• 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.

• Structural Engineering and Mechanics
• /
• v.78 no.3
• /
• pp.319-332
• /
• 2021

The wood-concrete composite is an interesting solution in the field of Civil Engineering to create high performance bending elements for bridges, as well as in the building construction for the design of wood concrete floor systems. The authors of this paper has been working for the past few years on the development of the bonding process as applied to wood-concrete composite structures. Contrary to conventional joining connectors, this assembling technique does ensure an almost perfect connection between wood and concrete. This paper presents a careful theoretical investigation into interfacial stresses at the level of the two interfaces in composite wooden beam- reinforced concrete slab strengthened by external bonding of prestressed composite plate under a uniformly distributed load. The model is based on equilibrium and deformations compatibility requirements in all parts of the strengthened composite beam, i.e., the wooden beam, RC slab, the CFRP plate and the adhesive layer. The theoretical predictions are compared with other existing solutions. This research is helpful for the understanding on mechanical behaviour of the interface and design of the CFRP- wooden-concrete hybrid structures.

• Wind and Structures
• /
• v.32 no.3
• /
• pp.267-281
• /
• 2021

Bending-twisting coupling induced in big composite wind turbine blades is one of the passive control mechanisms which is exploited to mitigate loads incurred due to deformation of the blades. In the present study, flutter characteristics of bend-twist coupled blades, designed for load alleviation in wind turbine systems, are investigated by time-domain analysis. For this purpose, a baseline full GFRP blade, a bend-twist coupled full GFRP blade, and a hybrid GFRP and CFRP bend-twist coupled blade is designed for load reduction purpose for a 5 MW wind turbine model that is set up in the wind turbine multi-body dynamic code PHATAS. For the study of flutter characteristics of the blades, an over-speed analysis of the wind turbine system is performed without using any blade control and applying slowly increasing wind velocity. A detailed procedure of obtaining the flutter wind and rotational speeds from the time responses of the rotational speed of the rotor, flapwise and torsional deformation of the blade tip, and angle of attack and lift coefficient of the tip section of the blade is explained. Results show that flutter wind and rotational speeds of bend-twist coupled blades are lower than the flutter wind and rotational speeds of the baseline blade mainly due to the kinematic coupling between the bending and torsional deformation in bend-twist coupled blades.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2882-2903
• /
• 2022

Image super-resolution (SR) processing is of great value in the fields of digital image processing, intelligent security, film and television production and so on. This paper proposed a densely connected deep learning network based on cascade architecture, which can be used to solve the problem of super-resolution in the field of image quality enhancement. We proposed a more efficient residual scaling dense block (RSDB) and the multi-channel cascade architecture to realize more efficient feature reuse. Also we proposed a hybrid loss function based on L₁ error and L_∞ error to achieve better L_∞ error performance. The experimental results show that the overall performance of the network is effectively improved on cascade architecture and residual scaling. Compared with the residual dense net (RDN), the PSNR / SSIM of the new method is improved by 2.24% / 1.44% respectively, and the L_∞ performance is improved by 3.64%. It shows that the cascade connection and residual scaling method can effectively realize feature reuse, improving the residual convergence speed and learning efficiency of our network. The L_∞ performance is improved by 11.09% with only a minimal loses of 1.14% / 0.60% on PSNR / SSIM performance after adopting the new loss function. That is to say, the L_∞ performance can be improved greatly on the new loss function with a minor loss of PSNR / SSIM performance, which is of great value in L_∞ error sensitive tasks.

• Journal of Convergence for Information Technology
• /
• v.11 no.8
• /
• pp.207-211
• /
• 2021

This paper addresses a two-stage flexible flow shop scheduling problem in which there is one machine in stage 1 and two identical machines in stage 2. The objective is the minimization of the total completion time. The problem is formulated by a mixed integer quadratic programming (MIQP) and a hybrid simulated annealing (HSA) is proposed to solve the MIQP. The HSA adopts the exploration capabilities of a genetic algorithm and incorporates a simulated annealing to reduce the premature convergence. Extensive computational tests on randomly generated problems are carried out to evaluate the performance of the HSA.

