• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.212-218
• /
• 2020

There are dozens of different types of lesions that can be diagnosed through chest X-ray images, including Atelectasis, Cardiomegaly, Mass, Pneumothorax, and Effusion. Computed tomography(CT) test is generally necessary to determine the exact diagnosis and location and size of thoracic lesions, however computed tomography has disadvantages such as expensive cost and a lot of radiation exposure. Therefore, in this paper, we propose a deep learning algorithm for judging the presence or absence of lesions in chest X-ray images as the primary screening tool for the diagnosis of thoracic lesions. The proposed algorithm was designed by comparing various configuration methods to optimize the judgment of presence of lesions from chest X-ray. As a result, the evaluation rate of lesion presence of the proposed algorithm is about 1% better than the existing algorithm.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.2
• /
• pp.119-125
• /
• 2022

In this paper, we present design, implementation and test results of CTM (Chirp Transceiver Module) EM (Engineering Model) for C-Band SAR (Synthetic Aperture Radar) Payload. The CTM is designed to operate dual frequency scan method that simultaneously operate two frequencies in each 50MHz bandwidth to achieve 120Km swath with 10m resolution at about 500Km altitude. The CTM used radiation tolerant RTG4 FPGA for space environment, and implemented with the Parallel DDS (PDDS) method which uses a small memory capacity compared to the memory-map method. Test results show high purity chirp signal generation and excellent IRF performance from received chirp signal after direct digital conversion.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.83-90
• /
• 2023

Blurred image is an important factor in lowering image recognition rates in Computer vision. This mainly occurs when the camera is unstablely out of focus or the object in the scene moves quickly during the exposure time. Blurred images greatly degrade visual quality, weakening visibility, and this phenomenon occurs frequently despite the continuous development digital camera technology. In this paper, it replace the modified building module based on the Deep multi-patch neural network designed with convolution neural networks to capture details of input images and Attention techniques to focus on objects in blurred images in many ways and strengthen the image. It measures and assigns each weight at different scales to differentiate the blurring of change and restores from rough to fine levels of the image to adjust both global and local region sequentially. Through this method, it show excellent results that recover degraded image quality, extract efficient object detection and features, and complement color constancy.

• Journal of Korean Society of Forest Science
• /
• v.112 no.4
• /
• pp.490-501
• /
• 2023

Laboratory column tests were conducted to analyze infiltration and water redistribution processes on the basis of rainfall. To efficiently measure moisture content within soil layers, this research developed a predictive model grounded in a convolutional neural network (CNN), a deep learning technique. The digital images obtained during the column tests were incorporated into the established CNN. The moisture content of each soil layer over time was effectively measured. The measured values were also in relatively good agreement with the moisture content determined using the moisture sensors installed for each soil layer. The use of CNN enabled a comprehensive understanding of continuous moisture distribution within the soil layers, as well as the infiltration process according to soil texture and initial moisture content conditions.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.1
• /
• pp.38-46
• /
• 2024

In general, EEG signal analysis has been the subject of several studies due to its ability to provide an objective mode of recording brain stimulation, which is widely used in brain-computer interface research with applications in medical diagnosis and rehabilitation engineering. In this study, we developed EEG reception hardware to measure electroencephalograms and implemented a processing system, classifying it into server and data processing. It was conducted as an intermediate-stage research on the implementation of a brain-computer interface using electroencephalograms, and was implemented in the form of predicting the user's arm movements according to measured electroencephalogram data. Electroencephalogram measurements were performed using input from four electrodes through an analog-to-digital converter. After sending this to the server through a communication process, we designed and implemented a system flow in which the server classifies the electroencephalogram input using a convolutional neural network model and displays the results on the user terminal.

• Journal of the Korean Society of Radiology
• /
• v.12 no.1
• /
• pp.23-30
• /
• 2018

To evaluate the effect of patient size on effective dose and image quality for Digital Chest Tomosynthesis(DTS) using additional 0.3 mm copper filtration. Eighty artificial nodules were placed in the thorax phantom("Lungman," Kyoto Kagaku, Japan), and Digital Chest Tomosynthesis(DTS) images of the phantom were acquired both with and without added 0.3 mm Cu filtration. To simulate patients of three sizes: small, average size and oversize, one or two 20-mm-thick layer of PMMA(polymethyl methacrylatek) blocks were placed on the phantom. The Effective dose was calculated using Monte Carlo simulations. Two evaluations of image quality methods have been employed. Three readers counted the number of nodules detected in the lung, and the measured contrast-to-noise ratios(CNRs) were used. Data were analyzed statistically. The ED reduced $26{\mu}Sv$ in a phantom, $33{\mu}Sv$ in one 20-mm-thick layer of PMMA block placed on the phantom, and $48{\mu}Sv$ in two 20-mm-thick layer of PMMA blocks placed on the phantom. The Effective dose(ED) differences between DTS with and without filtration were significant(p<0.05). In particular, when we used two 20-mm-thick layer of PMMA blocks placed on the phantom, the ED was significantly reduced by 36% compared with those without additional filtration. Nodule detection sensitivities were not different between with and without added filtration. Differences of CNRs were statistically insignificant(p>0.05). Use of additional filtration allows a considerable dose reduction during Digital Chest Tomosynthesis(DTS) without loss of image quality. In particular, additional filtration showed outstanding result for effective dose reduction on two 20-mm-thick layer of PMMA blocks placed on the phantom. It applies to overweight patients.

