Earticle

영상의 특징인 색상, 모양, 질감 등을 이용해 영상을 검색하는 연구들은 많이 진행되어 왔다. 또한 작물의 질병 영상 과 관련된 연구들도 진행되고 있다. 농업 현장에서 재배되는 작물에 발생한 질병을 확인하는데 도움이 되기 위해 본 논문에서는 시설원예 작물의 질병 영상을 이용한 유사도 기반 작물 질병 검색 시스템을 제안한다. 제안하는 시스템 은 단일 Descriptor를 사용하지 않고, 조합 Descriptor를 통해 기존 대비 영상의 유사도 검색 성능을 높였고 유사 도 검색 결과를 가독성 높게 사용자에게 제공하기 위해 가중치 기반 산출방법을 적용했다. 본 논문에서는 총 13개 의 개별 Descriptor를 이용해 조합을 진행했다. 조합 Descriptor를 이용해 6개 작물의 질병에 대해 유사도 검색을 진행했고 작물별로 평균 accuracy가 높은 조합 Descriptor를 선정해 유사도 검색에 사용했다. 검색된 결과는 병명 의 비율을 기반으로 한 산출방법과 가중치를 기반으로 한 산출방법을 사용해 백분율로 나타냈다. 병명의 비율을 기 반으로 한 산출방법은 질의 영상과 유사도 검색에 사용되는 영상의 수가 많은 병명이 1순위로 출력되는 문제점이 있다. 이를 해결하기 위해 가중치를 기반으로 한 산출방법을 사용했다. 작물의 병명별 테스트 영상을 두 가지 산출 방법에 적용해 검색 성능을 측정했다. 작물의 질병별로 두 가지 산출방법에 대해 검색 성능 값의 평균을 비교한 결 과 고추, 사과 작물에서는 병명의 비율을 기반으로 한 산출방법의 성능이 가중치를 기반으로 한 산출방법의 성능보 다 평균 약 11.89%의 높은 성능 결과를 보였다. 국화, 딸기, 배, 포도 작물에서는 가중치를 기반으로 한 산출방법 이 병명의 비율을 기반으로 한 산출방법의 성능보다 평균 약 20.34%의 높은 성능 결과를 보였다. 또한 본 논문에 서 제안하는 시스템의 UI/UX는 실제 사용자의 피드백을 통해 편리하게 구성했다. 시스템의 화면마다 상단에 제목 과 설명을 출력했고 사용자가 질병의 정보를 보기 편리하게 화면을 구성했다. 검색된 질병의 정보는 위에서 제안한 산출방법을 토대로 유사한 질병의 영상과 병명을 출력한다. 시스템의 환경은 PC 환경 기반의 웹 브라우저와 모바일 디바이스 환경 기반의 웹 브라우저를 통해 사용할 수 있도록 구현했다.

Many studies have been carried out to retrieve images using colors, shapes, and textures which are characteristic of images. In addition, there is also progress in research related to the disease images of the crop. In this paper, to be a help to identify the disease occurred in crops grown in the agricultural field, we propose a similarity-based crop disease search system using the diseases image of horticulture crops. The proposed system improves the similarity retrieval performance compared to existing ones through the combination descriptor without using a single descriptor and applied the weight based calculation method to provide users with highly readable similarity search results. In this paper, a total of 13 Descriptors were used in combination. We used to retrieval of disease of six crops using a combination Descriptor, and a combination Descriptor with the highest average accuracy for each crop was selected as a combination Descriptor for the crop. The retrieved result were expressed as a percentage using the calculation method based on the ratio of disease names, and calculation method based on the weight. The calculation method based on the ratio of disease name has a problem in that number of images used in the query image and similarity search was output in a first order. To solve this problem, we used a calculation method based on weight. We applied the test image of each disease name to each of the two calculation methods to measure the classification performance of the retrieval results. We compared averages of retrieval performance for two calculation method for each crop. In cases of red pepper and apple, the performance of the calculation method based on the ratio of disease names was about 11.89% on average higher than that of the calculation method based on weight, respectively. In cases of chrysanthemum, strawberry, pear, and grape, the performance of the calculation method based on the weight was about 20.34% on average higher than that of the calculation method based on the ratio of disease names, respectively. In addition, the system proposed in this paper, UI/UX was configured conveniently via the feedback of actual users. Each system screen has a title and a description of the screen at the top, and was configured to display a user to conveniently view the information on the disease. The information of the disease searched based on the calculation method proposed above displays images and disease names of similar diseases. The system’s environment is implemented for use with a web browser based on a pc environment and a web browser based on a mobile device environment.

