Hasil untuk "Plant culture"

J. Lund, G. E. Fogg

Dejan Grba

While generative artificial intelligence (generative AI) is being examined extensively, some issues it epitomizes call for more refined scrutiny and deeper contextualization. Besides the lack of nuanced understanding of art's continuously changing character in discussions about generative AI's cultural impact, one of the notably underexplored aspects is the conceptual and ideological substrate of AI science and industry whose attributes generative AI propagates by fostering the integration of diverse modes of AI-powered artmaking into the mainstream culture and economy. Taking the current turmoil around the generative AI as a pretext, this paper summarizes a broader study of AI's influence on art notions focusing on the confluence of certain foundational concepts in computer science and ideological vectors of the AI industry that transfer into art, culture, and society. This influence merges diverse and sometimes inconsistent but somehow coalescing philosophical premises, technical ideas, and political views, many of which have unfavorable overtones.

Chen-Quan Gu, Chen-Quan Gu, Chen-Quan Gu et al.

Malus sieversii, a Tertiary relict and primary progenitor of the cultivated apple, is experiencing severe habitat degradation in China’s Tianshan Mountains. To understand how soil ecosystem functions respond to tree vigor decline, we monitored surface soils beneath the canopy of wild apple trees monthly from April to October. Trees were classified into three vigor classes based on the percentage of dead branches: Vigor Class I (<20%), Vigor Class II (40–60%), and Vigor Class III (>80%). Soil multifunctionality (SMF) and temporal variability of nutrients (TVN) were derived from seven key nutrient indicators. Soils under Vigor Class II trees exhibited the lowest SMF and highest TVN, indicating maximal functional instability during intermediate degradation. While SMF peaked and TVN reached its seasonal minimum in October, Vigor Class II showed a consistent decline in TVN over time, unlike the irregular fluctuations in Vigor Classes I and III. A significant negative SMF–TVN correlation in Vigor Classes II and III suggests a trade-off between functionality and stability. Partial least squares path modeling revealed that soil organic carbon, total nitrogen, and total phosphorus were the dominant direct driver of both SMF and TVN, with climate exerting no significant direct effects once tree vigor and soil conditions were accounted for. These results suggest that Vigor Class II represents a critical early-warning stage: soil functional capacity begins to deteriorate before visible signs of severe tree decline or mortality. Targeted ecological restoration of Vigor Class II trees is essential to prevent irreversible ecosystem degradation. Therefore, while continued protection of healthy Vigor Class I trees remains essential, conservation efforts should place greater emphasis on restoring Vigor Class II trees to disrupt degradation feedbacks before irreversible ecosystem decline occurs.

Mina Zolfaghari, Abbas Yadegar, Atefe Rezaei et al.

In the present research, zinc oxide (ZnO) nanoparticles (NPs) were biosynthesized through reduction by Anvillea garcinii leaf extract. A. garcinii leaves contain bioactive sesquiterpenes, terpenoids, and phenolic compounds, which are likely responsible for the reduction and stabilization of ZnO NPs. Compared to conventional physicochemical approaches, this synthesis method has several advantages, including simplicity, low cost, sustainability, and replicability. In this study, the impacts of various calcination (annealing) temperatures (60 °C and 500 °C) and different pHs (8, 10, and 12) on the properties of green-synthesized ZnO NPs were evaluated. Characterization was performed by analytical instruments including UV-Vis spectroscopy, Fourier transform infrared (FT-IR) spectroscopy and X-ray diffraction (XRD) analyses, nanoparticle analyzer, and field emission scanning electron microscope (FE-SEM). The UV–Vis adsorption spectra of the ZnO NPs revealed a prominent peak at approximately 230 nm. The observed peaks in FTIR spectra align well with those reported in various studies on ZnO NPs. By microscopic observation and XRD validation, the spherical and hexagonal nature of ZnO NPs was confirmed. The pH and temperature used were effective on the particle size, so that the smallest NPs (16.4 nm) were obtained with the help of the most alkaline synthesis medium (pH 12) and oven drying (60 °C). While the largest dimension (63 nm) corresponded to the NPs synthesized under the lowest pH (8) and dried with a 500 °C furnace. Synthesized NPs exhibited high antioxidant properties. The small sizes of biosynthesized ZnO NPs and their phytochemical-coated surfaces affected their biological activity. The cytotoxic impact of NPs on the gastric cancer cells was dose-dependent, and IC50 values for ZnO prepared at 60 and 500 °C (coded as ZnO-60 and ZnO-500) were 35.11 and 42.7 μg/mL respectively. In addition, they were potent antimicrobial agents against Gram-negative bacteria Escherichia coli and 3 strains of Helicobacter pylori, and Gram-positive bacterium Staphylococcus aureus. The green synthesis of ZnO NPs represents a sustainable approach that minimizes environmental impact while producing effective nanomaterials. By using natural plant extracts, researchers can develop cost-effective and eco-friendly methods for NP production, enhancing their potential applications across diverse sectors such as medical fields, environmental science, and materials engineering.

