• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.209-214
• /
• 2021

Panoptic segmentation, which is now widely used in computer vision such as medical image analysis, and autonomous driving, helps understanding an image with holistic view. It identifies each pixel by assigning a unique class ID, and an instance ID. Specifically, it can classify 'thing' from 'stuff', and provide pixel-wise results of semantic prediction and object detection. As a result, it can solve both semantic segmentation and instance segmentation tasks through a unified single model, producing two different contexts for two segmentation tasks. Semantic segmentation task focuses on how to obtain multi-scale features from large receptive field, without losing low-level features. On the other hand, instance segmentation task focuses on how to separate 'thing' from 'stuff' and how to produce the representation of detected objects. With the advances of both segmentation techniques, several panoptic segmentation models have been proposed. Many researchers try to solve discrepancy problems between results of two segmentation branches that can be caused on the boundary of the object. In this survey paper, we will introduce the concept of panoptic segmentation, categorize the existing method into two representative methods and explain how it is operated on two methods: top-down method and bottom-up method. Then, we will analyze the performance of various methods with experimental results.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.67.1-67.1
• /
• 2019

We present 2-dimensional continuum radiative transfer modeling for EC53. EC 53 is a Class I YSO, which was brightened at $850{\mu}m$ by a factor of 1.5. This luminosity variation was revealed by the JCMT Transient Survey. The increase in brightness is likely related to the enhanced accretion. We aim to investigate how much increase of protostellar luminosity causes the observed brightness increase at $850{\mu}m$. Thus we modeled the SED of EC 53 both in the quiescence and (small scale) outburst phases, with and without the external heating from the interstellar radiation field (ISRF). We found that the internal protostellar luminosity should increase more to fit the observed flux enhancement if the ISRF is considered in the model.

• Steel and Composite Structures
• /
• v.39 no.4
• /
• pp.353-366
• /
• 2021

Cored moment resisting stub column (CMSC) was previously developed by the features of adopting a core segment which remains mostly elastic and reduced column section (RCS) details around the ends to from a stable hysteretic behavior with large post-yield stiffness and considerable ductility. Several full-scale CMSC components with various length proportions of the RCSs with respect to overall lengths have been experimentally investigated through both far-field and near-fault cyclic loadings followed by fatigue tests. Test results verified that the proposed CMSC provided very ductile hysteretic responses with no strength degradation even beyond the occurrence of the local buckling at the side-segments. The effect of RCS lengths on the seismic performance of the CMSC was verified to relate with the levels of the deformation concentration at the member ends, the local buckling behavior and overall ductility. Estimation equations were established to notionally calculate the first-yield and ultimate strengths of the CMSC and validated by the measured responses. A numerical model of the CMSC was developed to accurately capture the hysteretic performance of the specimens, and was adopted to clarify the effect of the surrounding frame and to perform a parametric study to develop the estimation of the elastic stiffness.

• 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.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.5
• /
• pp.261-272
• /
• 2022

Agriculture and the rural sector play a crucial part in Vietnam's socio-economic growth. The study's goal is to see how technology transfer from young intellectual research activities affects the economic evolution of Vietnam's agriculture and rural sector in the 4.0 technology era. The research has used a quantitative method through analysis of linear structural model SEM, with a survey scale including 480 samples that are managers in departments and branches in agriculture and rural sector in the provinces in Vietnam. Research results show that technology transfer from research activities of the young intellectual has a direct and positive impact on economic development in agriculture and rural sector. This level of impact will increase with the participation of the intermediary factors such as awareness of managers, trust, and mechanisms in the mobilization and use of resources. These results contribute to both theoretical and practical aspects when proving the impact of technology transfer from the research activity of the young intellectual to the economic development in the field of agriculture and rural sector in the 4.0 era and the mediating role of awareness of managers, trust and mechanisms in the mobilization and use of resources.

• Journal of the Korean Chemical Society
• /
• v.67 no.2
• /
• pp.89-98
• /
• 2023

The cell membrane, also known as the biological membrane, surrounds every living cell. The main components of cell membranes are lipids and therefore called as lipid membranes. These membranes are mainly made up of a two-dimensional lipid bilayer along with integral and peripheral proteins. The complex nature of lipid membranes makes it difficult to study and hence artificial lipid membranes are prepared which mimic the original lipid membranes. These artificial lipid membranes are prepared from phospholipid vesicles (liposomes). The liposomes are formed when self-forming phospholipid bilayer comes in contact with water. Liposomes can be unilamellar or multilamellar vesicles which comprises of phospholipids that can be produced naturally or synthetically. The phospholipids are non-toxic, biodegradable and are readily produced on a large scale. These liposomes are mostly used in the drug delivery systems. This paper offers comprehensive literature with insights on developing basic understanding of lipid membranes from its structure, organization, and phase behavior to its potential use in biomedical applications. The progress in the field of artificial membrane models considering methods of preparation of liposomes for mimicking lipid membranes, interactions between the lipid membranes, and characterizing techniques such as UV-visible, FTIR, Calorimetry and X-ray diffraction are explained in a concise manner.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.569-574
• /
• 2023

