• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.754-771
• /
• 2021

In the task of continuous dimension emotion recognition, the parts that highlight the emotional expression are not the same in each mode, and the influences of different modes on the emotional state is also different. Therefore, this paper studies the fusion of the two most important modes in emotional recognition (voice and visual expression), and proposes a two-mode dual-modal emotion recognition method combined with the attention mechanism of the improved AlexNet network. After a simple preprocessing of the audio signal and the video signal, respectively, the first step is to use the prior knowledge to realize the extraction of audio characteristics. Then, facial expression features are extracted by the improved AlexNet network. Finally, the multimodal attention mechanism is used to fuse facial expression features and audio features, and the improved loss function is used to optimize the modal missing problem, so as to improve the robustness of the model and the performance of emotion recognition. The experimental results show that the concordance coefficient of the proposed model in the two dimensions of arousal and valence (concordance correlation coefficient) were 0.729 and 0.718, respectively, which are superior to several comparative algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• Journal of Sensor Science and Technology
• /
• v.28 no.4
• /
• pp.251-255
• /
• 2019

We propose a two-step lithography process to minimize edge-bead issues caused by thick photoresist (PR) coating. In the conventional PR process, the edge bead can be efficiently removed by applying an edge-bead removal (EBR) process while rotating the silicon wafer at a high speed. However, applying conventional EBR to the production of desired PR mold with unique negative patterns cannot be used because a lower rpm of spin coating and a lower temperature in the soft bake process are required. To overcome this problem, a two-step lithography process was developed in this study and applied to the fabrication of a polydimethylsiloxane (PDMS) film having super-hydrophobic characteristics. Following UV exposure with a first photomask, the exposed part of the silicon wafer was selectively removed by applying a PR developer while rotating at a low rpm. Then, unique PR mold structures were prepared by employing an additional under-exposure process with a second mask, and the mold patterns were transferred to the PDMS. Results showed that the fabricated PDMS film based on the two-step lithography process reduced the height difference from 23% to 5%. In addition, the water contact angle was greatly improved by spraying of hydrophobic nanosilica on the dual-scaled PDMS surface.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.6
• /
• pp.1163-1177
• /
• 2020

The purpose of this study is to figure out the information needed to improve the shape and size suitability of face-applied mask sheets. The study analyzed the shape of the mask sheet from the scanned images of 50 products of 37 domestic brands. In addition, each measurement of 42 mask sheets were compared and analyzed multilaterally with the 3D measurement dimensions of the faces of men and women in their 20s from the 6th SizeKorea data. Analysis on the shapes of mask sheets indicated that domestic commercial mask sheets are mainly made of single or dual sheets, with slits for enhancing fitness to the three-dimensional face. In the dimensional analysis of Korean men, women and mask sheets, most of the lengths of the mask sheets were significantly larger or smaller than the actual faces of men and women. The horizontal length and vertical length of the forehead above the eyes are significantly shorter, thereby requiring adjustments in the dimensions of this area. In order to improve the size suitability of the mask, it is necessary to adjust the dimensions of the problem area according to the research results as well as diversify the dimensions considering the target layer.

• Current Optics and Photonics
• /
• v.5 no.6
• /
• pp.652-659
• /
• 2021

The theoretical analysis and optimization of extrinsic Fabry-Perot interferometer (EFPI) opticalfiber humidity sensors are deeply investigated. For a typical dual-cavity structure composed of an optical fiber and a humidity-sensitive membrane (HSM), the changes in refractive index (RI) and initial length are discussed for polymer materials and porous oxide materials when relative humidity (RH) increases. The typical interference spectrum is simulated at different RH using MATLAB. The spectral change caused by changing HSM RI and initial length are simulated simutineously, showing different influences on humidity response. To deeply investigate the influence on RH sensitivity, the typical response sensitivity curves for different HSM lengths and air-cavity lengths are simulated. The results show that the HSM is the vital factor. Short HSM length can improve the sensitivity, but for HSM RI and length the influences on sensitivity are opposite, because of the opposite spectral-shift trend. Deep discussion and an optimization method are provided to solve this problem. According to analysis, an opaque HSM is helpful to improve sensitivity. Furthermore, if using an opaque HSM, a short air cavity and long HSM length can improve the sensor's sensitivity These results provide deep understanding and some ideas for designing and optimizing highly sensitive EFPI fiber humidity sensors.

