• Journal of Biosystems Engineering
• /
• v.28 no.6
• /
• pp.517-524
• /
• 2003

There have been worldwide research and development efforts to automate various processes of bio-production and those efforts will be expanded with priority given to tasks which require high intensive labor or produce high value-added product and tasks under hostile environment. In the field of bio-production capabilities of the versatility and robustness of automated system have been major bottlenecks along with economical efficiency. This paper introduces a new concept of automation based on tole-operation, which can provide solutions to overcome inherent difficulties in automating bio-production processes. Operator(farmer), computer, and automatic machinery share their roles utilizing their maximum merits to accomplish given tasks successfully. Among processes of greenhouse watermelon cultivation tasks such as pruning, watering, pesticide application, and harvest with loading were chosen based on the required labor intensiveness and functional similarities to realize the proposed concept. The developed system was composed of 5 major hardware modules such as wireless remote monitoring and task control module, wireless remote image acquisition and data transmission module, gantry system equipped with 4 d.o.f. Cartesian type robotic manipulator, exchangeable modular type end-effectors, and guided watermelon loading and storage module. The system was operated through the graphic user interface using touch screen monitor and wireless data communication among operator, computer, and machine. The proposed system showed practical and feasible way of automation in the field of volatile bio-production process.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.4
• /
• pp.1638-1643
• /
• 2018

Multi-layer ceramic capacitors as decoupling capacitor were fabricated by dielectric composition with a high dielectric constant. The fabricated decoupling capacitors were embedded in the PCB of the 10G RF transceiver module and evaluated for the characteristics of electrical noise by the level of AC input voltage. In order to further improve the electrical properties of the $BaTiO_3$ based composite, glass frit, MgO, $Y_2O_3$, $Mn_3O$, $V_2O_5$, $BaCO_3$, $SiO_2$, and $Al_2O_3$ were used as additives. The electrical properties of the composites were determined by various amounts of additives and optimum sintering temperature. As a result of the optimized composite, it was possible to obtain a density of $5.77g/cm^3$, a dielectric constant of 1994, and an insulation resistance of $2.91{\times}10^{12}{\Omega}$ at an additive content of 5wt% and a sintering temperature of $1250^{\circ}C$. After forming a $2.5{\mu}m$ green sheet using the doctor blade method, a total of 77 layers were laminated and sintered at $1180^{\circ}C$. A decoupling capacitor with a size of $0.6mm(W){\times}0.3mm(L){\times}0.3mm(T)$ (width, length and thickness, respectively) and a capacitance of 100 nF was embedded using a PCB process for the 10G RF Transceiver modules. In the range of AC input voltage 400mmV @ 500kHz to 2200mV @ 900kHz, the embedded 10G RF Transceiver modules evaluated that it has better electrical performance than the non-embedded modules.

• Journal of the Korea Convergence Society
• /
• v.10 no.1
• /
• pp.103-113
• /
• 2019

License plate recognition camera is dedicated device designed for acquiring images of the target vehicle for recognizing letters and numbers in a license plate. Mostly, it is used as a part of the system combined with server and image analysis module rather than as a single use. However, building a system for vehicle license plate recognition is costly because it is required to construct a facility with a server providing the management and analysis of the captured images and an image analysis module providing the extraction of numbers and characters and recognition of the vehicle's plate. In this study, we would like to develop an embedded type convergent camera (Edge Base) which can expand the function of the camera to not only the license plate recognition but also the security CCTV function together and to perform two functions within the camera. This embedded type convergence camera equipped with a high resolution 4K IP camera for clear image acquisition and fast data transmission extracted license plate area by applying YOLO, a deep learning software for multi object recognition based on open source neural network algorithm and detected number and characters of the plate and verified the detection accuracy and recognition accuracy and confirmed that this camera can perform CCTV security function and vehicle number plate recognition function successfully.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.359-366
• /
• 2022