• Radiation Oncology Journal
• /
• v.17 no.1
• /
• pp.84-88
• /
• 1999

Purpose :To develop a method for verifying a treatment setup in stereotactic radiotherapy by ma- tching portal images to DRRs. Materials and Methods : Four pairs of orthogonal portal images of one patient immobilized by a thermoplastic mask frame for fractionated stereotactic radiotherapy were compared with DRRs. Portal images are obtained in AP (anteriorfposterior) and lateral directions with a target localizer box containing fiducial markers attached to a stereotactic frame. DRRs superimposed over a planned iso-center and fiducial markers are printed out on transparent films. And then, they were overlaid over onhogonal penal images by matching anatomical structures. From three different kind of objects (isgcenter, fiducial markers, anatomical structure) on DRRs and portal images, the displacement error between anatomical structure and isocenters (overall setup error), the displacement error between anatomical structure and fiducial markers (irnrnobiliBation error), and the displacement error between fiducial markers and isocenters (localization error) were measured. Results : Localization error were 1.5$\pm$0.3 mm (AP), 0.9$\pm$0.3 mm (lateral), and immobilization errors were 1.9$\pm$0.5 mm (AP), 1.9$\pm$0.4 mm (lateral). In addition, overall setup errors were 1.0$\pm$0.9 mm (AP), 1.3$\pm$0.4 mm (lateral). From these orthogonal displacement errors, maximum 3D displacement errors($\sqrt{(\DeltaAP)^{2}+(\DeltaLat)^{2}$)) were found to be 1.7$\pm$0.4 mm for localization, 2.0$\pm$0.6 mm for immobilization, and 2.3$\pm$0.7 mm for overall treatment setup. Conclusion : By comparing orthogonal portal images with DRRs, we find out that it is possible to verify treatment setup directly in stereotactic radiotherapy.

• Journal of the Korean Society of Radiology
• /
• v.5 no.5
• /
• pp.283-287
• /
• 2011

In this study, fine $Gd_2O_2S$:Tb powder was synthesized by using a low temperature solution-combustion method for a high-resolution digital x-ray imaging detector. From the fabricated phosphor power, the fine scintillator films was fabricated by particle sedimentation method and was investigated the luminescent property. From the experimental results of relative light output as a function of terbium concentration, the highest luminescent efficiency has at 5 wt% Tb concentration, and luminescent intensity decreased rapidly according to quenching effect about higher Tb concentration. Also, the relative light output of $270{\mu}m$-$Gd_2O_2S$:Tb film has 2945 pC/$cm^2$/mR. And light intensity was saturated at higher film thickness. Finally, to evaluate an image acquisition performance of fabricated phosphor, images were obtained by using commercial CMOS sensor and measured the MTF, NPS, and DQE. DQE(0 lp/mm) of fine phosphor film has 37%. But, DQE improvement of fine phosphor film is possible by resolving problem of film fabrication process and has a significant potential in the application of digital radiation imaging system later.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.20 no.12
• /
• pp.1340-1350
• /
• 2009

The design and implementation of planar Active Phased Array Antenna System are described in this paper. This Antenna system operates at X-band with its bandwidth 10 % and dual polarization is realized using dual slot feeding microstrip patch antenna and SPDT(Single Pole Double Through) switch. Array Structure is $16\times16$ triangular lattice structure and each array is composed of TR(Transmit & Receive) module with more than 40 dBm power. Each TR module includes digital attenuator and phase shifter so that antenna beam can be electronically steered over a scan angle$({\pm}60^{\circ})$. Measurement of antenna pattern is conducted using a near field chamber and the results coincide with the expected beam pattern. From these results, it can be convinced that this antenna can be used with control of beam steering and beam shaping.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.3
• /
• pp.699-707
• /
• 2016

This paper proposes a low-complexity central processing unit (CPU) that is suitable for deeply embedded systems, including Internet of things (IoT) applications. The core features a 16-bit instruction set architecture (ISA) that leads to high code density, as well as a multicycle architecture with a counter-based control unit and adder sharing that lead to a small hardware area. A co-processor, instruction cache, AMBA bus, internal SRAM, external memory, on-chip debugger (OCD), and peripheral I/Os are placed around the core to make a system-on-a-chip (SoC) platform. This platform is based on a modified Harvard architecture to facilitate memory access by reducing the number of access clock cycles. The SoC platform and CPU were simulated and verified at the C and the assembly levels, and FPGA prototyping with integrated logic analysis was carried out. The CPU was synthesized at the ASIC front-end gate netlist level using a $0.18{\mu}m$ digital CMOS technology with 1.8V supply, resulting in a gate count of merely 7700 at a 50MHz clock speed. The SoC platform was embedded in an FPGA on a miniature board and applied to deeply embedded IoT applications.