For maintenance of concrete structures, it is necessary to identify and maintain various defects. With the current method, there are problems with efficiency, safety, and reliability when inspecting large-scale social infrastructure, so it is necessary to introduce a new inspection method. Recently, with the development of deep learning technology for images, concrete defect classification research is being actively conducted. However, studies on contamination and spalling other than cracks are limited. In this study, a variety of concrete defect type classification models were developed through transfer learning on a pre-learned deep learning model, factors that reduce accuracy were derived, and future development directions were presented. This is expected to be highly utilized in the field of concrete maintenance in the future.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.64-72
• /
• 2024

In recent times cyber attackers can use Artificial Intelligence (AI) to boost the sophistication and scope of attacks. On the defense side, AI is used to enhance defense plans, to boost the robustness, flexibility, and efficiency of defense systems, which means adapting to environmental changes to reduce impacts. With increased developments in the field of information and communication technologies, various exploits occur as a danger sign to cyber security and these exploitations are changing rapidly. Cyber criminals use new, sophisticated tactics to boost their attack speed and size. Consequently, there is a need for more flexible, adaptable and strong cyber defense systems that can identify a wide range of threats in real-time. In recent years, the adoption of AI approaches has increased and maintained a vital role in the detection and prevention of cyber threats. In this paper, an Ensemble Deep Restricted Boltzmann Machine (EDRBM) is developed for the classification of cybersecurity threats in case of a large-scale network environment. The EDRBM acts as a classification model that enables the classification of malicious flowsets from the largescale network. The simulation is conducted to test the efficacy of the proposed EDRBM under various malware attacks. The simulation results show that the proposed method achieves higher classification rate in classifying the malware in the flowsets i.e., malicious flowsets than other methods.

• Current Optics and Photonics
• /
• v.8 no.5
• /
• pp.463-471
• /
• 2024

Multimode fibers (MMFs) possess high information throughput and small core diameter, making them highly promising for applications such as endoscopy and communication. However, modal dispersion hinders the direct use of MMFs for image transmission. By training neural networks on time-series waveforms collected from MMFs it is possible to reconstruct images, transforming blurred speckle patterns into recognizable images. This paper proposes a fully convolutional neural-network model, MSMDFNet, for image restoration in MMFs. The network employs an encoder-decoder architecture, integrating multiscale convolutional modules in the decoding layers to enhance the receptive field for feature extraction. Additionally, attention mechanisms are incorporated from both spatial and channel dimensions, to improve the network's feature-perception capabilities. The algorithm demonstrates excellent performance on MNIST and Fashion-MNIST datasets collected through MMFs, showing significant improvements in various metrics such as SSIM.

• KIEAE Journal
• /
• v.12 no.4
• /
• pp.77-82
• /
• 2012

This study conducted the experiment of reduction of Volatile Organic Compounds(VOCs) and Formaldehyde concentration by Native plants, Fatsia japonica and Ardisia pusilla. The two plants are advantageous in that they are highly available as they grow wild, and being easy to get. Fatsia japonica is a plant of its wide and large leaf diverged 7 or 8 parts, which is thought to have a high effect of air purification. Ardisia pusilla has a smaller leaf than Fatsia japonica, which is characterized by more leaves and beautiful. Field measurements were performed using Fatsia japonica and Ardisia pusilla which were verified as air-purifying plants in Korea. The effect of reducing the concentration of VOCs and Formaldehyde by plant studied in a full scale mock-up model. The dimensions of the two models were equal. The concentration of Benzene, Toluene, Ethylbenzene, Xylene, Stylene, Formaldehyde were monitored, since they were known as most toxic materials. The concentration of VOCs was monitored three hours after the plants were placed and three days after the plants were placed. Field measurements were performed in models where the plants were placed and were not. As a result, they had all an effect of reducing pollution. In all cases of experiment of planting and growing volume, the more planting volume, the more excellent the effect. Toluene was more effective in Fatsia japonica and Ardisia pusilla planted, Formaldehyde was more effective in Fatsia japonica planted respectively. In planting and growing and placing experiment, the placement at sunny spot was more effective than that at scattered growing. When Fatsia japonica was placed at sunny spot, the reduction effect of Formaldehyde was the most excellent, and when Ardisia pusilla was placed at sunny spot, the reduction effect of Toluene was the most effective.