• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1275-1292
• /
• 2021

As a fine-grained classification problem, aspect-level sentiment classification predicts the sentiment polarity for different aspects in context. To address this issue, researchers have widely used attention mechanisms to abstract the relationship between context and aspects. Still, it is difficult to effectively obtain a more profound semantic representation, and the strong correlation between local context features and the aspect-based sentiment is rarely considered. In this paper, a hybrid attention capsule network for aspect-level sentiment classification (ABASCap) was proposed. In this model, the multi-head self-attention was improved, and a context mask mechanism based on adjustable context window was proposed, so as to effectively obtain the internal association between aspects and context. Moreover, the dynamic routing algorithm and activation function in capsule network were optimized to meet the task requirements. Finally, sufficient experiments were conducted on three benchmark datasets in different domains. Compared with other baseline models, ABASCap achieved better classification results, and outperformed the state-of-the-art methods in this task after incorporating pre-training BERT.

• Journal of Distribution Science
• /
• v.18 no.12
• /
• pp.5-13
• /
• 2020

Purpose: The objective of this study is to explore and prioritize strategic factors for revitalization of the sports contents distribution industry. Research design, data and methodology: To this end, strategic factors for revitalization of the sports contents distribution industry were explored based on literature review, and 14 experts were consulted to prioritize the factors. Results: Major conclusions deduced are the following: First, the factors were prioritized in order of legal policy factors, contents factors, and technical infrastructure factors. Second, subdomains of legal policy factors were prioritized in order of policy process factors, legislation enactment and revision factors, budget factors, business model factors focusing on sports contents. Third, subdomains of contents factors were prioritized in order of humanware contents factors, sports contents diversification factors, and high-quality sports contents production factors. Fourth, subdomains of technical infrastructure factors were prioritized in order of sports contents service platform factors, technical development and standardization, global distribution channel provision, and distribution metadata standardization. Conclusions: Findings of this study are of significance given that this study stratifies factors of sports contents distribution industry revitalization-about which there have been very few previous studies- analyzed mainly in terms of justifiability and timeliness, and presents preferential business strategies.

• International Journal of Computer Science & Network Security
• /
• v.21 no.4
• /
• pp.115-122
• /
• 2021

In the recent past enormous enterprise applications have migrated into the cloud computing (CC). The researchers have contributed to this ever growing technology and as a result several innovations strengthened to offer the quality of service (QoS) as per the demand of the customer. It was treated that management of resources as the major challenge to offer the QoS while focusing on the trade-offs among the performance, availability, reliability and the cost. Apart from these regular key focuses to meet the QoS other key issues in CC are data integrity, privacy, transparency, security and legal aspects (DIPTSL). This paper aims to carry out the literature survey by reflecting on the prior art of the work with regard to QoS in CC and possible implementation of block chain to implement decentralised CC solutions governing DIPTSL as an integral part of QoS.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1246-1262
• /
• 2021

Recent studies have demonstrated the strong ability of deep convolutional neural networks (CNNs) to significantly boost the performance in single image super-resolution (SISR). The key concern is how to efficiently recover and utilize diverse information frequencies across multiple network layers, which is crucial to satisfying super-resolution image reconstructions. Hence, previous work made great efforts to potently incorporate hierarchical frequencies through various sophisticated architectures. Nevertheless, economical SISR also requires a capable structure design to balance between restoration accuracy and computational complexity, which is still a challenge for existing techniques. In this paper, we tackle this problem by proposing a competent architecture called Enhanced U-Net Network (EUN), which can yield ready-to-use features in miscellaneous frequencies and combine them comprehensively. In particular, the proposed building block for EUN is enhanced from U-Net, which can extract abundant information via multiple skip concatenations. The network configuration allows the pipeline to propagate information from lower layers to higher ones. Meanwhile, the block itself is committed to growing quite deep in layers, which empowers different types of information to spring from a single block. Furthermore, due to its strong advantage in distilling effective information, promising results are guaranteed with comparatively fewer filters. Comprehensive experiments manifest our model can achieve favorable performance over that of state-of-the-art methods, especially in terms of computational efficiency.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.136-150
• /
• 2021

