• 한국정보통신학회논문지
• /
• 제23권3호
• /
• pp.276-281
• /
• 2019

푸드 프린터는 반드시 식품의약품안전처의 허가를 받은 식용 잉크 카트리지를 사용해야한다. 잉크 카트리지의 정품 여부를 판독하기 위해 2D 바코드를 사용하는데 색소가 열압력에 의해 발산하여 인쇄가 되기 때문에 바코드에 오염이 발생한다. 본 논문에서는 라떼 아트 프린터에서 식용 색소 분진에 의한 정품 인증 바코드의 오염 문제를 해결하고자 다양한 모폴로지 연산에 기반한 전처리(pre-processing) 알고리즘을 제안하였다. 오염된 바코드 이미지들을 QR코드 리더기로 인식시키기 전에 본 알고리즘을 적용하면 기존의 리더기 대비 인식이 가능한 오염도가 25%에서 40%로 증가함을 알 수 있었으며 45%의 오염도에서도 50%의 확률로 인식이 되는 것을 확인하였다.

• 농업생명과학연구
• /
• 제53권3호
• /
• pp.147-157
• /
• 2019

In this study, we tried to find out the most appropriate pre-processing method and to verify the feasibility of developing a low-price sensing system for predicting the hardy kiwis sugar content based on VNIRS and subsequent spectral analysis. A total of 495 hardy kiwi samples were collected from three farms in Muju, Jeollabukdo, South Korea. The samples were scanned with a spectrophotometer in the range of 730-2300 nm with 1 nm spectral sampling interval. The measured data were arbitrarily separated into calibration and validation data for sugar content prediction. Partial least squares (PLS) regression was performed using various combinations of pre-processing methods. When the latent variable (LV) was 8 with the pre-processing combination of standard normal variate (SNV) and orthogonal signal correction (OSC), the highest R2 values of calibration and validation were 0.78 and 0.84, respectively. The possibility of predicting the sugar content of hardy kiwi was also examined at spectral sampling intervals of 6 and 10 nm in the narrower spectral range from 730 nm to 1200 nm for a low-price optical sensing system. The prediction performance had promising results with R2 values of 0.84 and 0.80 for 6 and 10 nm, respectively. Future studies will aim to develop a low-price optical sensing system with a combination of optical components such as photodiodes, light-emitting diodes (LEDs) and/or lamps, and to locate a more reliable prediction model by including meteorological data, soil data, and different varieties of hardy kiwi plants.

• 한국IT서비스학회지
• /
• 제19권5호
• /
• pp.83-91
• /
• 2020

Language Models such as BERT has been an important factor of deep learning-based natural language processing. Pre-training the transformer-based language models would be computationally expensive since they are consist of deep and broad architecture and layers using an attention mechanism and also require huge amount of data to train. Hence, it became mandatory to do fine-tuning large pre-trained language models which are trained by Google or some companies can afford the resources and cost. There are various techniques for fine tuning the language models and this paper examines three techniques, which are data augmentation, tuning the hyper paramters and partly re-constructing the neural networks. For data augmentation, we use no-answer augmentation and back-translation method. Also, some useful combinations of hyper parameters are observed by conducting a number of experiments. Finally, we have GRU, LSTM networks to boost our model performance with adding those networks to BERT pre-trained model. We do fine-tuning the pre-trained korean-based language model through the methods mentioned above and push the F1 score from baseline up to 89.66. Moreover, some failure attempts give us important lessons and tell us the further direction in a good way.

• Journal of Ginseng Research
• /
• 제35권4호
• /
• pp.497-503
• /
• 2011

In order to enhance bioactive functionalities of ginseng, an acid impregnation processing was applied as a pre-treatment in producing red ginseng. Acid impregnation studies were conducted, and acids (ascorbic, malic, and citric acid) were selected. The optimal concentration of each acid was investigated in this study in terms of ginsenoside contents. The most concerned ginsenoside, $Rg_3$ was increased by ascorbic, malic, and citric acid pre-treated red ginseng up to 1 M acid concentration. In the case of ascorbic acid pre-treated red ginseng, $Rg_2$ concentration was increased depending on acid concentrations. Citric acid pre-treatment enhanced $Rg_2$, $Rg_3$, and $Rh_1+Rh_2$ formation in red ginseng. Therefore, ginsenoside patterns in red ginseng could be changed by acid impregnation pre-treatment depending on acid concentration and acid types. This research is expected to contribute to the development of the ginseng industry via new red ginseng products with selective and intensified functionality.

