Deep learning-based machine vision with limited data

Kang, Hyungu Sungkyunkwan University 2025 국내박사

Deep learning approaches, represented by convolutional neural network (CNN), have achieved outstanding performance in machine vision tasks. However, their practical employment is often constrained by real-world data limitations such as incomplete labels and image distortions. This dissertation proposes effective learning strategies to enhance the performance and robustness of CNNs under three representative limited data scenarios in machine vision including partially labeled training datasets, weakly labeled training datasets, and distorted query images. First, we propose a domain-aware semi-supervised representation learning method for image analysis. Existing methods typically assume either fully labeled or entirely unlabeled datasets, making them less practical in scenarios where only a subset of instances is labeled. To address this for wafer map analysis, our method combines labeled and unlabeled wafer maps for representation learning while enforcing rotational invariance constraints. Second, we present a weakly supervised learning method for detecting defective cells (fine-grained) using only module-level (coarse-grained) annotations, significantly reducing the annotation costs compared to traditional cell-level annotation. The method is based on the assumption that all cells in a normal module are non-defective, whereas at least one defective cell exists in a defective module. By leveraging this weak supervision, accurate cell-level defect detection can be achieved without fine-grained annotations. Third, we develop a distortion-robust training method for CNNs that enables robust classification under image distortions. Instead of preprocessing or retraining with augmented data, our method incorporates consistency regularization into the supervised learning objective, encouraging the CNN to produce consistent predictions across distorted variants of an image. The effectiveness of the proposed methods was demonstrated through experimental evaluations adapted to the specific challenges of each application domain, highlighting their applicability and potential to enhance machine vision-based automation in real-world industrial environments where access to high-quality data is limited. 딥러닝, 특히 합성곱 신경망을 기반으로 한 접근법은 머신 비전 분야에서 뛰어난 성능을 보여왔다. 그러나 실제 환경에서는 불완전한 레이블 정보나 이미지 왜곡과 같은 다양한 데이터 제약으로 인해 이러한 모델의 실질적인 적용에 한계가 존재한다. 본 학위논문에서는 머신 비전에서 흔히 발생하는 세 가지 대표적인 데이터 제약 상황인 부분적으로 레이블링된 학습 데이터셋, 대분류로 레이블링된 학습 데이터셋, 왜곡된 쿼리 이미지에 대응하기 위한 효과적인 학습 전략을 제안한다. 첫째, 이미지 분석을 위해 도메인 특성을 추가한 준지도 표현 학습 기법을 제안한다. 기존의 표현 학습 기법들은 완전히 레이블링된 데이터 또는 전혀 레이블되지 않은 데이터만을 가정하는 경우가 많아, 일부만 레이블이 있는 데이터셋 환경에서는 온전히 정보를 활용할 수 없다. 본 연구에서는 웨이퍼 맵 분석을 위해 레이블이 있는 웨이퍼 맵과 레이블이 없는 웨이퍼 맵을 함께 활용하여 표현을 학습하고, 표현 학습에 회전 불변성 제약을 적용함으로써 시각화, 클러스터링, 검색, 분류와 같은 후속 과업에서 더 효과적인 표현 학습을 가능하게 하였다. 둘째, 모듈 단위(대분류) 레이블만을 활용하여 셀 단위(세부) 결함을 탐지하는 약지도 학습 방법을 제안한다. 제안 방법은 정상 모듈의 모든 셀은 정상이며, 불량 모듈에는 최소 하나 이상의 결함 셀이 존재한다는 가정에 기반한다. 이를 통해 고비용의 구체적인 레이블링 없이도 셀 단위 결함을 정확하게 예측할 수 있다. 셋째, 이미지 왜곡 하에서도 강건한 분류가 가능하도록 합성곱 신경망을 학습시키는 일관성 정규화 기반 왜곡 강건 학습 기법을 제안한다. 기존의 왜곡 보정이나 증대 기반 접근 방식과 달리, 제안 방법에서는 일관성 정규화를 지도학습 목적 함수에 추가하여, 원본 이미지와 왜곡 이미지 간 예측의 일관성을 유지하도록 유도하였다. 제안 방법은 각각의 제약 조건에 맞춘 실험을 통해 그 효과가 실증되었으며, 이는 고품질 데이터 확보가 어려운 실제 산업 현장에서도 효율적인 머신 비전 적용을 통한 효율성 개선을 기대한다.