The modern market is highly competitive. It has progressed from traditional competition between enterprises to competition between supply chains. To ensure that enterprise can form the best strategy consistently, it is necessary to evaluate the trust of other enterprises in the supply chain. First, this paper analyzes the background and significance of supply chain trust research, analyzes and expounds on the qualitative and quantitative methods of supply chain trust evaluation, and summarizes the research in this field. Analytic hierarchy process (AHP) is the most frequently used method in the literature to evaluate and rank criteria through data analysis. However, the input data for AHP analysis is based on human judgment, and hence there is every possibility that the data may be vague to some extent. Therefore, in view of the above problems, this study improves the global trust method based on chain iteration. The improved global trust evaluation method based on chain iteration is more flexible and practical, hence, it can more accurately evaluate supply chain trust. Finally, combined with an actual case of Zhaoxian Chengji Food Co. Ltd., the paper qualitatively analyzes the current situation of supply chain trust management and effectively strengthens the supervision of enterprises to cooperative enterprises. Thus, the company can identify problems on time and strategic adjustments can be implemented accordingly. The effectiveness of the evaluation method proposed in this paper is demonstrated through a quantitative evaluation of its trust in downstream enterprise A. Results suggest that the subjective preferences of and historical transactions together affect the final evaluation of trust.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.476-490
• /
• 2022

With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more vital than ever. In this study, we propose a method to rapidly recognize a large speech database via a transformer-based end-to-end model. Transformers have improved the state-of-the-art performance in many fields. However, they are not easy to use for long sequences. In this study, various techniques to accelerate the recognition of real-world speeches are proposed and tested, including decoding via multiple-utterance-batched beam search, detecting end of speech based on a connectionist temporal classification (CTC), restricting the CTC-prefix score, and splitting long speeches into short segments. Experiments are conducted with the Librispeech dataset and the real-world Korean ASR tasks to verify the proposed methods. From the experiments, the proposed system can convert 8 h of speeches spoken at real-world meetings into text in less than 3 min with a 10.73% character error rate, which is 27.1% relatively lower than that of conventional systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• 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.

• ETRI Journal
• /
• v.44 no.5
• /
• pp.794-804
• /
• 2022

Transformer models have had a great impact on natural language processing (NLP) in recent years by realizing outstanding and efficient contextualized language models. Recent studies have used transformer-based language models for various NLP tasks, including Persian named entity recognition (NER). However, in complex tasks, for example, NER, it is difficult to determine which contextualized embedding will produce the best representation for the tasks. Considering the lack of comparative studies to investigate the use of different contextualized pretrained models with sequence modeling classifiers, we conducted a comparative study about using different classifiers and embedding models. In this paper, we use different transformer-based language models tuned with different classifiers, and we evaluate these models on the Persian NER task. We perform a comparative analysis to assess the impact of text representation and text classification methods on Persian NER performance. We train and evaluate the models on three different Persian NER datasets, that is, MoNa, Peyma, and Arman. Experimental results demonstrate that XLM-R with a linear layer and conditional random field (CRF) layer exhibited the best performance. This model achieved phrase-based F-measures of 70.04, 86.37, and 79.25 and word-based F scores of 78, 84.02, and 89.73 on the MoNa, Peyma, and Arman datasets, respectively. These results represent state-of-the-art performance on the Persian NER task.

• Wind and Structures
• /
• v.34 no.1
• /
• pp.101-113
• /
• 2022

We experimentally investigate the high-Reynolds flow around a rectangular cylinder of aspect ratio 5:1. This configuration is the object of the international BARC benchmark. Wind tunnel tests have been carried out for the flow at zero angle of attack and a Reynolds number, based on the crossflow cylinder length and on the freestream velocity, equal, to 40 000. Velocity measurements are obtained by using hot-wire anemometry along 50 different cross-flow traverses on the cylinder side and in the near wake. Differential pressure measurements are acquired on multiple streamwise sections of the model. The obtained measurements are in a good agreement with the state-of-the-art experiments. For the first time among the several contributions to the BARC benchmark, detailed flow measurements are acquired in the region near the cylinder side and in the near-wake flow. The edges and the thickness of the shear layers detaching from the upstream edges are derived from velocity measurements. Furthermore, we compute the flow frequencies characterizing the roll-up of the shear layers, the evolution of vortical structures near the cylinder side and the vortex shedding in the wake.