Integrated simulation framework for the process planning of ships and offshore structures

Recently, requests for accurate process planning using simulation have been increasing in many engineering fields, including the shipbuilding industry. To date, designers of shipyards have developed in-house simulation systems or used commercial systems such as the QUEST by Dassault system when requests for the simulation of process planning have occurred. However, these methods have some limitations. First, it requires a lot of time to develop a new in-house simulation system. In addition, it is hard to reuse previously developed systems when developing a new one and it is also hard for these to satisfy the various needs of shipyards effectively.     

A fuzzy ensemble of parallel polynomial neural networks with information granules formed by fuzzy clustering

In this paper, we introduce a new category of fuzzy models called a fuzzy ensemble of parallel polynomial neural network (FEP²N²), which consist of a series of polynomial neural networks weighted by activation levels of information granules formed with the use of fuzzy clustering. The two underlying design mechanisms of the proposed networks rely on information granules resulting from the use of fuzzy C-means clustering (FCM) and take advantage of polynomial neural networks (PNNs).The resulting model comes in the form of parallel polynomial neural networks. In the design procedure, in order to estimate the optimal values of the coefficients of polynomial neural networks we use a weighted least square estimation algorithm. We incorporate various types of structures as the consequent part of the fuzzy model when using the learning algorithm. Among the diverse structures being available, we consider polynomial neural networks, which exhibit highly nonlinear characteristics when being viewed as local learning models.We use FCM to form information granules and to overcome the high dimensionality problem. We adopt PNNs to find the optimal local models, which can describe the relationship between the input variables and output variable within some local region of the input space.We show that the generalization capabilities as well as the approximation abilities of the proposed model are improved as a result of using polynomial neural networks. The performance of the network is quantified through experimentation in which we use a number of benchmarks already exploited within the realm of fuzzy or neurofuzzy modeling.     

Heat transfer characteristics of flat plate finned-tube heat exchangers with large fin pitch

The objective of this study is to provide experimental data that can be used in the optimal design of flat plate finned-tube heat exchangers with large fin pitch. In this study, 22 heat exchangers were tested with a variation of fin pitch, number of tube row, and tube alignment. The air-side heat transfer coefficient decreased with a reduction of the fin pitch and an increase of the number of tube row. The reduction in the heat transfer coefficient of the four-row heat exchanger coil was approximately 10% as the fin pitch decreased from 15.0 to 7.5 mm over the Reynolds number range of 500–900 that was calculated based on the tube diameter. For all fin pitches, the heat transfer coefficient decreased as the number of tube row increased from 1 to 4. The staggered tube alignment improved heat transfer performance more than 10% compared to the inline tube alignment. A heat transfer correlation was developed from the measured data for flat plate finned-tubes with large fin pitch. The correlation yielded good predictions of the measured data with mean deviations of 3.8 and 6.2% for the inline and staggered tube alignment, respectively.     

Hydrogen production from low temperature WGS reaction on co-precipitated Cu–CeO2 catalysts: An optimization of Cu loading

Low temperature water–gas shift (WGS) reaction has been carried out at the gas hourly space velocity of 72,152 h⁻¹ over Cu–CeO₂ catalyst prepared by a co-precipitation method. Cu loading was optimized to obtain highly active co-precipitated Cu–CeO₂ catalysts for low temperature WGS. 80 wt% Cu–CeO₂ exhibited the highest CO conversion as well as the most stable activity (X_CO > 46% at 240 °C for 100 h). The excellent catalytic performance is mainly due to a strong metal to support interaction, resulting in the prevention of Cu sintering.     

Mechanical and dielectric properties of functionalized boron nitride nanosheets/silicon nitride composites

Uniformly dispersed boron nitride nanosheets (BNNSs) reinforced silicon nitride (Si₃N₄) composites were prepared by surface modification assisted flocculation combined with SPS sintering. In order to improve the dispersibility of the BNNSs in the composites, the liquid phase stripped BNNSs are surface functionalized by a two-step covalently modification. The amino-modified BNNSs (NH₂-BNNSs) and Si₃N₄ powders have opposite surface potential, mixed evenly by electrostatic interaction during flocculation. The results showed that mechanical properties of Si₃N₄ composites were obviously enhanced by adding NH₂-BNNSs. The fracture toughness and bending strength of Si₃N₄ composites added 0.75 wt% NH₂-BNNSs were increased by 34% and 28%, respectively, compared with monolithic Si₃N₄. Toughening mechanisms are synergistic action of the torn, pull-out or bridging of BNNSs and crack deflection mechanisms with microstructural analyzes. The dielectric properties of the Si₃N₄ ceramics are also improved after the addition of NH₂-BNNSs.     

Selective temporal filtering and its application to hand gesture recognition

In temporal data analysis, noisy data is inevitable in both testing and training. This noise can seriously influence the performance of the temporal data analysis. To address this problem, we propose a novel method, termed Selective Temporal Filtering that builds a noise-free model for classification during training and identifies key-feature vectors that are noise-filtered data from the input sequence during testing. The use of these key-feature vectors makes the classifier robust to noise within the input space. The proposed method is validated on a synthetic-dataset and a database of American Sign Language. Using key-feature vectors results in robust performance with respect to the noise content. Futhermore, we are able to show that the proposed method not only outperforms Conditional Random Fields and Hidden Markov Models in noisy environments, but also in a well-controlled environment where we assume no significant noise vectors exist.     

Korean automatic spacing using pretrained transformer encoder and analysis

Automatic spacing in Korean is used to correct spacing units in a given input sentence. The demand for automatic spacing has been increasing owing to frequent incorrect spacing in recent media, such as the Internet and mobile networks. Therefore, herein, we propose a transformer encoder that reads a sentence bidirectionally and can be pretrained using an out-of-task corpus. Notably, our model exhibited the highest character accuracy (98.42%) among the existing automatic spacing models for Korean. We experimentally validated the effectiveness of bidirectional encoding and pretraining for automatic spacing in Korean. Moreover, we conclude that pretraining is more important than fine-tuning and data size.     

Automatic logo transition detection in digital video contents

The amount of user created contents has been increasing rapidly and is associated with a serious copyright problem. Automatic logo detection and recognition in videos is a natural and efficient way of overcoming the copyright problem. However, logos have varying characteristics, which make logo detection and recognition very difficult. Moreover, logo transitions between two different logos exist in one video comprising several video contents. This disrupts the automatic logo detection and recognition. Therefore, in order to improve logo detection, it is necessary to take into account the logo transitions explicitly. This paper proposes an accurate logo transition detection method for recognizing logos in digital video contents. The proposed method accurately segments a video according to logo and efficiently recognizes various types of logos. The experimental results demonstrate the effectiveness of the proposed method for logo detection and video segmentation according to logo.