• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3390-3405
• /
• 2022

Long Short-Term Memory (LSTM) combined with attention mechanism is extensively used to generate semantic sentences of images in image captioning models. However, features of salient regions and spatial information are not utilized sufficiently in most related works. Meanwhile, the LSTM also suffers from the problem of underutilized information in a single time step. In the paper, two innovative approaches are proposed to solve these problems. First, the Synergy-Gated Attention (SGA) method is proposed, which can process the spatial features and the salient region features of given images simultaneously. SGA establishes a gated mechanism through the global features to guide the interaction of information between these two features. Then, the Recurrent Fusion LSTM (RF-LSTM) mechanism is proposed, which can predict the next hidden vectors in one time step and improve linguistic coherence by fusing future information. Experimental results on the benchmark dataset of MSCOCO show that compared with the state-of-the-art methods, the proposed method can improve the performance of image captioning model, and achieve competitive performance on multiple evaluation indicators.

• International Journal of Computer Science & Network Security
• /
• 제21권11호
• /
• pp.73-80
• /
• 2021

Nowadays microblogs have become the most popular platforms to obtain and spread information. Twitter is one of the most used platforms to share everyday life event. However, rumors and misinformation on Arabic social media platforms has become pervasive which can create inestimable harm to society. Therefore, it is imperative to tackle and study this issue to distinguish the verified information from the unverified ones. There is an increasing interest in rumor detection on microblogs recently, however, it is mostly applied on English language while the work on Arabic language is still ongoing research topic and need more efforts. In this paper, we propose a combined Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to detect rumors on Twitter dataset. Various experiments were conducted to choose the best hyper-parameters tuning to achieve the best results. Moreover, different neural network models are used to evaluate performance and compare results. Experiments show that the CNN-LSTM model achieved the best accuracy 0.95 and an F1-score of 0.94 which outperform the state-of-the-art methods.

• Journal of Information Processing Systems
• /
• 제18권5호
• /
• pp.637-649
• /
• 2022

Investors aim to increase their profitability by investing in the stock market. An adroit strategy for minimizing related risk lies through diversifying portfolio operationalization. In this paper, we propose a six-step stocks portfolio selection model. This model is based on data mining clustering techniques that reflect the ensuing impact of the political, economic, legal, and corporate governance in Mongolia. As a dataset, we have selected stock exchange trading price, financial statements, and operational reports of top-20 highly capitalized stocks that were traded at the Mongolian Stock Exchange from 2013 to 2017. In order to cluster the stock returns and risks, we have used k-means clustering techniques. We have combined both k-means clustering with Markowitz's portfolio theory to create an optimal and efficient portfolio. We constructed an efficient frontier, creating 15 portfolios, and computed the weight of stocks in each portfolio. From these portfolio options, the investor is given a choice to choose any one option.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.166-166
• /
• 2023

Compound hazards (CHs) are two or more extreme climate events combined which occur simultaneously in the same region at the same time. Compared to individual hazards, the combination of hazards that cause CHs can result in greater economic losses and deaths. While several extreme climate events have been recorded across Asia for the past decades, many studies have only focused on a single hazard. In this study, we assess the spatiotemporal pattern of dry compound hazards which includes drought, heatwave, fire and wind across Asia for the last 42 years (1980-2021) using the historical data from ERA5 Reanalysis dataset. We utilize a daily spatial data of each climate event to assess the occurrence of such compound hazards on a daily basis. Heatwave, fire and wind hazard occurrences are analyzed using daily percentile-based thresholds while a pre-defined threshold for SPI is applied for drought occurrence. Then, the occurrence of each type of compound hazard is taken from overlapping the map of daily occurrences of a single hazard. Lastly, a multivariate assessment are conducted to quantify the occurrence frequency, hotspots and trends of each type of compound hazard across Asia. By conducting a multivariate analysis of the occurrence of these compound hazards, we identify the relationships and interactions in dry compound hazards including droughts, heatwaves, fires, and winds, ultimately leading to better-informed decisions and strategies in the natural risk management.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2222-2240
• /
• 2023

Brand fandom refers to a collection of consumers with strong emotions toward a brand. Studying the dynamics of brand fandom can help brands understand which services or strategies influence their consumers to become a part of brand fandom. However, existing literature on fandom in the last three decades has mainly used qualitative methods, and there is still a lack of research on fandom using quantitative methods. Specifically, previous studies lack a framework for locating fandoms from online textual data and analyzing their dynamics. This study proposes a framework for exploring brand fandom dynamics based on online textual data. This framework consists of four phases based on the design thinking model: Preparing Data, Defining Fandom Categories, Generating Fandom Dynamics, and Analyzing Fandom Dynamics. This framework uses techniques such as social network analysis and process mining, combined with brand personality theory. We demonstrate the applicability of this framework using case studies of two Korean home appliance brands. The dataset contains 14,593 posts by consumers in 374 online communities. The results show that the proposed framework can analyze brand fandom dynamics using textual customer data. Our study contributes to the interdisciplinary research at the intersection of data-driven service design and consumer culture quantification.