Recent studies have shown that inverse design using deep learning has the potential to rapidly generate the optimal design that satisfies the target performance without the need for iterative optimization processes. Unlike traditional methods, deep learning allows the network to rapidly generate a large number of solution candidates for the same objective after a single training, and enables the generation of diverse designs tailored to the objectives of inverse design. These inverse design techniques are expected to significantly enhance the efficiency and innovation of design processes in various fields such as aerospace, biology, medical, and engineering. We analyzes inverse design models that are mainly utilized in the nano and chemical fields, and proposes inverse design models based on supervised and unsupervised learning that can be applied to the engineering system. It is expected to present the possibility of effectively applying inverse design methodologies to the design optimization problem in the field of engineering according to each specific objective.

To reproduce binaural sound at a listener’s ears using stereo loudspeakers in a portable device environment, it is important to design inverse filters that cancel out acoustical crosstalk signals. However, the direct and the crosstalk paths of a head- related transfer function are similar at certain frequencies, resulting in an excessive boost at those frequencies when inverse filters are designed. To mitigate this problem, a cross-talk cancellation filter design method is proposed which allows for the selective attenuation of unwanted peaks in the spectrum by constraining the magnitude of the difference between the direct and crosstalk paths. The performance of the proposed method is then evaluated by means of subjective source localization and objective tests. It is shown from the tests that the proposed method is able to provide binaural sound effects with very closely spaced stereo loudspeakers.

In the cutting edge world, data security has turned into an essential issue furthermore the innovation is going to increment quickly. In this paper, the symmetric key standard for encryption and decoding is propelled Encryption standard (AES). The key stride in the AES is the "S-Box". S Box is an imperative segment for symmetric key calculations. An S-box takes some number of information bits "p" and interprets them in yield bits 'q', where "p" is not as a matter of course equivalent to 'q'. In AES Encryption calculation Sub Bytes change uses S-Box and Inverse S-Box uses Inverse of S-Box. The Sub Bytes substitution is a nonlinear byte substitution that uses substitution table (i.e., S-Box) takes the multiplicative reverse (GF (28)) and infers a relative change to do the Sub Bytes change. Though, converse Sub Bytes Substitution additionally uses gaze upward table (i.e., Reverse S-Box) takes an opposite relative change and after that suggests multiplicative backwards of Galois Field (GF (28)). In this printed material, we investigated substitution table/reverse substitution table, multiplicative opposite and relative change and its converse (i.e. reverse relative change) science in Galois field. A standout amongst the most basic issues in AES is the force utilization. Here, we predominantly centered around the force utilization and in addition security of S-box which is the most power devouring square in the AES. We have executed and reproduced S-Box and Inverse S-Box Lookup table and acquired another improved scrambled Lookup table for more upgraded mystery by utilizing Xilinx Spartan-3 assessment board. The Simulation and execution instruments utilized are Xilinx ISE 14.1i and ModelSim 6.0.