In this paper, we present the Korean menu-ordering Sentence Text-to-Speech (TTS) system using conformer-based FastSpeech2. Conformer is the convolution-augmented transformer, which was originally proposed in Speech Recognition. Combining two different structures, the Conformer extracts better local and global features. It comprises two half Feed Forward module at the front and the end, sandwiching the Multi-Head Self-Attention module and Convolution module. We introduce the Conformer in Korean TTS, as we know it works well in Korean Speech Recognition. For comparison between transformer-based TTS model and Conformer-based one, we train FastSpeech2 and Conformer-based FastSpeech2. We collected a phoneme-balanced data set and used this for training our models. This corpus comprises not only general conversation, but also menu-ordering conversation consisting mainly of loanwords. This data set is the solution to the current Korean TTS model's degradation in loanwords. As a result of generating a synthesized sound using ParallelWave Gan, the Conformer-based FastSpeech2 achieved superior performance of MOS 4.04. We confirm that the model performance improved when the same structure was changed from transformer to Conformer in the Korean TTS.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.1-15
• /
• 2024

The construction of smart communities is a new method and important measure to ensure the security of residential areas. In order to solve the problem of low accuracy in face recognition caused by distorting facial features due to monitoring camera angles and other external factors, this paper proposes the following optimization strategies in designing a face recognition network: firstly, a global graph convolution module is designed to encode facial features as graph nodes, and a multi-scale feature enhancement residual module is designed to extract facial keypoint features in conjunction with the global graph convolution module. Secondly, after obtaining facial keypoints, they are constructed as a directed graph structure, and graph attention mechanisms are used to enhance the representation power of graph features. Finally, tensor computations are performed on the graph features of two faces, and the aggregated features are extracted and discriminated by a fully connected layer to determine whether the individuals' identities are the same. Through various experimental tests, the network designed in this paper achieves an AUC index of 85.65% for facial keypoint localization on the 300W public dataset and 88.92% on a self-built dataset. In terms of face recognition accuracy, the proposed network achieves an accuracy of 83.41% on the IBUG public dataset and 96.74% on a self-built dataset. Experimental results demonstrate that the network designed in this paper exhibits high detection and recognition accuracy for faces in surveillance videos.

• Membrane Journal
• /
• v.18 no.4
• /
• pp.325-335
• /
• 2008

In this study, we used multi-channels ceramic membrane having larger permeate volume per unit time rather than tubular membrane. The hybrid process for advanced drinking water treatment was composed of granular activated carbons (GAC) packing between module inside and outside of multi-channels microfiltration membrane. Instead of natural organic matters (NOM) and fine inorganic particles in natural water source, modified solution was prepared with humic acid and kaolin. Kaolin concentration was fixed at 30mg/L and humic acid was changed as $2{\sim}10\;mg/L$ to inspect effect of organic matters. As a result, both resistance of membrane fouling ($R_f$) and permeate flux (J) were highly influenced by concentration of humic acid. Also, in result of water-back-flushing period (FT) effect, the shorter FT was the more effective to reduce membrane fouling and to enhance permeate flux because of frequent water-back-flushing. However, the optimal FT condition was 8 min when operating costs were considered. Then, the hybrid process using multi-channels ceramic membrane and GAC was applied to lake water treatment. As a result, average treatment efficiencies in our experiment using the hybrid process were 98.02% for turbidity, 75.64% for $UV_{254}$ absorbance, 7.18% for TDS and 84.73% for $COD_{Mn}$.

• Journal of Radiation Protection and Research
• /
• v.21 no.4
• /
• pp.313-327
• /
• 1996

As an at-reactor(AR) storage method o( spent fuel, there are horizontal concrete module type, metal storage cask type, concrete storage cask type, dual purpose (transportation and storage) cask type and multi-purpose (transportation, storage and disposal) cask type. All other types except multi-purpose one have been already used for AR dry storage of spent fuels after obtaining operation license in various foreign countries. Also the development of multi-purpose type has been continued for operation license. In America, Japan, Germany, Canada, Spain, Switzerland, and Czech Republic, etc., AR dry storage facilities are under operation or on propulsion, and spent fuels are transported to interim storage facility or reprocessing plant after dry storage at reactor temporarily. At Wolsung site, in case of Korea, concrete silo type has already been introduced, and it is believed to be inevitable to store spent fuels at reactor temporarily, considering the reality that storage capacity of spent fuel is approaching to the limit in some nuclear power plants. In this report, the system characteristics, design requirements, technical standards and status of AR storage system, which is suitable for domestic site such as Kori, have been studied. In most cases, the licensed period of storage cask is limited up to 20 years and the integrity of material and maintenance of leaktightness are required during the whole service life.