• Mycobiology
• /
• 제51권2호
• /
• pp.67-71
• /
• 2023

A powdery mildew (Erysiphaceae) has been continuously collected on the leaves of Lonicera harae in the southern part of the Korean Peninsula, where this shrub is indigenous. Microscopic examination of the asexual morphs revealed that the current collections are differentiated from the all known Erysiphe species on Lonicera spp. by its longer conidiophores and longer conidia. Although the morphology of the chasmothecia is reminiscent of Erysiphe ehrenbergii and E. lonicerae, the specimens on L. harae differ from them in having smaller ascospores. A phylogenetic tree generated from a combined dataset of the internal transcribed spacer region and 28S rDNA gene sequences demonstrates that sequences obtained from three powdery mildew collections on L. harae clustered together as an independent species clade with high bootstrap values distant from other Erysiphe species on Lonicera, representing a species of its own. Based on morphological differences and molecular-phylogenetic results, the powdery mildew on L. harae is proposed as a new species, Erysiphe lonicerigena, and the holomorph of the fungus is described and illustrated in this study.

• Structural Engineering and Mechanics
• /
• 제86권2호
• /
• pp.181-195
• /
• 2023

To predict the rheological behaviours along with the compressive strength of self-compacting concrete that incorporates environmentally friendly ingredients as cement substitutes, a comparative evaluation of machine learning methods is conducted. To model four parameters, slump flow diameter, L-box ratio, V-funnel time, as well as compressive strength at 28 days-a complete mix design dataset from available pieces of literature is gathered and used to construct the suggested machine learning standards, SVM, MARS, and Mp5-MT. Six input variables-the amount of binder, the percentage of SCMs, the proportion of water to the binder, the amount of fine and coarse aggregates, and the amount of superplasticizer are grouped in a particular pattern. For optimizing the hyper-parameters of the MARS model with the lowest possible prediction error, a gravitational search algorithm (GSA) is required. In terms of the correlation coefficient for modelling slump flow diameter, L-box ratio, V-funnel duration, and compressive strength, the prediction results showed that MARS combined with GSA could improve the accuracy of the solo MARS model with 1.35%, 11.1%, 2.3%, as well as 1.07%. By contrast, Mp5-MT often demonstrates greater identification capability and more accurate prediction in comparison to MARS-GSA, and it may be regarded as an efficient approach to forecasting the rheological behaviors and compressive strength of SCC in infrastructure practice.

• 한국균학회지
• /
• 제50권3호
• /
• pp.195-204
• /
• 2022

A fungal strain, designated KNUF-20-NI009, was isolated from soil collected from Gunsan-si, Jeollabuk-do, Korea. The isolate showed cultural features typical of the genus Xenoroussoella. Colonies cultivated on malt extract agar were olivaceous-brown to pale olivaceous-white at the margins, with undersides of dark olivaceous to olivaceous-brown and a white margin. The conidia, with a size range of 2.7-5.1×1.6-3.3 ㎛ ($\bar{x}=3.6\times2.6{\mu}m$, n=50), were globoid to ellipsoid in shape, hyaline when immature, becoming light brown to golden-brown when mature, and characterized by 1 or 2 guttules. Multi-locus sequence analysis based on a combined dataset of internal transcribed spacer regions (ITS), large subunit rDNA (LSU), small subunit rDNA (SSU), translation elongation factor 1-alpha (TEF1α), and RNA polymerase II largest subunit (RPB2) sequences revealed KNUF-20-NI009 to be a strain of Xenoroussoella triseptata. This is the first report of this species in Korea.

• Mycobiology
• /
• 제51권5호
• /
• pp.288-299
• /
• 2023

Aspergillus is one of the largest and diverse genera of fungi with huge economical, biotechnological, and social significance. Taxonomically, Aspergillus is divided into six subgenera comprising 27 sections. In this study, 235 strains of Aspergillus subgenus Circumdati (section: Candidi, Circumdati, Flavi, Flavipedes, Nigri, and Terrei) preserved at the Korean Agricultural Culture Collection (KACC) were analyzed and re-identified using a combined dataset of partial b-tubulin (BenA), Calmodulin (CaM) gene sequences and morphological data. We confirmed nineteen species to be priorly reported in Korea (A. neotritici, A. terreus, A. floccosus, A. allahabadii, A. steynii, A. westerdijkiae, A. ochraceus, A. ostianus, A. sclerotiorum, A. luchuensis, A. tubingensis, A. niger, A. welwitschiae, A. japonicus, A. nomius, A. tamarii, A. parasiticus, A. flavi, and A. oryzae). Among the studied strains, three species (A. subalbidus, A. iizukae, and A. uvarum), previously unreported or not officially documented, were discovered in Korea, to the best of our knowledge. We have given a detailed description of the characteristic features of the three species, which remain uncharted in Korea.

• 한국인터넷방송통신학회논문지
• /
• 제23권5호
• /
• pp.71-76
• /
• 2023

본 논문에서는 딥러닝을 이용한 영상 분할에서 성능을 향상하기 위해 퍼지 논리를 적용하는 퍼지 딥러닝 모델인 퍼지 U-Net을 제안한다. 퍼지 논리를 이용한 퍼지 모듈을 영상 분할에서 우수한 성능을 보이는 딥러닝 모델인 U-Net에 결합하여 다양한 형태의 퍼지 모듈을 시뮬레이션하였다. 제안된 딥러닝 모델의 퍼지 모듈은 이미지의 특징맵과 해당 분할 결과 사이의 본질적이고 복잡한 규칙을 학습다. 이를 위해 치아 CBCT 데이터에 적용하여 제안된 방법의 우수성을 입증하였다. 시뮬레이션 결과 제안된 퍼지 U-Net에서 더하기 스킵 연결을 사용한 모델의 ADD-RELU 퍼지 모듈 구조의 성능이 시험용 데이터에 대해 0.7928로 가장 우수한 것을 볼 수 있다.