Rida Qadri, Aida M. Davani, Kevin Robinson et al.

Large language models are increasingly being integrated into applications that shape the production and discovery of societal knowledge such as search, online education, and travel planning. As a result, language models will shape how people learn about, perceive and interact with global cultures making it important to consider whose knowledge systems and perspectives are represented in models. Recognizing this importance, increasingly work in Machine Learning and NLP has focused on evaluating gaps in global cultural representational distribution within outputs. However, more work is needed on developing benchmarks for cross-cultural impacts of language models that stem from a nuanced sociologically-aware conceptualization of cultural impact or harm. We join this line of work arguing for the need of metricizable evaluations of language technologies that interrogate and account for historical power inequities and differential impacts of representation on global cultures, particularly for cultures already under-represented in the digital corpora. We look at two concepts of erasure: omission: where cultures are not represented at all and simplification i.e. when cultural complexity is erased by presenting one-dimensional views of a rich culture. The former focuses on whether something is represented, and the latter on how it is represented. We focus our analysis on two task contexts with the potential to influence global cultural production. First, we probe representations that a language model produces about different places around the world when asked to describe these contexts. Second, we analyze the cultures represented in the travel recommendations produced by a set of language model applications. Our study shows ways in which the NLP community and application developers can begin to operationalize complex socio-cultural considerations into standard evaluations and benchmarks.

Herve Goeau, Pierre Bonnet, Alexis Joly

Automated plant identification has improved considerably thanks to recent advances in deep learning and the availability of training data with more and more field photos. However, this profusion of data concerns only a few tens of thousands of species, mainly located in North America and Western Europe, much less in the richest regions in terms of biodiversity such as tropical countries. On the other hand, for several centuries, botanists have systematically collected, catalogued and stored plant specimens in herbaria, especially in tropical regions, and recent efforts by the biodiversity informatics community have made it possible to put millions of digitised records online. The LifeCLEF 2021 plant identification challenge (or "PlantCLEF 2021") was designed to assess the extent to which automated identification of flora in data-poor regions can be improved by using herbarium collections. It is based on a dataset of about 1,000 species mainly focused on the Guiana Shield of South America, a region known to have one of the highest plant diversities in the world. The challenge was evaluated as a cross-domain classification task where the training set consisted of several hundred thousand herbarium sheets and a few thousand photos to allow learning a correspondence between the two domains. In addition to the usual metadata (location, date, author, taxonomy), the training data also includes the values of 5 morphological and functional traits for each species. The test set consisted exclusively of photos taken in the field. This article presents the resources and evaluations of the assessment carried out, summarises the approaches and systems used by the participating research groups and provides an analysis of the main results.

Deepjyoti Chetia, Sanjib Kr Kalita, Prof Partha Pratim Baruah et al.

Medicinal plants have been a key component in producing traditional and modern medicines, especially in the field of Ayurveda, an ancient Indian medical system. Producing these medicines and collecting and extracting the right plant is a crucial step due to the visually similar nature of some plants. The extraction of these plants from nonmedicinal plants requires human expert intervention. To solve the issue of accurate plant identification and reduce the need for a human expert in the collection process; employing computer vision methods will be efficient and beneficial. In this paper, we have proposed a model that solves such issues. The proposed model is a custom convolutional neural network (CNN) architecture with 6 convolution layers, max-pooling layers, and dense layers. The model was tested on three different datasets named Indian Medicinal Leaves Image Dataset,MED117 Medicinal Plant Leaf Dataset, and the self-curated dataset by the authors. The proposed model achieved respective accuracies of 99.5%, 98.4%, and 99.7% using various optimizers including Adam, RMSprop, and SGD with momentum.

