• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.374-376
• /
• 2021

임상에서 암 관련 질병의 확진을 위해 영상장비를 이용한 기초 진단 이후 추가적인 방법으로 생체검사 등을 이용한 병리적 검사가 필수적이다. 이러한 생체검사를 진행하기 위해서는 전문지식을 가진 종양학자, 임상병리사 등의 도움과 최소한의 소요시간은 확진을 위해 반드시 필요하다. 최근 들어, 인공지능을 활용한 암세포의 자동분류가 가능한 시스템 구축에 관련된 연구가 활발하게 진행되고 있다. 하지만, 이전 연구들은 한정된 알고리즘을 기반으로 하여 세포의 종류와 정확도에 한계를 보인다. 본 연구에서 심층 학습의 일종인 합성곱 신경망을 통해 총 4가지의 암세포를 식별하는 방법을 제안한다. 세포 배양을 통해 얻은 광학영상을 OpenCV를 사용하여 세포의 위치 식별 및 이미지 분할과 같은 전처리 수행 후, EfficientNet을 통해 학습하였다. 모델은 EfficientNet을 기준으로 다양한 hyper parameter를 사용하고, InceptionV3을 학습하여 성능을 비교분석 하였다. 그 결과 96.8%의 높은 정확도로 세포를 분류하는 결과를 보였으며, 이러한 분석방법은 암의 확진에 도움이 될 것으로 기대한다.

• Journal of Information Processing Systems
• /
• 제19권3호
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1807-1822
• /
• 2023

Innovation and rapid increased functionality in user friendly smartphones has encouraged shutterbugs to have picturesque image macros while in work environment or during travel. Formal signboards are placed with marketing objectives and are enriched with text for attracting people. Extracting and recognition of the text from natural images is an emerging research issue and needs consideration. When compared to conventional optical character recognition (OCR), the complex background, implicit noise, lighting, and orientation of these scenic text photos make this problem more difficult. Arabic language text scene extraction and recognition adds a number of complications and difficulties. The method described in this paper uses a two-phase methodology to extract Arabic text and word boundaries awareness from scenic images with varying text orientations. The first stage uses a convolution autoencoder, and the second uses Arabic Character Segmentation (ACS), which is followed by traditional two-layer neural networks for recognition. This study presents the way that how can an Arabic training and synthetic dataset be created for exemplify the superimposed text in different scene images. For this purpose a dataset of size 10K of cropped images has been created in the detection phase wherein Arabic text was found and 127k Arabic character dataset for the recognition phase. The phase-1 labels were generated from an Arabic corpus of quotes and sentences, which consists of 15kquotes and sentences. This study ensures that Arabic Word Awareness Region Detection (AWARD) approach with high flexibility in identifying complex Arabic text scene images, such as texts that are arbitrarily oriented, curved, or deformed, is used to detect these texts. Our research after experimentations shows that the system has a 91.8% word segmentation accuracy and a 94.2% character recognition accuracy. We believe in the future that the researchers will excel in the field of image processing while treating text images to improve or reduce noise by processing scene images in any language by enhancing the functionality of VGG-16 based model using Neural Networks.

• 한국안전학회지
• /
• 제14권1호
• /
• pp.216-221
• /
• 1999

전력용 케이블은 전선로의 지중화 추세에 따라 사용이 증가하고 있다. 케이블 절연체의 경우 장기간의 전압인가에 의해 열화 및 절연파괴 된다. 전력용 케이블의 절연파괴시 발생하는 사회/경제적 문제는 매우 심각한 것으로 알려져 있다. 절연체의 열화에 영향을 주는 요인은 매우 복잡하지만 그중에서도 전기트리 열화에 의한 파괴는 비교적 두꺼운 고체 유전체인 경우에 절연파괴 사고의 주된 원인이 되고 있다. 전기트리의 개시나 진전시 부분방전이 발생하므로 부분방전의 검출에 의해 전기트리의 발생 및 진전 양상을 관측할 수 있고 부분방전의 해석에 의해 절연재료의 잔여 수명을 예측할 수 있다. 본 논문에서는 고전압 전력용 케이블 절연재로써 광범위하게 사용되고 있는 저밀도 폴리에틸렌 시편에서의 전기트리 진전 양상을 비파괴 진단 기법에 의하여 검출하고자 내부 부분방전을 관측/해석하였다.