본 논문에서는 효율적인 AES 암호화를 위한 곱셈역원 연산기인 S-Box 설계를 제안한다. 제안한 방법은 먼저, 합성체 기반의 개선된 S-Box 모듈을 설계하고, 다단 파이프라인(multi-stage pipeline) 구조의 S-Box의 성능을 평가 한다. 제안하는 S-Box 모듈에서의 곱셈역원 연산은 조합 논리로 구성되기 때문에 하드웨어 부담이 감소되고 처리 속도 가 개선된다. 논리합성을 통하여 3-단 파이프라인 구조의 S-Box 의 경우, 기존 방법[3]과의 연산속도 비교에서 약 28% 정도 개선됨을 보인다. 본 논문에서 제안한 개선된 S-Box는 Verilog-HDL을 사용하여 혼합 레벨에서 모델링을 행하였 으며, Xilinx ISE 14.7툴을 사용하여 Spartan 3s1500l FPGA 상에서 합성을 수행하였다. 그리고 타이밍 시뮬레이션 (ModelSim PE 10.3 사용)을 통하여 설계된 S-Box가 정상적으로 동작함을 확인하였다.

This paper proposes the design of an advanced S-Box for calculating multiplicative inverse in AES encryption process. In this approach, advanced S-box module is first designed based on composite field, and then the performance evaluation is performed for S-box with multi-stage pipelining architecture. In the proposed S-Box architecture, each module for multiplicative inverse is constructed using combinational logic for realizing both small-area and high-speed. Through logic synthesis result, the designed 3-stage pipelined S-Box shows speed improvement of about 28% compared to the conventional method[3]. The proposed advanced AES S-Box is performed modelling at the mixed level using Verilog-HDL, and logic synthesis is also performed on Spartan 3s1500l FPGA using Xilinx ISE 14.7 tool.

The pump-turbine impeller is the key component of pumped storage power plant. Current design methods of pump-turbine impeller are private and protected from public viewing. Generally, the design proceeds in two steps: the initial hydraulic design and optimization design to achieve a balanced performance between pump mode and turbine mode. In this study, the 3D inverse design method is used for the initial hydraulic impeller design. However, due to the special demand of high performance in both pump and reverse mode, the design method is insufficient. This study is carried out by modifying the geometrical parameters of the blade which have great influence and need special consideration in obtaining the high performance on the both modes, such as blade shape type at low pressure side (inlet of pump mode, outlet of turbine mode) and the blade lean at blade high pressure side (outlet of pump mode, inlet of turbine mode). The influence of the geometrical parameters on the performance characteristic is evaluated by CFD analysis which presents the efficiency and internal flow results. After these investigations of the geometrical parameters, the criteria of designing pump-turbine impeller blade low and high sides shape is achieved.

Numerical analysis and its inverse design process of 2nd stage of JT8D aircraft engine is described. One of the most important factors that affect the performante of turbomachine is secondary flow in the blade passage, so that the performance of turbomachine can be improved by controlling secondary flow. In this paper, as a method to control secondary flow, commercial inverse design program, TurboDesign is used. Meridional derivative of angular momentum is selected as a parameter to control blade leading in this program, To validate inverse designed model, computational analysis is applied which includes rotor-stator-interaction. In this paper, CFB results of both original and inverse designed model are compared to examine how much the performance improves without reduction of work output.

In this paper, we suggest reliability as a metric to evaluate the robustness of a design for the optimal design of electromagnetic devices, with respect to constraints under the uncertainties in design variables. For fast numerical efficiency, we applied the sensitivity-assisted Monte Carlo simulation (S-MCS) method to perform reliability calculation. Furthermore, we incorporated the S-MCS with single-objective and multi-objective particle swarm optimization algorithms to achieve reliability-based optimal designs, undertaking probabilistic constraint and multi-objective optimization approaches, respectively. We validated the performance of the developed optimization algorithms through application to the optimal design of a superconducting magnetic energy storage system.

A computationally efficient stiffness design method for building structures is proposed in which dynamic soil-structure interaction based on the wave-propagation theory is taken into account. A sway-rocking shear building model with appropriate ground impedances derived from the cone models due to Meek and Wolf (1994) is used as a simplified design model. Two representative models, i.e. a structure on a homogeneous half-space ground and a structure on a soil layer on rigid rock, are considered. Super-structure stiffness satisfying a desired stiffness performance condition are determined via an inverse problem formulation for a prescribed ground-surface response spectrum. It is shown through a simple yet reasonably accurate model that the ground conditions, e.g. homogeneous half-space or soil layer on rigid rock (frequency-dependence of impedance functions), ground properties (shear wave velocity), depth of surface ground, have extensive influence on the super-structure design.