Hanna Herasimchyk, Robin Labryga, Tomislav Prusina

We present a multi-head vision transformer approach for multi-label plant species prediction in vegetation plot images, addressing the PlantCLEF 2025 challenge. The task involves training models on single-species plant images while testing on multi-species quadrat images, creating a drastic domain shift. Our methodology leverages a pre-trained DINOv2 Vision Transformer Base (ViT-B/14) backbone with multiple classification heads for species, genus, and family prediction, utilizing taxonomic hierarchies. Key contributions include multi-scale tiling to capture plants at different scales, dynamic threshold optimization based on mean prediction length, and ensemble strategies through bagging and Hydra model architectures. The approach incorporates various inference techniques including image cropping to remove non-plant artifacts, top-n filtering for prediction constraints, and logit thresholding strategies. Experiments were conducted on approximately 1.4 million training images covering 7,806 plant species. Results demonstrate strong performance, making our submission 3rd best on the private leaderboard. Our code is available at https://github.com/geranium12/plant-clef-2025/tree/v1.0.0.

Burak Satar, Zhixin Ma, Patrick A. Irawan et al.

Multimodal vision-language models (VLMs) have made substantial progress in various tasks that require a combined understanding of visual and textual content, particularly in cultural understanding tasks, with the emergence of new cultural datasets. However, these datasets frequently fall short of providing cultural reasoning while underrepresenting many cultures. In this paper, we introduce the Seeing Culture Benchmark (SCB), focusing on cultural reasoning with a novel approach that requires VLMs to reason on culturally rich images in two stages: i) selecting the correct visual option with multiple-choice visual question answering (VQA), and ii) segmenting the relevant cultural artifact as evidence of reasoning. Visual options in the first stage are systematically organized into three types: those originating from the same country, those from different countries, or a mixed group. Notably, all options are derived from a singular category for each type. Progression to the second stage occurs only after a correct visual option is chosen. The SCB benchmark comprises 1,065 images that capture 138 cultural artifacts across five categories from seven Southeast Asia countries, whose diverse cultures are often overlooked, accompanied by 3,178 questions, of which 1,093 are unique and meticulously curated by human annotators. Our evaluation of various VLMs reveals the complexities involved in cross-modal cultural reasoning and highlights the disparity between visual reasoning and spatial grounding in culturally nuanced scenarios. The SCB serves as a crucial benchmark for identifying these shortcomings, thereby guiding future developments in the field of cultural reasoning. https://github.com/buraksatar/SeeingCulture

Jona Cappelle, Jarne Van Mulders, Sarah Goossens et al.

Precision agriculture demands non-invasive, energy-efficient, and sustainable plant monitoring solutions. In this work, we present the design and implementation of a lightweight, batteryless plant movement sensor powered solely by RF energy. This sensor targets Controlled Environment Agriculture (CEA) and utilizes inertial measurements units (IMUs) to monitor leaf motion, which correlates with plant physiological responses to environmental stress. By eliminating the battery, we reduce the ecological footprint, weight, and maintenance requirements, transitioning from lifetime-based to operation-based energy storage. Our design minimizes circuit complexity while enabling flexible, adaptive readout scheduling based on energy availability and sensor data. We detail the energy requirements, RF power transfer considerations, integration constraints, and outline future directions, including multi-antenna power delivery and networked sensor synchronization.

Fakhraddin Alwajih, Abdellah El Mekki, Hamdy Mubarak et al.

Large Language Models (LLMs) inherently reflect the vast data distributions they encounter during their pre-training phase. As this data is predominantly sourced from the web, there is a high chance it will be skewed towards high-resourced languages and cultures, such as those of the West. Consequently, LLMs often exhibit a diminished understanding of certain communities, a gap that is particularly evident in their knowledge of Arabic and Islamic cultures. This issue becomes even more pronounced with increasingly under-represented topics. To address this critical challenge, we introduce PalmX 2025, the first shared task designed to benchmark the cultural competence of LLMs in these specific domains. The task is composed of two subtasks featuring multiple-choice questions (MCQs) in Modern Standard Arabic (MSA): General Arabic Culture and General Islamic Culture. These subtasks cover a wide range of topics, including traditions, food, history, religious practices, and language expressions from across 22 Arab countries. The initiative drew considerable interest, with 26 teams registering for Subtask 1 and 19 for Subtask 2, culminating in nine and six valid submissions, respectively. Our findings reveal that task-specific fine-tuning substantially boosts performance over baseline models. The top-performing systems achieved an accuracy of 72.15% on cultural questions and 84.22% on Islamic knowledge. Parameter-efficient fine-tuning emerged as the predominant and most effective approach among participants, while the utility of data augmentation was found to be domain-dependent.

