• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.704-707
• /
• 2021

Pigs' aggressive behavior represents one of the common issues that occur inside pigpens and which harm pigs' health and welfare, resulting in a financial burden to farmers. Continuously monitoring several pigs for 24 hours to identify those behaviors manually is a very difficult task for pig caretakers. In this study, we propose a lightweight video-based approach for monitoring pigs' aggressive behavior that can be implemented even in small-scale farms. The proposed system receives sequences of frames extracted from an RGB video stream containing pigs and uses MnasNet with a DM value of 0.5 to extract image features from pigs' ROI identified by predefined annotations. These extracted features are then forwarded to a lightweight LSTM to learn temporal features and perform behavior recognition. The experimental results show that our proposed model achieved 0.92 in recall and F1-score with an execution time of 118.16 ms/sequence.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.37.1-37.1
• /
• 2020

Cosmic-ray protons (CRp) are efficiently produced at starburst galaxies (SBGs), where the star formation rate (SFR) rate is high. In this talk, we present estimates of gamma-ray and neutrino emissions from nearby SBGs, M82, NGC253, and Arp220. Inside the starburst nucleus (SBN), CRp are accelerated at supernova remnant (SNR) shocks as well as at stellar wind (SW) termination shocks, and their transport is governed by the advection due to starburst-driven wind and diffusion mediated by turbulence. We here model the momentum distributions of SNR and SW-produced CRp with single or a double power-law forms. We also employ two different diffusion models, where CRp are resonantly scattered off large-scale turbulence in SBN or self-excited waves driven by CR streaming instability. We then calculate gamma-ray/neutrino fluxes. The observed gamma-ray fluxes by Fermi-LAT, Veritas, and H.E.S.S are well reproduced with double power-law distribution for SNR-produced CRp and the CRp diffusion by self-excited turbulence. The estimated neutrino fluxes are <~10-3 of the atmospheric neutrino flux in the energy range of Eneutrino <~100 GeV and <~10-1 of the IceCube point source sensitivity in the energy range of Eneutrino >~60 TeV.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.70.1-70.1
• /
• 2020

A type IIb supernova (SN IIb) is the result of core-collapse of a massive star which lost most of its hydrogen-rich envelope during its evolution. The pre-SN progenitor properties, such as the total radius and the mass of the hydrogen-rich envelope, can widely vary due to the mass-loss history of the progenitors. Optical light curves of SNe IIb are dominated by energy released by the hydrogen recombination and the radioactive decay of 56Ni in the early and late epochs respectively. This may result in distinctive double peaked light curves like the one observed in SN 1993J. The first peak, caused by the hydrogen recombination, can be modelled with numerical simulations providing information on the pre-SN progenitor properties. We compare two radiation-hydrodynamics codes, STELLA and SNEC, that are frequently used in SNe modelling, and investigate the effect of opacity treatment on the temporal evolution of the color temperature of SNe and eventually on the optical light curves. We find that with a proper treatment of the scattering opacity, SNe IIb models exploded from the progenitor models evolved with latest stellar evolution model hardly match the observational data. We also discuss the smaller scale features found in the models during hydrogen recombination phase.

• Smart Structures and Systems
• /
• v.31 no.1
• /
• pp.45-56
• /
• 2023

Vibration-based structural health monitoring is used to ensure the safety of structures by installing sensors in structures. The peak picking method, one of the applications of vibration-based structural health monitoring, is a method that analyze the dynamic characteristics of a structure using the peaks of the frequency response function. However, the results may vary depending on the person predicting the peak point; further, the method does not predict the exact peak point in the presence of noise. To overcome the limitations of the existing peak picking methods, this study proposes a new method to automate the modal analysis process by utilizing long short-term memory, a type of recurrent neural network. The method proposed in this study uses the time series data of the frequency response function directly as the input of the LSTM network. In addition, the proposed method improved the accuracy by using the phase as well as amplitude information of the frequency response function. Simulation experiments and lab-scale model experiments are performed to verify the performance of the LSTM network developed in this study. The result reported a modal assurance criterion of 0.8107, and it is expected that the dynamic characteristics of a civil structure can be predicted with high accuracy using data without experts.

