introducing error components in ADMs, we formulate statistical modelling to obtain more precise prediction. These error components are based on the default neighbourhood structures created by the point source and already recognised by ADMs. Application is made to a real dataset. Posterior inference and model choice are assessed via Markov Chain Monte Carlo techniques, deviance information criterion, and mean squared predicted error. [ABSTRACT FROM AUTHOR]