Sławomir Dadas, Małgorzata Grębowiec, Michał Perełkiewicz et al.

Large language models (LLMs) are becoming increasingly proficient in processing and generating multilingual texts, which allows them to address real-world problems more effectively. However, language understanding is a far more complex issue that goes beyond simple text analysis. It requires familiarity with cultural context, including references to everyday life, historical events, traditions, folklore, literature, and pop culture. A lack of such knowledge can lead to misinterpretations and subtle, hard-to-detect errors. To examine language models' knowledge of the Polish cultural context, we introduce the Polish linguistic and cultural competency benchmark, consisting of 600 manually crafted questions. The benchmark is divided into six categories: history, geography, culture & tradition, art & entertainment, grammar, and vocabulary. As part of our study, we conduct an extensive evaluation involving over 30 open-weight and commercial LLMs. Our experiments provide a new perspective on Polish competencies in language models, moving past traditional natural language processing tasks and general knowledge assessment.

Viacheslav Vasilev, Julia Agafonova, Nikolai Gerasimenko et al.

Text-to-image generation models have gained popularity among users around the world. However, many of these models exhibit a strong bias toward English-speaking cultures, ignoring or misrepresenting the unique characteristics of other language groups, countries, and nationalities. The lack of cultural awareness can reduce the generation quality and lead to undesirable consequences such as unintentional insult, and the spread of prejudice. In contrast to the field of natural language processing, cultural awareness in computer vision has not been explored as extensively. In this paper, we strive to reduce this gap. We propose a RusCode benchmark for evaluating the quality of text-to-image generation containing elements of the Russian cultural code. To do this, we form a list of 19 categories that best represent the features of Russian visual culture. Our final dataset consists of 1250 text prompts in Russian and their translations into English. The prompts cover a wide range of topics, including complex concepts from art, popular culture, folk traditions, famous people's names, natural objects, scientific achievements, etc. We present the results of a human evaluation of the side-by-side comparison of Russian visual concepts representations using popular generative models.

Yiqing Guo, Karel Mokany, Shaun R. Levick et al.

Earth observation data have shown promise in predicting species richness of vascular plants ($α$-diversity), but extending this approach to large spatial scales is challenging because geographically distant regions may exhibit different compositions of plant species ($β$-diversity), resulting in a location-dependent relationship between richness and spectral measurements. In order to handle such geolocation dependency, we propose \textit{Spatioformer}, where a novel geolocation encoder is coupled with the transformer model to encode geolocation context into remote sensing imagery. The Spatioformer model compares favourably to state-of-the-art models in richness predictions on a large-scale ground-truth richness dataset (HAVPlot) that consists of 68,170 in-situ richness samples covering diverse landscapes across Australia. The results demonstrate that geolocational information is advantageous in predicting species richness from satellite observations over large spatial scales. With Spatioformer, plant species richness maps over Australia are compiled from Landsat archive for the years from 2015 to 2023. The richness maps produced in this study reveal the spatiotemporal dynamics of plant species richness in Australia, providing supporting evidence to inform effective planning and policy development for plant diversity conservation. Regions of high richness prediction uncertainties are identified, highlighting the need for future in-situ surveys to be conducted in these areas to enhance the prediction accuracy.

Samhita Marri, Arun N. Sivakumar, Naveen K. Uppalapati et al.

Tracking plant features is crucial for various agricultural tasks like phenotyping, pruning, or harvesting, but the unstructured, cluttered, and deformable nature of plant environments makes it a challenging task. In this context, the recent advancements in foundational models show promise in addressing this challenge. In our work, we propose PlantTrack where we utilize DINOv2 which provides high-dimensional features, and train a keypoint heatmap predictor network to identify the locations of semantic features such as fruits and leaves which are then used as prompts for point tracking across video frames using TAPIR. We show that with as few as 20 synthetic images for training the keypoint predictor, we achieve zero-shot Sim2Real transfer, enabling effective tracking of plant features in real environments.