• Restorative Dentistry and Endodontics
• /
• 제47권4호
• /
• pp.43.1-43.13
• /
• 2022

Objectives: This study compared the surface gloss (SG), gloss retention (GR), and color stability (CS) of 2 universal resin composites after chemical (CA) and mechanical (MA) aging. Materials and Methods: Twenty disc-shaped samples of G-ænial A'Chord (GC-Europe) and Filtek Universal (3M-ESPE) were polished with sequential abrasive papers. For CA, specimens were stored in 1 mL of 75% ethanol for 15 days at 37℃, and readings (SG, GR, and CS) were obtained at baseline and 5, 10, and 15 days. For MA, specimens were subjected to 10,750 simulated brushing cycles. SG and CS were evaluated after every 3,583 cycles. SG was measured with a glossmeter (geometrical configuration: 60°), and values were expressed in gloss units. Color was measured with a spectrophotometer using the CIE-L^*a^*b^* color system. The Student's t-test, 1-way analysis of variance, and Scheffé test were used for statistical analysis (α = 0.05). Results: G-ænial presented significantly higher SG values than Filtek (p = 0.02), with GR reductions of 5.2% (CA) and 5.3% (MA) for G-ænial and 7.6% (CA) and 7.2% (MA) for Filtek. The aging protocol had no statistically significant effect on SG or GR (p = 0.25) from baseline to the final readings. G-ænial-MA presented the lowest color difference (ΔE = 1.8), and G-ænial-CA and Filtek-CA had the largest changes (ΔE = 8.6 and ΔE = 11.8, respectively). Conclusion: G-ænial presented higher SG values and better CS. Both restorative materials demonstrated acceptable GR and CS. Aging protocols impacted these properties negatively.

• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.59-68
• /
• 2023

Currently, yellow phosphor of Y3Al5O12:Ce3+ (YAG:Ce) fluorescent material is applied to a 450~480nm blue LED light source to implement a white LED device and it has a simple structure, can obtain sufficient luminance, and is economical. However, in this method, in terms of spectrum analysis, it is difficult to mass-produce white LEDs having the same color coordinates due to color separation cause by the wide wavelength gap between blue and yellow band. There is a disadvantage that it is difficult to control optical properties such as color stability and color rendering. In addition, this method does not emit purple light in the range of 380 to 420nm, so it is white without purple color that can not implement the spectrum of the entire visible light spectrum as like sunlight. Because of this, it is difficult to implement a color rendering index(CRI) of 90 or higher, and natural light characteristics such as sunlight can not be expected. For this, need for a method of implementing sunlight with one LED by using a method of combining phosphors with one light source, rather than a method of combining red, blue, and yellow LEDs. Using this method, the characteristics of an artificial sunlight LED device with a spectrum similar to that of sunlight were demonstrated by implementing LED devices of various color temperatures with high color rendering by injecting phosphors into a 405nm deep blue LED light source. In order to find the spectrum closest to sunlight, different combinations of phosphors were repeatedly fabricated and tested. In addition, reliability and mass productivity were verified through temperature and humidity tests and ink penetration tests.

• Nuclear Engineering and Technology
• /
• 제55권10호
• /
• pp.3907-3912
• /
• 2023

Radiation portal monitors (RPMs) installed at airports and harbors to prevent illicit trafficking of radioactive materials generally use large plastic scintillators. However, their energy resolution is poor and radionuclide identification is nearly unfeasible. In this study, to improve isotope identification, a RPM system based on a multi-array plastic scintillator and convolutional neural network (CNN) was evaluated by measuring the spectra of radioactive sources. A multi-array plastic scintillator comprising an assembly of 14 hexagonal scintillators was fabricated within an area of 50 × 100 cm². The energy spectra of ¹³⁷Cs, ⁶⁰Co, ²²⁶Ra, and ⁴K (KCl) were measured at speeds of 10-30 km/h, respectively, and an energy-weighted algorithm was applied. For the CNN, 700 and 300 spectral images were used as training and testing images, respectively. Compared to the conventional plastic scintillator, the multi-arrayed detector showed a high collection probability of the optical photons generated inside. A Compton maximum peak was observed for four moving radiation sources, and the CNN-based classification results showed that at least 70% was discriminated. Under the speed condition, the spectral fluctuations were higher than those under dwelling condition. However, the machine learning results demonstrated that a considerably high level of nuclide discrimination was possible under source movement conditions.