• Earthquakes and Structures
• /
• v.24 no.2
• /
• pp.127-140
• /
• 2023

The vibration of microtubule in human cells is the source of electrical field around it and inside cell structure. The induction of electrical field is a direct result of the existence of dipoles on the surface of the microtubules. Measuring the electrical fields could be performed using nano-scale sensors and the data could be transformed to other computers using internet of things (IoT) technology. Processing these data is feasible by artificial intelligence-based methods. However, the first step in analyzing the vibrational behavior is to study the mechanics of microtubules. In this regard, the vibrational behavior of the microtubules is investigated in the present study. A shell model is utilized to represent the microtubules' structure. The displacement field is assumed to obey first order shear deformation theory and classical theory of elasticity for anisotropic homogenous materials is utilized. The governing equations obtained by Hamilton's principle are further solved using analytical method engaging Navier's solution procedure. The results of the analytical solution are used to train, validate and test of the deep neural network. The results of the present study are validated by comparing to other results in the literature. The results indicate that several geometrical and material factors affect the vibrational behavior of microtubules.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1671-1686
• /
• 2022

Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.207-209
• /
• 2022

In the IoT environment, it is possible to collect life pattern data by recognizing human physical activity from smart devices. In this paper, the proposed model consists of a prediction stage and a recommendation stage. The prediction stage predicts the scale of anxiety and depression by using logistic regression and k-nearest neighbor algorithm through machine learning on the dataset collected from life pattern data. In the recommendation step, if the symptoms of anxiety and depression are classified, the principal component analysis algorithm is applied to recommend food and light exercise that can improve them. It is expected that the proposed anxiety/depression prediction and food/exercise recommendations will have a ripple effect on improving the quality of life of individuals.

• Geomechanics and Engineering
• /
• v.31 no.3
• /
• pp.305-318
• /
• 2022

Permeable reactive barriers used for groundwater treatment require proper estimation of the reactive material behavior regarding the emplacement method. This study evaluates the dry emplacement of zeolite (clinoptilolite) to be used as a reactive material in the barrier by carrying out several geotechnical laboratory tests. Dry zeolite samples, exhibited higher wetting-induced compression strains at the higher vertical stresses, up to 12% at 400 kN/m². The swelling potential was observed to be limited with a 3.5 swell index and less than 1% free swelling strain. Direct shear tests revealed that inundation reduces the shear strength of a dry zeolite column by a maximum of 10%. Falling head permeability tests indicate decreasing permeability values with increasing the vertical effective stress. Regarding self-loading and inundation, the porosity along the zeolite column was calculated using a proposed 1D numerical model to predict the permeability with depth considering the laboratory tests. The calculated discharge efficiency was significantly decreased with depth and less than 2% relative to the top for barrier depths deeper than 20 m. Finally, the importance of directional dependence in the permeability of the zeolite medium for calibrating 2D finite element flow analysis was highlighted by bench-scale tests performed under 2D flow conditions.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.32-36
• /
• 2015

This study explores the issue of program management consortia involving multinational participants. The aim of this research was to leverage advantages in program management (PM) skills and PM model improvement in product line construction in mega scale construction programs, typically funded by public funds. Such ventures involve multinational parties using dedicated partnering based on a program management consortium (PMC) to reduce confrontation between parties in complex circumstances, allowing an open and non-adversarial approach to project management. This research also seeks to implement an ongoing feedback program of best practices and lessons learned to minimize the repetition of mistakes and to reduce costs in sequenced construction. Recently, the Korean government has planned to undertake three large new projects: the Korean Peninsula major river maintenance, the reclamation of Se-Mangum, and the Science/Business City. This paper starts by providing a framework for the cost-reduction strategy for the United States Forces Korea (USFK) Relocation Program, which will be funded with public funds and a private fund investment (PFI) that combines programs executed by two governments as owners and multinational stakeholders, joined in the PMC. The establishment of project-oriented consortia is an innovative and non-adversarial approach to massive international construction projects. Such projects have used various tools effectively and skillfully. This experience may offer an opportunity to practice new and advanced program management delivery methods, and it is expected that Korea will gain a competitive advantage in the international construction market.