• Title/Summary/Keyword: a tuning

Search Result 2,823, Processing Time 0.025 seconds

Breast Cancer Histopathological Image Classification Based on Deep Neural Network with Pre-Trained Model Architecture (사전훈련된 모델구조를 이용한 심층신경망 기반 유방암 조직병리학적 이미지 분류)

  • Mudeng, Vicky;Lee, Eonjin;Choe, Se-woon
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2022.05a
    • /
    • pp.399-401
    • /
    • 2022
  • A definitive diagnosis to classify the breast malignancy status may be achieved by microscopic analysis using surgical open biopsy. However, this procedure requires experts in the specializing of histopathological image analysis directing to time-consuming and high cost. To overcome these issues, deep learning is considered practically efficient to categorize breast cancer into benign and malignant from histopathological images in order to assist pathologists. This study presents a pre-trained convolutional neural network model architecture with a 100% fine-tuning scheme and Adagrad optimizer to classify the breast cancer histopathological images into benign and malignant using a 40× magnification BreaKHis dataset. The pre-trained architecture was constructed using the InceptionResNetV2 model to generate a modified InceptionResNetV2 by substituting the last layer with dense and dropout layers. The results by demonstrating training loss of 0.25%, training accuracy of 99.96%, validation loss of 3.10%, validation accuracy of 99.41%, test loss of 8.46%, and test accuracy of 98.75% indicated that the modified InceptionResNetV2 model is reliable to predict the breast malignancy type from histopathological images. Future works are necessary to focus on k-fold cross-validation, optimizer, model, hyperparameter optimization, and classification on 100×, 200×, and 400× magnification.

  • PDF

A Miniaturized 2.5 GHz 8 W GaN HEMT Power Amplifier Module Using Selectively Anodized Aluminum Oxide Substrate (선택적 산화 알루미늄 기판을 이용한 소형 2.5 GHz 8 W GaN HEMT 전력 증폭기 모듈)

  • Jeong, Hae-Chang;Oh, Hyun-Seok;Yeom, Kyung-Whan
    • The Journal of Korean Institute of Electromagnetic Engineering and Science
    • /
    • v.22 no.12
    • /
    • pp.1069-1077
    • /
    • 2011
  • In this paper, a design and fabrication of a miniaturized 2.5 GHz 8 W power amplifier using selectively anodized aluminum oxide(SAAO) substrate are presented. The process of SAAO substrate is recently proposed and patented by Wavenics Inc. which uses aluminum as wafer. The selected active device is a commercially available GaN HEMT chip of TriQuint company, which is recently released. The optimum impedances for power amplifier design were extracted using the custom tuning jig composed of tunable passive components. The class-F power amplifier are designed based on EM co-simulation of impedance matching circuit. The matching circuit is realized in SAAO substrate. For integration and matching in the small package module, spiral inductors and single layer capacitors are used. The fabricated power amplifier with $4.4{\times}4.4\;mm^2$ shows the efficiency above 40 % and harmonic suppression above 30 dBc for the second(2nd) and the third(3rd) harmonic at the output power of 8 W.

Controlled Production of Monodisperse Polycaprolactone Microparticles using Microfluidic Device (미세유체장치를 이용한 생분해성 Polycarprolactone의 단분산성 미세입자 생성제어)