• Journal of Ocean Engineering and Technology
• /
• v.36 no.1
• /
• pp.21-31
• /
• 2022

In recent years, various studies have been conducted on oscillating-water-column-type wave energy converters (OWC-WECs) with multiple chambers with the objective of efficiently utilizing the limited space of offshore/onshore structures. In this study, a numerical investigation based on a numerical wave tank was conducted on single, dual, and triple OWC chambers to examine the hydrodynamic performances and the energy conversion characteristics of the multiple water columns. The boundary value problem with the Laplace equation was solved by using a numerical wave tank based on a finite element method. The validity of the current numerical method was confirmed by comparing it with the measured data in the previous experimental research. We undertook a series of numerical simulations and observed that the water column motion of sloshing mode in a single chamber can be changed into the piston motion of different phases in multiple OWC chambers. Therefore, the piston motion in the multiple chambers can generate considerable airflow at a specific resonant frequency. In addition, the division of the OWC chamber results in a reduction of the time-dependent variability of the final output power from the device. As a result, the application of the multiple chambers leads to an increase of the energy conversion performance as well as a decrease of the variability of the wave energy converter.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.80-96
• /
• 2022

Nowadays, artificial intelligence promotes the rapid development of skin cancer detection technology, and the federated skin cancer detection model (FSDM) and dual generative adversarial network model (DGANM) solves the fragmentation and privacy of data to a certain extent. To overcome the problem that the many-objective evolutionary algorithm (MaOEA) cannot guarantee the convergence and diversity of the population when solving the above models, a many-objective evolutionary algorithm based on integrated strategy (MaOEA-IS) is proposed. First, the idea of federated learning is introduced into population mutation, the new parents are generated through sub-populations employs different mating selection operators. Then, the distance between each solution to the ideal point (SID) and the Achievement Scalarizing Function (ASF) value of each solution are considered comprehensively for environment selection, meanwhile, the elimination mechanism is used to carry out the select offspring operation. Eventually, the FSDM and DGANM are solved through MaOEA-IS. The experimental results show that the MaOEA-IS has better convergence and diversity, and it has superior performance in solving the FSDM and DGANM. The proposed MaOEA-IS provides more reasonable solutions scheme for many scholars of skin cancer detection and promotes the progress of intelligent medicine.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.740-753
• /
• 2023

Text recognition in natural scene images is a challenging problem in computer vision. The accurate identification of ship number characters can effectively improve the level of ship traffic management. However, due to the blurring caused by motion and text occlusion, the accuracy of ship number recognition is difficult to meet the actual requirements. To solve these problems, this paper proposes a dual-branch network based on the CRNN identification network. The network couples image restoration and character recognition. The CycleGAN module is used for blur restoration branch, and the Pix2pix module is used for character occlusion branch. The two are coupled to reduce the impact of image blur and occlusion. Input the recovered image into the text recognition branch to improve the recognition accuracy. After a lot of experiments, the model is robust and easy to train. Experiments on CTW datasets and real ship maps illustrate that our method can get more accurate results.

• Transactions of Materials Processing
• /
• v.32 no.3
• /
• pp.107-113
• /
• 2023

The importance of dual-fuel engines has increased for reducing CO₂ emissions. However, the low operating temperature of this engine may induce low-temperature corrosion at combustion parts, which reduces the engine service life. To overcome this problem, NiCr38Al4 alloy was developed for valve spindle, but the cost of this alloy is expensive due to its high Cr content. For reducing the manufacturing cost of valve spindle, in the present work, NiCr38Al4 alloy was welded with Nimonic80A alloy by conducting friction welding. The tensile test results show that the strength of friction-welded specimens follows the properties of the lower-strength parent materials, without severe cracks at the interface. The large shear strain and frictional heat from friction welding not only reduce grain size but also induce solute element diffusion at the interfacial region. Because of the low Cr diffusivity compared with Ti, Cr carbides were not observed in the Nimonic80A matrix, while Ti carbides were distributed in both the Nimonic80A and SNCrW matrices.

• Steel and Composite Structures
• /
• v.51 no.5
• /
• pp.473-485
• /
• 2024

This paper proposes a composite form of fuzzy adaptive control plan based on a robust observer. The fuzzy 2D control gains are regulated by the parameters in the LMIs. Then, control and learning performance indices with weight matrices are constructed as the cost functions, which allows the regulation of the trade-off between the two performance by setting appropriate weight matrices. The design of 2D control gains is equivalent to the LMIs-constrained multi-objective optimization problem under dual performance indices. By using this proposed smart tracking design via fuzzy nonlinear criterion, the data link can be further extended. To evaluate the performance of the controller, the proposed controller was compared with other control technologies. This ensures the execution of the control program used to track position and trajectory in the presence of great model uncertainty and external disturbances. The performance of monitoring and control is verified by quantitative analysis. The goals of this paper are towards access to adequate, safe and affordable housing and basic services, promotion of inclusive and sustainable urbanization and participation, implementation of sustainable and disaster-resilient buildings, sustainable human settlement planning and manage. Therefore, the goal is believed to achieved in the near future by the ongoing development of AI and control theory.