A mathematical methodology is proposed for designing nozzle hole shapes producing controlled geometric cavitation. The proposed methodology uses an unstructured RANS flow solver, with the ability to compute sensitivity derivatives via an adjoint algorithm. The adjoint formulation for the N-S equations is presented while variation of the turbulence viscosity is not taken into account during the geometry modifications. The sensitivities are calculated in a mode independently of the shape parameterisation. The method is used to develop and evaluate conceptual shapes for nozzle hole cavitation reduction. The localized region at the hole inlet producing cavitation, is parameterised using its radius of curvature, while a cost function is formulated to eliminate the negative pressures present at this location. Sensitivity derivatives are used to assess the dependence of the localized region on the minimum pressure, and to drive the geometry to the targeted shape. The results show that the computer model can provide nozzle hole entry shapes that produce predefined flow characteristics, and thus can be used as an inverse design tool for nozzle hole cavitation control.

Robust design (RD) has emerged as a key feature in process design and development for more than twenty years. Many researchers and industrial engineers around the world have invested their intensive efforts to develop and apply RD in many fields in order to improve quality of output products. However, there is also room for improvement. The primary objective of this research is to determine "robust formulation" of a medicine by checking its gelation index. In order to achieve this target, based on the nature of problem, at first, a customized experimental format is designed for obtaining data. Second, time-depended responses based models are developed by the proposed inverse problem (IP) methodology. Third, an RD model based on mean square error (MSE) concept is introduced for time-depended responses. Finally, the proposed approach is illustrated by a case study while comparing obtained results to the response surface methodology (RSM) approach.

A number of existing and emerging concepts for formulating solution algorithms applicable to multidisciplinary inverse problems involving aerodynamics, heat conduction, elasticity, and material properties of arbitrary three-dimensional objects are briefly surveyed. Certain unique features of these algorithms and their advantages are sketched for use with boundary element and finite element methods.

$\textbullet$ Introduction $\textbullet$ Modeling of a Piezoelectric Actuator $\textbullet$ Inverse Hysteresis Modeling and Linearization $\textbullet$ Controller Design: PID plus Repetitive Controller $\textbullet$ Simulation Results $\textbullet$ Conclusion

The filter bank multicarrier modulation (FBMC) technique is one of multicarrier modulation technique (MCM), which is mainly used to improve channel capacity of cognitive radio (CR) network and frequency spectrum access technique. The existing FBMC System contains serial to parallel converter, normal QAM modulation, Radix2 inverse FFT, parallel to serial converter and poly phase filter. It needs high area, delay and power consumption. To further reduce the area, delay and power of FBMC structure, a new clock gating technique is applied in the QAM modulation, radix2 multipath delay commutator (R2MDC) based inverse FFT and unified addition and subtraction (UAS) based FIR filter with parallel asynchronous self time adder (PASTA). The clock gating technique is mainly used to reduce the unwanted clock switching activity. The clock gating is nothing but clock signal of flip-flops is controlled by gate (i.e.) AND gate. Hence speed is high and power consumption is low. The comparison between existing QAM and proposed QAM with clock gating technique is carried out to analyze the results. Conversely, the proposed inverse R2MDC FFT with clock gating technique is compared with the existing radix2 inverse FFT. Also the comparison between existing poly phase filter and proposed UAS based FIR filter with PASTA adder is carried out to analyze the performance, area and power consumption individually. The proposed FBMC with clock gating technique offers low power and high speed than the existing FBMC structures.

The impeller and vane diffuser for the mixed flow pump(NS550) was designed by using meridional selection program and inverse design method. We decided the meridional shape of the impeller from the meridional design parameter, such as the specific speed and maximum diameter at the impeller exit. The meridional shape of vane diffuser was set from the impeller shape, distribution of cross sectional area and maximum diffuser diameter. The angle of impeller blade and diffuser vane was designed by using inverse design method. The predicted overall performance by using commercial CFD code(ANSYS CFX-11) shown good agreement with design goals.