Ruo-Yu Li, Chang-Hwa Wang

The use of smart devices as media for digital learning constitutes a new-generation digital learning paradigm. Therefore, context-aware game-based learning has attracted considerable attention. Location-based games have not only positive effects on learning but also pronounced effects on culture and history. Accordingly, focusing on railway cultural heritages, we attempted to assess interdependent relationships between key factors crucial for the design of a location-based mobile game for cultural heritages. We adopted the analytic network process (ANP) for our assessment. We initially performed a literature review to generalize relevant criteria and elements and developed a questionnaire based on the fuzzy delphi method (FDM); thus, key factors, namely 3 criteria and 15 elements, were selected. We also applied an online ANP-based questionnaire; on the basis of the experts opinions, we established a network model and determined the priority order of the key factors. The results revealed that experts considered culture learning to be of the highest importance, with the most important three elements being prior knowledge, challenge levels, and cultural narrative. In addition, culture learning exhibited a strong interaction with content design. In each criterion, one element had a considerable influence on the remaining elements, as determined by an analysis of matrices.

Jianping Yao, Son N. Tran, Saurabh Garg et al.

Deep learning plays an important role in modern agriculture, especially in plant pathology using leaf images where convolutional neural networks (CNN) are attracting a lot of attention. While numerous reviews have explored the applications of deep learning within this research domain, there remains a notable absence of an empirical study to offer insightful comparisons due to the employment of varied datasets in the evaluation. Furthermore, a majority of these approaches tend to address the problem as a singular prediction task, overlooking the multifaceted nature of predicting various aspects of plant species and disease types. Lastly, there is an evident need for a more profound consideration of the semantic relationships that underlie plant species and disease types. In this paper, we start our study by surveying current deep learning approaches for plant identification and disease classification. We categorise the approaches into multi-model, multi-label, multi-output, and multi-task, in which different backbone CNNs can be employed. Furthermore, based on the survey of existing approaches in plant pathology and the study of available approaches in machine learning, we propose a new model named Generalised Stacking Multi-output CNN (GSMo-CNN). To investigate the effectiveness of different backbone CNNs and learning approaches, we conduct an intensive experiment on three benchmark datasets Plant Village, Plant Leaves, and PlantDoc. The experimental results demonstrate that InceptionV3 can be a good choice for a backbone CNN as its performance is better than AlexNet, VGG16, ResNet101, EfficientNet, MobileNet, and a custom CNN developed by us. Interestingly, empirical results support the hypothesis that using a single model can be comparable or better than using two models. Finally, we show that the proposed GSMo-CNN achieves state-of-the-art performance on three benchmark datasets.

Guozhe Zhang, Cuihua Gu, Yacheng Ye et al.

Heat shock transcription factors (HSFs) are among the most important regulators of plant responses to abiotic stimuli. They play a key role in numerous transcriptional regulatory processes. However, the specific characteristics of HSF gene family members and their expression patterns in different tissues and under drought stress have not been precisely investigated in <i>Heimia myrtifolia</i>. This study analyzed transcriptome data from <i>H. myrtifolia</i> and identified 15 members of the HSF family. Using a phylogenetic tree, these members were classified into three major classes and fifteen groups. The amino acid physicochemical properties of these members were also investigated. The results showed that all <i>HmHSF</i> genes are located in the nucleus, and multiple sequence alignment analysis revealed that all HmHSF proteins have the most conserved DBD structural domains. Interestingly, a special HmHSF15 protein was found in the three-dimensional structure of the protein, which has a conserved structural domain that performs a function in addition to the unique structural domain of HSF proteins, resulting in a three-dimensional structure for HmHSF15 that is different from other HmHSF proteins. GO enrichment analysis shows that most <i>HmHSFA</i>-like genes are part of various biological processes associated with abiotic stresses. Finally, this study analyzed the tissue specificity of <i>HmHSF</i> genes in different parts of <i>H. myrtifolia</i> by qRT-PCR and found that <i>HmHSF</i> genes were more abundantly expressed in roots than in other tissues, and <i>HmHSF05</i>, <i>HmHSF12</i>, and <i>HmHSF14</i> genes were different from other <i>HSF</i> genes, which could be further analyzed to verify their functionality. The results provide a basis for analyzing the functions of <i>HmHSF</i> genes in <i>H. myrtifolia</i> and help to explore the molecular regulatory mechanism of <i>HmHSF</i> in response to drought stress.

