Search

The introduction of exotic species and the associated impacts are increasing worldwide due to the development and increase in transportation and international trade. As new populations of the non-native Gekko japonicus and G. swinhonis have recently been discovered in South Korea, this study was conducted to investigate the distribution of these species, evaluate the establishment potential of non-native populations and infer their routes of introduction. The study comprised targeted field surveys around the major international ports, generation of ecological niche models (ENMs), based on the known distributions and comparison of the ecological niches of the two species. The results suggest that G. japonicus and G. swinhonis are primarily distributed in the humid subtropical climate (Cfa) and the monsoon-influenced hot-summer humid continental climate (Dwa), respectively. According to the ENMs predicted across South Korea, suitable habitats for G. japonicus were located along the western and southern coasts of the country, whereas those for G. swinhonis were predicted along the western coastal regions and several major cities inland. These distributional patterns may be attributed to adaptations of the two gecko congeners to distinct climatic conditions leading to divergent ecological niches. Considering the known distributions of the two species in South Korea, the most likely routes of introduction are accidental translocations through international trade and the inland populations most likely originated from human-mediated dispersals along the major rivers. This study highlights the need to implement quarantine procedures for international cargo arriving in South Korea. Additional field surveys are further recommended to focus on urban areas adjacent to international ports and major rivers to curtail further introductions of non-native geckos. [ABSTRACT FROM AUTHOR]

This research intended to establish a new fashion-related artificial intelligence research topic concerning fashion editorials which could induce streams of further studies. A new fashion editorial dataset, which is a prerequisite in training an AI model, has been established in this study to meet the research purpose. A total of over 150K fashion editorials were initially collected and processed to satisfy necessary dataset conditions. A novel dataset of fashion editorials consisting of approximately 60K editorials is proposed through the process. In order to prove the adequacy of the new dataset, data distribution was analyzed and a generative model was selected and trained to attest that new fashion editorials can be created with the proposed editorial dataset. The results generated by the trained model were qualitatively investigated. The model has shown to have learned various features that compose editorials with the dataset, successfully generating fashion editorials. Quantitative evaluation with FID scores was conducted to support the selection of the generative model used for the qualitative assessment. [ABSTRACT FROM AUTHOR]

In this study, an artificial neural network (ANN) was established to predict product properties (mass, diameter, height) using six process conditions of the injection-molding process (melt temperature, mold temperature, injection speed, packing pressure, packing time, and cooling time) as input parameters. The injection-molding process consists of continuous sequential stages, including the injection stage, packing stage, and cooling stage. However, the related research tends to have an insufficient incorporation of structural characteristics based on these basic process stages. Therefore, in order to incorporate these process stages and characteristics into the ANN, a process-based multi-task learning technique was applied to the connection between the input parameters and the front-end of the hidden layer. This resulted in the construction of two network structures, and their performance was evaluated by comparing them with the typical network structure. The results showed that a multi-task learning architecture that incorporated process-level specific structures in the connections between the input parameters and the front end of the hidden layer yielded relatively better root mean square errors (RMSEs) values than a conventional neural network architecture, by as much as two orders of magnitude. Based on these results, this study has provided guidance for the construction of artificial neural networks for injection-molding processes that incorporates process-stage specific features and structures in the architecture. [ABSTRACT FROM AUTHOR]

In this study, a multi-input, multi-output-based artificial neural network (ANN) was constructed by classifying output parameters into different groups, considering the physical meanings and characteristics of product quality factors in the injection molding process. Injection molding experiments were conducted for bowl products, and a dataset was established. Based on this dataset, an ANN model was developed to predict the quality of molded products. The input parameters included melt temperature, mold temperature, packing pressure, packing time, and cooling time. The output parameters included mass, diameter, and height of the molded product. The output parameters were divided into two cases. In one case, diameter, and height, representing length, were grouped together, while mass was organized into a separate group. In the other case, mass, diameter and height were separated individually and applied to the ANN. A multi-task learning method was used to group the output parameters. The performance of the two constructed multi-task learning-based ANNs was compared with that of the conventional ANN where the output parameters were not separated and applied to a single layer. The comparative results showed that the multi-task learning architecture, which grouped the output parameters considering the physical meaning and characteristics of the quality of molded products, exhibited an improved prediction performance of about 32.8% based on the RMSE values. [ABSTRACT FROM AUTHOR]

Microplastic pollution has emerged as a global environmental concern, exhibiting wide distribution within marine ecosystems, including the Arctic Ocean. Limited Arctic microplastic data exist from beached plastics, seabed sediments, floating plastics, and sea ice. However, no studies have examined microplastics in the sea ice of the Canadian Arctic Archipelago and Tallurutiup Imanga National Marine Conservation Area, and few have explored Arctic marginal seas' water column. The majority of the microplastic data originates from the Eurasian Arctic, with limited data available from other regions of the Arctic Ocean. This study presents data from two distinct campaigns in the Canadian Arctic Archipelago and Western Arctic marginal seas in 2019 and 2020. These campaigns involved sampling from different regions and matrices, making direct comparisons inappropriate. The study's primary objective is to provide insights into the spatial and vertical distribution of microplastics. The results reveal elevated microplastic concentrations within the upper 50 m of the water column and significant accumulation in the sea ice, providing evidence to support the designation of sea ice as a microplastic sink. Surface seawater exhibits a gradient of microplastic counts, decreasing from the Chukchi Sea towards the Beaufort Sea. Polyvinyl chloride polymer (~60%) dominated microplastic composition in both sea ice and seawater. This study highlights the need for further investigations in this region to enhance our understanding of microplastic sources, distribution, and transport. [ABSTRACT FROM AUTHOR]