• Journal of Positioning, Navigation, and Timing
• /
• 제12권3호
• /
• pp.245-255
• /
• 2023

Time comparison techniques are necessary for generating and keeping Coordinated Universal Time (UTC) and distributing standard time clocks. Global Navigation Satellite System (GNSS) Common View, GNSS All-in-View, Two-Way Satellite Time and Frequency Transfer (TWSTFT), Very Long Baseline Interferometry (VLBI), optical fiber, and Network Time Protocol (NTP) based methods have been used for time comparison. In these methods, GNSS based time comparison techniques are widely used for time synchronization in critical national infrastructures and in common areas of application such as finance, military, and wireless communication. However, GNSS-based time comparison techniques are vulnerable to jamming or interference environments and it is difficult to respond to GNSS signal disconnection according to the international situation. In response, in this paper, Code-Division Multiple Access (CDMA) based All-to-All TWSTFT operation method is proposed. A software-based simulation platform also was designed for performance analysis in multi-TWSTFT signal environments. Furthermore, code and carrier measurement jitters were calculated in multi-signal environments using the designed simulation platform. By using the technique proposed in this paper, it is anticipated that the TWSTFT-based time comparison method will be used in various fields and satisfy high-performance requirements such as those of a GNSS master station and power plant network reference station.

• 천문학회지
• /
• 제56권2호
• /
• pp.277-286
• /
• 2023

It is difficult to distinguish the pure signal produced by an orbiting planetary companion around giant stars from other possible sources, such as stellar spots, pulsations, or certain activities. Since 2003, we have obtained radial (RV) data from evolved stars using the high-resolution, fiber-fed Bohyunsan Observatory Echelle Spectrograph (BOES) at the Bohyunsan Optical Astronomy Observatory (BOAO). Here, we report the results of RV variations in the binary star HD 135438. We found two significant periods: 494.98 d with eccentricity of 0.23 and 8494.1 d with eccentricity of 0.83. Considering orbital stability, it is impossible to have two companions in such close orbits with high eccentricity. To determine the nature of the changes in the RV variability, we analyzed indicators of stellar spot and stellar chromospheric activity to find that there are no signals related to the significant period of 494.98 d. However, we calculated the upper limits of rotation period of the rotational velocity and found this to be 478-536 d. One possible interpretation is that this may be closely related to the rotational modulation of an orbital inclination at 67-90 degrees. The other signal corresponding to the period of 8494.1 d is probably associated with a stellar companion orbiting the giant star. A Markov Chain Monte Carlo (MCMC) simulation considering a single companion indicates that HD 135438 system hosts a stellar companion with 0.57^+0.017 _-0.017 M_⊙ with an orbital period of 8498 d.

• 한국전기전자재료학회논문지
• /
• 제37권3호
• /
• pp.253-260
• /
• 2024

In this study, ITO thin films were fabricated on a glass substrate at different thicknesses without introducing oxygen using RF sputtering system. The structural, electrical, and optical properties were evaluated at various thicknesses ranging from 50 to 300 mm. As the thickness of deposited ITO thin film become thicker from 50 to 100 mm, carrier concentration, mobility, and band gap energy also increased while the resistivity and transmittance decreased in the visible light region. When the film thickness increased from 100 to 300 mm, the carrier concentration, mobility, and band gap energy decreased while the resistivity and transmittance increased. The optimum electrical properties were obtained for the ITO film 100 nm. After optimizing the thickness, the ITO thin films were post-annealed at different temperatures ranging from 100 to 300℃. As the annealing temperature increased, the ITO crystal phase became clearer and the grain size also increased. In particular, the ITO thin film annealed at 300℃ indicated high carrier concentration (4.32 × 10²¹ cm^-3), mobility (9.01 cm²/V·s) and low resistivity (6.22 × 10^-4 Ω·cm). This means that the optimal post-annealing temperature is 300℃ and this ITO thin film is suitable for use in solar cells and display application.