• International journal of advanced smart convergence
• /
• 제5권2호
• /
• pp.18-23
• /
• 2016

Cell walls of microalgae consist of a polysaccharide and glycoprotein matrix providing the cells with a formidable defense against its environment. Anaerobic digestion (AD) of microalgae is primarily inhibited by the chemical composition of their cell walls containing biopolymers able to resist bacterial degradation. Adoption of pre-treatments such as thermal, thermal hydrolysis, ultrasound and enzymatic hydrolysis have the potential to remove these inhibitory compounds and enhance biogas yields by degrading the cell wall, and releasing the intracellular algogenic organic matter (AOM). This paper preproposal stage investigated the effect of different pre-treatments on microalgae cell wall, and their impact on the quantity of soluble biomass released in the media and thus on the digestion process yields. This Paper present optimum approach to degradation of the cell wall by ultra-sonication with practical design specification parameter for ultrasound based pretreatment system. As a result of this paper presents, a microalgae system in a wastewater treatment flowsheet for residual nutrient uptake can be justified by processing the waste biomass for energy recovery. As a conclusion on this result, Low energy harvesting technologies and pre-treatment of the algal biomass are required to improve the overall energy balance of this integrated system.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 춘계종합학술대회
• /
• pp.405-408
• /
• 2005

본 논문에서는 복원이 가능한 웨이블릿 변환을 사용한 통합된 손실 압축 방법을 제안한다. 제안한 알고리즘은 우선 원 영상에 선 양자화 과정을 진행하여 그레이 레벨의 수가 원 영상과 일치한 영상을 구성한다. 양자화 된 원 영상에 웨이블릿 변환 필터를 적용하여 대역분할을 한다. 가장 낮은 대역의 부호화는 재구성된 영상의 전체화질에 가장 큰 영향을 미치는 것을 고려하여 예측기를 사용한 허프만 부호화를 이용한다. 제안된 알고리즘에 의해 재구성된 영상들은 JPEG 및 선양자화 없이 원 영상의 웨이블릿 계수들을 부호화 하는 방법에 비해 높은 PSNR을 보였다. 선양자화 과정을 사용 함으로서 최대에러를 조절 할 수 있으며 대규모 영상압축에 유용할 것으로 기대된다.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2008년도 춘계학술대회 논문집
• /
• pp.439-443
• /
• 2008

We investigate the mechanical behavior of a pre-heat treated steel of ESW95, which is being used for automotive parts including tie-rods to save manufacturing cost and enhance product quality. SCM435 is also investigated to reveal the characteristics of the pre-heat treated steel tested. AFDEX/MAT is used to extract the true stress-strain curve over the large strain with higher accuracy. It has been found that ESW95 has very week strain-hardening behavior which can be negligible compared with SCM435 and that the initial yield strength is quite high and the toughness of ESW95 reaches nearly 75% of SCM435. ESW95 is characterized by the weak strain-hardening behavior and high yield strength that can be lead to minimization of post-processing including heat treatment and straightening. ESW95 and SCM435 are also compared by applying them to ball-stud forging by computer simulation. It is expected that a great deal of change may take place in production as well as in service if the pre-heated steels are adopted.

• 소성∙가공
• /
• 제29권6호
• /
• pp.362-369
• /
• 2020

In this study, elastoplastic finite element analysis with multi-body treatment was used to elucidate the mechanical phenomena occurring from pre-stressing of die-system. A finite element analysis model with detailed conditions is proposed. The effects of die pre-stressing slope on the circumferential components of the pre-stressed die inserts were evaluated. The role of tight fitting between the supporter and die case was also emphasized because it has a significant effect on the undesirable change in the target slope of machined inner surface of the die case around the die insert. The two mechanical problems include the one between die-insert and die case and the other between supporter and die case, and their correlation is minimized to establish the optimum design in the die structural design stage because it cannot be quantitatively controlled owing to various factors affecting the die structural behavior during die pre-stressing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2754-2767
• /
• 2019

Cloud computing is widely used in information spreading and processing, which has provided a easy and quick way for users to access data and retrieve service. Generally, in order to prevent the leakage of the information, the data in cloud is transferred in the encrypted form. As one of the traditional security technologies, access control is an important part for cloud security. However, the current access control schemes are not suitable for cloud, thus, it is a vital problem to design an access control scheme which should take account of complex factors to satisfy the various requirements for cipher text protection. We present a novel access control scheme based on proxy re-encryption(PRE) technology (PreBAC) for cipher text. It will suitable for the protection of data confidently and information privacy. At first, We will give the motivations and related works, and then specify system model for our scheme. Secondly, the algorithms are given and security of our scheme is proved. Finally, the comparisons between other schemes are made to show the advantages of PreBAC.

• 한국군사과학기술학회지
• /
• 제25권4호
• /
• pp.347-354
• /
• 2022

The synthetic aperture radar(SAR) is an equipment that can acquire images in all weathers day and night based on radar signals. The on-board processor of satellite SAR generates transmission signal by digital signal processing, converts it into an analog signal and transmits to antenna. Until the transmission signal generated by on-board processor is output, the signal passes the transmission cables and analog devices. At this time, these hardware distort the signal and makes SAR performance worse. To improve the performance, pre-distortion technique is used. But, general pre-distortion using taylor series is not sufficient to compensate for the distortion. This paper suggests transmit signal design method with improved pre-distortion. This paper uses envelop sampling method and interpolation filter for frequency domain compensation. The proposed method accurately compensates the hardware distortion and reduces resource usage of FPGA. To analyze proposed method's performance, IRF characteristics are compared when the proposed method applies to signal with errors.