• Steel and Composite Structures
• /
• v.43 no.4
• /
• pp.419-429
• /
• 2022

In response to the sustainability requirements set in the EU Commission's "Green Deal" towards reduction of the greenhouse gas emissions, it is estimated that the structural design for deconstruction is going to contribute considerably to the sustainable development of the built environment. The demountability of multi-material structural systems basically depends on the shear connectors used in the structural system. This paper focuses on a type of demountable injected shear connector with an injected steel-reinforced resin (iSRR) which consists of spherical steel particles embedded in a resin. Its application to steel-to-concrete and steel-to-Fiber Reinforced Polymer (FRP) decks is presented along with its benefits. In parallel, an overview of the experimental and numerical research on the evaluation of the mechanical properties of the demountable bolted connectors with iSRR is discussed. Last, detailed finite element (FE) models and a parametric study are performed to quantify the confinement level of the SRR material influenced by the oversized hole diameter.

• Journal of Electrochemical Science and Technology
• /
• v.13 no.1
• /
• pp.1-18
• /
• 2022

Persistent organic pollutants (POPs) and emerging pollutants (EP) are characterized by their difficulty to be removed through biological oxidation processes (BOPs); they persist in the environment and could have adverse effects on the aquatic ecosystem and human health. The electro-oxidation (EO) process has been successfully used as an alternative technique to oxidize many kinds of the aforementioned pollutants in wastewater. However, the EO process has been criticized for its high energy consumption cost and its potential generation of by-products. In order to decrease these drawbacks, its combination with biological oxidation processes has been reported as a solution to reduce costs and to reach high rates of recalcitrant pollutants removal from wastewaters. Thus, the location of EO in the treatment line is an important decision to make, since this decision affects the formation of by-products and biodegradability enhancement. This paper reviews the advantages and disadvantages of EO as a pre and post-treatment in combination with BOPs. A perspective of the EO scale-up is also presented, where hydrodynamics and the relationship of A/V (area of the electrode/working volume of the electrochemical cell) experiments are examined and discussed.

• New & Renewable Energy
• /
• v.17 no.3
• /
• pp.1-7
• /
• 2021

The Korean government announced various energy policies, such as the to reduce 37% of the business-as-usual (BAU) greenhouse gas emissions by 2030. The policies aim to increase the renewable electricity generation ratio to 20% by 2030. PVT is a hybrid technology, which combines photovoltaic (PV) and solar collectors. It is capable of generating electricity and thermal energy simultaneously. It has a great potential to be used as a renewable and clean solar energy. However, there exists a shortage of space for the installation of PVT systems in Korea. To overcome this, in this paper proposes four types of soundproof wall PVT air channels, which were designed and optimized, based on the CFD (Computation Fluid Dynamic) analysis results. The thermal energy generation for multiple PVT units connected in series and pressure drop sensitivity were analyzed, depending on inlet velocity.

• Smart Structures and Systems
• /
• v.29 no.3
• /
• pp.513-522
• /
• 2022

Due to the importance of accurate analysis of bearing capacity in civil engineering projects, this paper studies the efficiency of two novel metaheuristic-based models for this objective. To this end, black hole algorithm (BHA) and multi-verse optimizer (MVO) are synthesized with an artificial neural network (ANN) to build the proposed hybrid models. Based on the settlement of a two-layered soil (and a shallow footing) system, the stability values (SV) of 0 and 1 (indicating the stability and failure, respectively) are set as the targets. Each model predicted the SV for 901 stages. The results indicated that the BHA and MVO can increase the accuracy (i.e., the area under the receiving operating characteristic curve) of the ANN from 94.0% to 96.3 and 97.2% in analyzing the SV pattern. Moreover, the prediction accuracy rose from 93.1% to 94.4 and 95.0%. Also, a comparison between the ANN's error decreased by the BHA and MVO (7.92% vs. 18.08% in the training phase and 6.28% vs. 13.62% in the testing phase) showed that the MVO is a more efficient optimizer. Hence, the suggested MVO-ANN can be used as a reliable approach for the practical estimation of bearing capacity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.4081-4098
• /
• 2022

With the aim of tackling the contradiction between computation intensive industrial applications and resource-weak Edge Devices (EDs) in Industrial Internet of Things (IIoT), a novel computation task offloading scheme in SDIN-enabled MEC based IIoT is proposed in this paper. With the aim of reducing the task accomplished latency and energy consumption of EDs, a joint optimization method is proposed for optimizing the local CPU-cycle frequency, offloading decision, and wireless and computation resources allocation jointly. Based on the optimization, the task offloading problem is formulated into a Mixed Integer Nonlinear Programming (MINLP) problem which is a large-scale NP-hard problem. In order to solve this problem in an accessible time complexity, a sub-optimal algorithm GPCOA, which is based on hybrid evolutionary computation, is proposed. Outcomes of emulation revel that the proposed method outperforms other baseline methods, and the optimization result shows that the latency-related weight is efficient for reducing the task execution delay and improving the energy efficiency.