  • Jeong, Heon-Ho
    • Clean Technology
    • /
    • v.25 no.4
    • /
    • pp.283-288
    • /
    • 2019
  • Monodisperse microparticles has been particularly enabling for various applications in the encapsulation and delivery of pharmaceutical agents. The microfluidic devices are attractive candidates to produce highly uniform droplets that serve as templates to form monodisperse microparticles. The microfluidic devices that have micro-scale channel allow precise control of the balance between surface tension and viscous forces in two-phase flows. One of its essential abilities is to generate highly monodisperse droplets. In this paper, a microfluidic approach for preparing monodisperse polycaprolactone (PCL) microparticles is presented. The microfluidic devices that have a flow-focusing generator are manufactured by soft-lithography using polydimethylsiloxane (PDMS). The crucial factors in the droplet generation are the controllability of size and monodispersity of the microdroplets. For this, the volumetric flow rates of the dispersed phase of oil solution and the continuous phase of water to generate monodisperse droplets are optimized. As a result, the optimal flow condition for droplet dripping region that is able to generate uniform droplet is found. Furthermore, the droplets containing PCL polymer by solvent evaporation after collection of droplet from device is solidified to generate the microparticle. The particle size can be controlled by tuning the flow rate and the size of the microchannel. The monodispersity of the PCL particles is measured by a coefficient of variation (CV) below 5%.

A Study on the Design and Fabrication of Diplexer Using H-plane T-junction for KOREASAT-III Transponder (자계면 T-접합을 이용한 무궁화 III호 위성체용 다이플렉서의 설계 및 제작에 관한 연구)

  • 이용민;홍완표;신철재;강준길;나극환
    • The Journal of Korean Institute of Electromagnetic Engineering and Science
    • /
    • v.10 no.4
    • /
    • pp.582-593
    • /
    • 1999
  • This paper presents the design and fabrication of the diplexer for a KOREASAT-III Ka-band satellite transponder. The transmission characteristics of the diplexer is analyzed by calculating the generalized scattering matrix using mode matching method. It is composed of 2 bandpass filters, coupled with H-plane T-junction having symmetrical inductive iris and E-plane metal insert structures. Compared with the size and weight of the Rx and Tx filter loaded with a transponders respectively, those of the diplexer can be effectively reduced. In a high power transmission, the variation of the filter characteristics is minimized by the scheme that irises are extended to the exterior of H-plane of the waveguide. This scheme needs no extra heat sinks for dissipating high power. The diplexer is designed to improve the simplification, durability and reliability by eliminating tuning screws, which have been used to compensate for the characteristics of fabricated filters. The bandpass filters of the diplexer show the insertion loss of less than 1.2 dB and the return loss in excess of 15 dB. The isolations of more than 65 dB have been achieved between Rx and Tx filter.

  • PDF

Mutation Analysis of Synthetic DNA Barcodes in a Fission Yeast Gene Deletion Library by Sanger Sequencing

  • Lee, Minho;Choi, Shin-Jung;Han, Sangjo;Nam, Miyoung;Kim, Dongsup;Kim, Dong-Uk;Hoe, Kwang-Lae
    • Genomics & Informatics
    • /
    • v.16 no.2
    • /
    • pp.22-29
    • /
    • 2018
  • Incorporation of unique barcodes into fission yeast gene deletion collections has enabled the identification of gene functions by growth fitness analysis. For fine tuning, it is important to examine barcode sequences, because mutations arise during strain construction. Out of 8,708 barcodes (4,354 strains) covering 88.5% of all 4,919 open reading frames, 7,734 barcodes (88.8%) were validated as high-fidelity to be inserted at the correct positions by Sanger sequencing. Sequence examination of the 7,734 high-fidelity barcodes revealed that 1,039 barcodes (13.4%) deviated from the original design. In total, 1,284 mutations (mutation rate of 16.6%) exist within the 1,039 mutated barcodes, which is comparable to budding yeast (18%). When the type of mutation was considered, substitutions accounted for 845 mutations (10.9%), deletions accounted for 319 mutations (4.1%), and insertions accounted for 121 mutations (1.6%). Peculiarly, the frequency of substitutions (67.6%) was unexpectedly higher than in budding yeast (~28%) and well above the predicted error of Sanger sequencing (~2%), which might have arisen during the solid-phase oligonucleotide synthesis and PCR amplification of the barcodes during strain construction. When the mutation rate was analyzed by position within 20-mer barcodes using the 1,284 mutations from the 7,734 sequenced barcodes, there was no significant difference between up-tags and down-tags at a given position. The mutation frequency at a given position was similar at most positions, ranging from 0.4% (32/7,734) to 1.1% (82/7,734), except at position 1, which was highest (3.1%), as in budding yeast. Together, well-defined barcode sequences, combined with the next-generation sequencing platform, promise to make the fission yeast gene deletion library a powerful tool for understanding gene function.