А. P. Levitskiy, Yu. A. Levitskiy, I. A. Selivanska et al.

The work shows that Fatty acids of dietary fats provide two main functions in the human and animal body: energy and structural-regulatory, Polyunsaturated fatty acids (PUFA) are the basis of membrane lipids of all cells of the body The structure and functional activity of cells, their resistance to pathogenic factors depends on the ratio of ω-6 / ω-3 PUFA. Аdherence to recommended metabolic energy reserves in poultry feed is essential to optimize feed costs. The use of oils or fats is a common economic practice in modern poultry production. Energy functions are carried out due to the oxidation of energy fatty acids in mitochondria, which include, first of all, palmitic (С16:0), palmitooleic (С16:0), stearic (С18:1) and oleic (С18:1). In addition to providing energy, edible oil can also enhance dietary palatability, reduce dustiness, and increase lipoprotein hydrolysis to promote the production of essential fatty acids. Adipose tissue should be considered not only as a source of various fatty acids, but also as an important endocrine organ that takes an active part in the activity of the immune system. To determine the effect of a diet with high oleic sunflower oil on the content of energy fatty acids (EFA) and long-chain PUFA (LCPUFA) in rat liver lipids. We used high oleic sunflower oil (HOSO) containing 85.5% oleic acid. The rats were fed a fat-free diet (FFD) and diets with 5 or 15% HOSO for 35 days. Lipids were extracted from the liver and separated into three fractions: neutral lipids (NL), phospholipids (PL) and free fatty acids (FFA). The fatty acid composition of lipid fractions was determined by gas chromatography. FFA are the sum of the following acids:С16:0, С16:1, С18:0, С18:1andС18:2. LCPUFA are presented С20:4 ω-6, С20:5 ω-3, С22:5 ω-3and С22:6 ω-3. Most of all, EFA is contained in the NL fraction (89%), then in the PL fraction (79%), and least of all in the FFA fraction (68%). LCPUFA is found most of all in the FFA fraction (20%), then in the PL fraction (13%), and least of all in the NL fraction (2%). In rats that received fat diets, the content of EFA increased in the NL fraction by 2-3%, in the FFA fraction by 5-8%, and did not change in the PL fraction. The content of LCPUFA ω-6 (arachidonic acid) with fat nutrition dose-dependently decreases in the fraction of NL and FFA and does not change in the fraction of PL. On the contrary, the content of ω-3 LCPUFA increases in rats treated with HOSO in all lipid fractions. Also, the ω-6/ω-3 LCPUFA ratio is significantly reduced in rats treated with HOSO. Consumption of HOSO stimulates endogenous biosynthesis of ω-3 LCPUFA.

Mi-Hyun Lee, Sung-Jun Hong, Dong Suk Park et al.

Bacterial leaf blight of carrots caused by Xanthomonas hortorum pv. carotae (Xhc) is an important worldwide seed-borne disease. In 2012 and 2013, symptoms similar to bacterial leaf blight were found in carrot farms in Jeju Island, Korea. The phenotypic characteristics of the Korean isolation strains were similar to the type strain of Xhc. Pathogenicity showed symptoms on the 14th day after inoculation on carrot plants. Identification by genetic method was multi-position sequencing of the isolated strain JJ2001 was performed using four genes (danK, gyrB, fyuA, and rpoD). The isolated strain was confirmed to be most similar to Xhc M081. Furthermore, in order to analyze the genetic characteristics of the isolated strain, whole genome analysis was performed through the next-generation sequencing method. The draft genome size of JJ2001 is 5,443,372 bp, which contains 63.57% of G + C and has 4,547 open reading frames. Specifically, the classification of pathovar can be confirmed to be similar to that of the host lineage. Plant pathogenic factors and determinants of the majority of the secretion system are conserved in strain JJ2001. This genetic information enables detailed comparative analysis in the pathovar stage of pathogenic bacteria. Furthermore, these findings provide basic data for the distribution and diagnosis of Xanthomonas hortorum pv. carotae, a major plant pathogen that infects carrots in Korea.