본 연구는 적분 방정식과 반복 "오차-수정" 개념을 이용하는 Takanashi의 이론에 기초한 초음속 실용적인 설계방법의 개발 결과로서, 형상의 수정량은 목표 압력분포와 설계대상의 압력분포와의 차를 경계조건으로 이용해 LSP 방정식을 풀므로써 계산되어진다. 이 연구에서는 Green의 정리를 이용하여 편미방정식 형태의 LSP 방정식을 적분방정식으로 변환하여 계산하는 방법을 이용하고 있다. 여기서는 Isolated wing과 wign-nacelles 두가지 경우의 설계를 예로 들었다.

A practical design method for supersonic wings has been developed. The method is based on Takanashi's method that uses integral equations and iterative "residual-correction" concept. The geometry correction is calculated by solving linearized small perturbation equation (LSP) with the difference between garget and objective surface pressure distributions as a boundary condition. In the present method, LSP equation is analytically transformed to integral equations by using the Green's theorem. Design results of an isolated wing and wing-nacelle configurations are presented here.

A new and efficient method is presented for design optimization, which is based on a computational fluid dynamics (CFD). The method is applied to design an airfoil configuration. The Navier-Stokes equations are solved for the viscous analysis of the flow, which provides the object function. The CFD analysis is then coupled with the optimization procedure that used a conjugate gradient method. During the one-dimensional search of the optimization procedure, an approximate flow analysis based on a first-order Taylor series expansion is used to reduce the computational cost, (This study is supported by Korean Ministry of Education through Research Fund)

유기 재배선층 인터포저의 고속·고집적 패키징에서 신호 무결성 확보를 위해 전송 선로의 특성 임피던스 매칭이 필수적이다. 기존 해석적 모델은 전송 선로의 물리적 구조 단순화 가정으로 실제 제작된 형상을 반영하기 어렵다. 한편, 2D 전자기장 해석기는 구조 편집기와 통합되어 에치 구조 반영이 용이하고 전송선로의 RGLC 모델 변환으로 회로 및 시스템 수준 설계 확장성이 높으나 목표 임피던스를 충족하는 전송선로 구조 결정에 필요한 시간 소요가 여전히 크다. 본 연구에서는 이러한 한계를 극복하기 위해, 사다리꼴 단면 및 다층 구조를 포함한 실제 특성을 반영한 데이터셋을 구축하고, AI 역설계 모델 통해 임피던스를 충족시키는 설계 방법론을 제안한다. 학습 모델 구축 이전, 데이터 분석을 진행하여 영역의 분포와 특성을 규명하고, 민감도 및 특이도 분석을 통해 데이터 라벨링 결과 및 특징 추출 결과를 반영된 모델 설계가 가능하도록 한다. 모델의 검증 단계에서도 데이터 약화 실험 및 전통적인 방법과의 비교를 통해 모델의 정확도와 신뢰성을 확보한다. 제안된 방법론은 인터포저 설계 자동화 및 최적화의 핵심 기술로 활용 가능할 것으로 기대한다.

In order to ensure the signal integrity of organic redistribution layer interposers for high-speed and high-density packaging, characteristic impedance matching of transmission lines is an essential task. Conventional analytical models are constrained by structural simplification of the transmission lines and cannot fully reflect actual fabricated structure. On the other hand, a 2D field-solver with structure editor could consider the etch shape and be extended to circuit or system level simulation by transforming the transmission lines into RGLC model. However, determining the parameters that ensure impedance matching still requires significant time and effort. To overcome these limitations, this study proposes an AI-based inverse design model supported by a dataset considering trapezoidal cross-sections and multilayer structures that represent realistic process characteristics. Prior to model training, data was analyzed to identify the distribution and properties of impedance-matched regions, and sensitivity-specificity evaluation was used to validate labeling and feature extraction, enabling reliable model construction. In the validation stage, the performance was assessed by data weakening experiments and comparison to traditional methods to ensure the robustness and accuracy. The proposed framework could serve as a key technology for interposer design automation and optimization.