Tuning Thermal Expansion Coefficient of Composites Containing Epoxy Resin/Inorganic Additives for Stone Conservation (에폭시 수지/무기물 첨가제 복합체의 열팽창계수 조절 및 석조문화재의 응용)

  • Choi, Yong-Seok;Chae, Il-Seok;Kang, Yong-Soo;Won, Jong-Ok;Kim, Jeong-Jin;Kim, Sa-Dug
    • Journal of Conservation Science
    • /
    • v.27 no.4
    • /
    • pp.431-440
    • /
    • 2011
  • The thermal expansion coefficient of epoxy/inorganic additives composites was controlled by changing the amount of the inorganic additives such as talc and fused silica. The epoxy resin comprises hydrogenated bisphenol A (HBA)-based epoxide, difunctional polyglycidyl epoxide (DPE) as a diluent and isophorone-diamine (IPDA) as a crosslinking agent, which was subsequently mixed with inorganic additives (talc and fused silica). The thermal expansion coefficient was decreased by increasing amount of inorganic additives, nearly to fresh granite. Fused silica was more effective than talc in lowering the thermal expansion coefficient. Additionally, lexural and tensile strengths of the composites were getting lower and higher with the amount of the inorganic fillers, respectively. It was thus concluded that an epoxy composite containing inorganic fillers was developed to show much lower thermal expansion coefficient, similar to fresh granite, than the neat epoxy resin, and also proper mechanical strengths for applications.

A Study on the Enhancement of Isolation of the MIMO Antenna for LTE/DCS1800/USPCS1900 Handset (LTE/DCS1800/USPCS1900 단말기용 MIMO 안테나의 격리도 개선에 관한 연구)

  • Cho, Dong-Ki;Son, Ho-Cheol;Lee, Jin-Woo;Lee, Sang-Woon;Lee, Mun-Soo
    • Journal of the Institute of Electronics Engineers of Korea TC
    • /
    • v.47 no.10
    • /
    • pp.80-85
    • /
    • 2010
  • In this paper, a MIMO antenna is proposed for LTE/DCSl800/USPCSl900 handset applications. The proposed antenna is based on the IFA and its wide bandwidth is obtained by using a stagger tuning technique. To improve the isolation, a suspended line is connected to the shorting points in two antennas, and capacitors and inductors are added to the connected suspended line. Two identical antennas of which dimension is 2.8cc($40{\times}10{\times}7mm$) are mounted on the two end lines of the system ground plane($40{\times}60mm$). Analysis of the antenna performance and optimization is performed using CST Microwave Studio. The bandwidths are satisfied for LTE band class 13(746-787MHz), class 14(758-798MHz) and DCSl800/USPCSl900 band (1710-1990MHz). The isolations between two antennas are about -12dB for LTE band and -10dB for DCSl800/USPCSl900 band. And the radiation efficiency of each antenna is about for LTE band 33% and 45% for DCSl800/USPCSl900 band respectively.

A Class-C type Wideband Current-Reuse VCO With 2-Step Auto Amplitude Calibration(AAC) Loop (2 단계 자동 진폭 캘리브레이션 기법을 적용한 넓은 튜닝 범위를 갖는 클래스-C 타입 전류 재사용 전압제어발진기 설계)