• Membrane Journal
• /
• v.15 no.4
• /
• pp.310-319
• /
• 2005

This paper describes the preliminary study on the development of multi-stage membrane demonstration plant for removal of carbon dioxide from flue gas stream being emitted from LNG boiler in thermal power generation plant. The prerequisite requirement is to design and develop the membrane process producing a $99\%\;CO_2$ with $90\%$ recovery from LNG flue gas of 1,000 $Nm^3$/day. Asymmetric polyethersulfone hollow fiber membranes and membrane modules developed in this laboratory[1] were used in this study. Using the permeation data for the hollow fiber membranes, modelling on the membrane module and multi-stage membrane process was done to meet the requirement condition of the process design. The effects of the operating pressure of feed and permeate side and feed concentration on $CO_2$ purity and recovery were investigated experimentally with the developed hollow fiber modules. These experimental results matched well with theoretical modelling results.

• Clean Technology
• /
• v.25 no.3
• /
• pp.206-222
• /
• 2019

Recently, various multiphase flows have been developed, and among them some models have been commercialized. However, most of them have been developed based on a pressure-based approach; therefore, various numerical difficulties were involved inherently. Accordingly, in order to overcome these numerical difficulties, a multiphase flow model, MultiPhaSe flow (MPS), following a fractional-flow based approach was developed. In this study, by combining a contaminant transport module describing an enhanced dissolution effect of a surfactant with MPS, a MultiPhaSe flow and TranSport (MPSTS) model was developed. The developed model was verified using the analytical solution of Clement. The MPSTS model can simulate the process of surfactant enhanced aquifer remediation including interphase mass transfer and contaminant transport in multiphase flow by using the coupled particle tracking method and Lagrangian-Eulerian method. In this study, a surfactant was used in a non aqueous phase liquid (NAPL) contaminated area, and the effect of hydro-geological heterogeneity in the layered media on remediation efficiency was studied using the developed model. According to the numerical simulation, when hydraulic conductivity in a lower layer is 10 times, 20 times, and 50 times larger than that in an upper layer, the concentration of dissolved diesel in the lower layer is much higher than that in the upper layer because the surfactant moves faster along the lower layer owing to preferential flow; thus, the surfactant enhances dissolution of residual non aqueous phase liquid in the lower layer.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.675-681
• /
• 2021

With the recent growth of the AI speaker market, the demand for speech synthesis technology that enables natural conversation with users is increasing. Therefore, there is a need for a multi-speaker speech synthesis system that can generate voices of various tones. In order to synthesize natural speech, it is required to train with a large-capacity. high-quality speech DB. However, it is very difficult in terms of recording time and cost to collect a high-quality, large-capacity speech database uttered by many speakers. Therefore, it is necessary to train the speech synthesis system using the speech DB of a very large number of speakers with a small amount of training data for each speaker, and a technique for naturally expressing the tone and rhyme of multiple speakers is required. In this paper, we propose a technology for constructing a speaker encoder by applying the deep learning-based x-vector technique used in speaker recognition technology, and synthesizing a new speaker's tone with a small amount of data through the speaker encoder. In the multi-speaker speech synthesis system, the module for synthesizing mel-spectrogram from input text is composed of Tacotron2, and the vocoder generating synthesized speech consists of WaveNet with mixture of logistic distributions applied. The x-vector extracted from the trained speaker embedding neural networks is added to Tacotron2 as an input to express the desired speaker's tone.