  • Kim, Dongyoung;Choi, Jinwook;Lee, Dongsoo;Lee, Kang-Yoon
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.51 no.11
    • /
    • pp.94-100
    • /
    • 2014
  • In this paper, a design of low power Current-Reuse Voltage Controlled Oscillator (VCO) which has wide tuning range about 1.95 GHz ~ 3.15 GHz is presented. Class-C type is applied to improve phase noise and 2-Step Auto Amplitude Calibration (AAC) is used for minimizing the imbalance of differential VCO output voltage which is main issue of Current-Reuse VCO. The mismatch of differential VCO output voltage is presented about 1.5mV ~ 4.5mV. This mismatch is within 0.6 % compared with VCO output voltage. Proposed Current-Reuse VCO is designed using CMOS $0.13{\mu}m$ process. Supply voltage is 1.2 V and current consumption is 2.6 mA at center frequency. The phase noise is -116.267 dBc/Hz at 2.3GHz VCO frequency at 1MHz offset. The layout size is $720{\times}580{\mu}m^2$.

Dielectric Waveguide Filters Design Embedded in PCB Substrates using Via Fence at Millimeter-Wave (밀리미터파 대역에서 Via Fence를 이용한 PCB 기판용 유전체 도파관 필터 설계)

  • 김봉수;이재욱;김광선;강민수;송명선
    • The Journal of Korean Institute of Electromagnetic Engineering and Science
    • /
    • v.15 no.1
    • /
    • pp.73-80
    • /
    • 2004
  • In this paper, the implementation and embedding method of the existing air-filled waveguide-filters at millimeter-wave on general PCB substrate is introduced by systematically inserting the vias inside waveguide and mathematically manipulating the simple equations obtained ken the classical circular-post waveguide filter design. All the metal structures placed vertically such as side wall fur perfect ground plane and circular-post for signal control in the air-filled WR-22 waveguide are replaced with several types of via for constructing the bandpass-filter. Side wall and poles inside waveguide are realized by placing a series array of via and tuning the via diameter. The lengths of x, y, z axis are reduced in proportion to root square of employed substrate dielectric constant and especially the length of z axis can be more reduced due to the characteristics of the wave propagation. Because the mass production on PCB is possible without fabricating a large-scaled metal waveguide of WR-22 as input/output ports at millimeter-wave regime, the manufacturing cost is reduced considerably. Finally, when using multilayer process like LTCC for small-sized module, it is one of advantages to use only one layer f3r the filter fabrication. To evaluate the validity of this novel technique, order-3 Chebyshev BPF(Bandpass-Filter) centered at 40 GHz-band with a 2.5 % FBW (Fractional Bandwidth) were used. The employed substrate has relative dielectric constant of 2.2 and thickness of 10 mil of Rogers RT/Duroid 5880. Accroding to design and measurement results, a good performance of insertion loss of 2 ㏈ and return loss of -30 ㏈ is achieved at full input/output ports.

Integrated Photonic Microwave Bandpass Filter Incorporating a Polymer Microring Resonator (폴리머 마이크로링 공진기를 이용한 광학적 마이크로웨이브 대역통과 필터)

  • Chin, Won-Jun;Kim, Do-Hwan;Song, Ju-Han;Lee, Sang-Shin
    • Korean Journal of Optics and Photonics
    • /
    • v.16 no.5
    • /
    • pp.469-475
    • /
    • 2005
  • An integrated photonic microwave bandpass filter has been proposed and demonstrated incorporating a coherently coupled microring resonator in low-loss polymers. The proposed device may feature compact site, simple structure, tuning via the thermooptic and electrooptic effect, and flexible integration with other electrical and optical devices. The resonator was designed to have an extremely small bandwidth so that it could be used to selectively pass the optical signal carrying the microwave signal to attain efficient bandpass filtering. We made and tested two resonators with a single ring and double rings, and performed a theoretical fitting of their measured transfer curves to predict the performance of the microwave filters based on them precisely. It was found that as the number of the rings used for the resonator increases, the bandwidth gets smaller, the rolloff sharper, and the band rejection higher. Finally our filter exhibited the center frequency of 10GHz, the 3-dB bandwidth of 1.0GHz, the corresponding quality (Q) factor of 10, and the rejection outside of the passband of more than 25dB.