Knowledge distillation of regression neural network

Kang, Myeonginn Sungkyunkwan University 2024 국내박사

최근 다양한 산업 분야에서 인공신경망 적용이 큰 성공을 거두고 있다. 그러나 거대 인공신경망은 많은 양의 계산과 자원을 필요로 하기 때문에 자원의 제약이 있는 환경에서의 활용에 어려움이 있다. 이를 해결하기 위해 거대 인공신경망 모델 (teacher)을 작은 인공신경망 모델 (student)로 압축하는 knowledge distillation 연구가 활발히 진행 중이다. 기존 knowledge distillation 방법들은 teacher network를 학습시키는데 사용했던 학습 데이터셋이 모두 재사용 가능함을 가정한다. 그러나 현실 문제에서는 다양한 제약으로 인해 학습 데이터셋이 항상 온전히 보존되거나 공개되지 않을 수 있다. 이를 해결하기 위해 학습 데이터셋이 일부 사용가능한 상황을 가정한 knowledge distillation 방법들이 제안되었지만 모두 분류 문제에 집중하고있다. 본 논문에서는 회귀 인공신경망에 적용될 수 있는 새로운 knowledge distillation 방법들을 제안한다. 첫째로, 학습 데이터셋 사용이 불가능한 상황에서 회귀 인공신경망에 적용 가능한 data-free knowledge distillation 방법을 제안한다. 거대한 teacher network가 주어졌을 때, generator network를 도입하여 teacher network의 지식을 작은 student network로 전이한다. Generator와 student network는 적대적 학습 방식을 사용해 동시에 학습된다. Generator network는 teacher와 student의 예측 차가 커지도록 하는 인공 데이터 포인트를 생성하도록 학습되고, 반면에 student network는 생성된 인공 데이터 포인트에 대한 teacher와 student의 예측 차를 줄이도록 학습된다. 둘째로, 학습 데이터셋이 일부 재사용 가능한 상황에서 회귀 인공신경망에 적용 가능한 새로운 knowledge distillation 방법인 teacher-student matching (TSM)을 제안한다. TSM은 세 개의 학습 방식을 포함한다: Perturbation-based matching (PM), Adversarial belief matching (ABM), Gradient matching (GM). TSM은 학습 데이터 부족 상황에서 기존의 knowledge distillation 방법의 성능 개선을 위해 추가 적용 방법으로 사용될 수 있다. 마지막으로, 학습 데이터셋 사용 불가능한 상황에서 회귀 인공신경망의 예측 불확실성 정량화를 위한 대리 기법을 제안한다. 이를 위해 첫번째로 제안한 회귀 인공신경망을 위한 data-free knowledge distillation 방법을 활용한다. Data-free knowledge distillation 방법과 추가적인 세 개의 대리 기법을 사용한다: Input perturbation, Gradient norm, MC-dropout, Knowledge distillation. 쿼리 데이터 포인트가 주어졌을 때, 각 대리 기법은 학습 데이터셋 사용 없이 회귀 인공신경망을 사용해 예측 불확실성을 정량화한다. 회귀 벤치마크 데이터셋에 대한 실험을 통해 각 제안 방법의 효과를 확인하였다. Artificial neural networks have been widely used in various industrial fields. For more efficient use of artificial neural networks in environments with limited computing resources, knowledge distillation is actively applied to compress a large neural network (teacher) to a smaller neural network (student). Conventional knowledge distillation requires a training dataset that was used to build the teacher network. However, the training dataset is often not fully accessible in many real-world applications due to some practical issues. To solve this problem, there are existing methods of knowledge distillation with insufficient training data, but they only focus on classification problems. This dissertation proposes novel knowledge distillation methods that can be applied to a regression network. First, we propose data-free knowledge distillation of the regression network. Given a large teacher network, a generator network is adopted to transfer the knowledge in the teacher network to a smaller student network. The generator and student networks are simultaneously trained in an adversarial manner. The generator network is trained to create synthetic data on which the teacher and student networks make different predictions, with the student network being trained to mimic the teacher network's predictions. Second, we propose knowledge distillation of the regression network with insufficient training data, called teacher-student matching (TSM). TSM includes three additional learning objectives that are modifications of existing knowledge distillation methods to make the student better emulate the prediction capability of the teacher: perturbation-based matching (PM), adversarial belief matching (ABM), and gradient matching (GM). TSM can be used as an add-on to any existing knowledge distillation method to improve its effectiveness under severe data insufficiency. Third, we propose a surrogate approach to quantify the prediction uncertainty of the regression network without any training data. To do this, we utilize the data-free knowledge distillation of the regression network. While the original aim of knowledge distillation is to compress the large neural network, we expand the use of knowledge distillation to quantify the prediction uncertainty. Four surrogate measures are introduced: Input perturbation, Gradient norm, MC-dropout, and Knowledge distillation. For a query data point, each surrogate measure can be calculated by using the regression network only to estimate the prediction uncertainty. The effectiveness of the proposed methods is demonstrated through experiments on regression benchmark datasets.

Combining deep learning with domain knowledge for wafer map pattern classification

Kang, Hyungu Sungkyunkwan University 2022 국내석사

Recently, machine learning has been effectively applied in the automation of wafer map pattern classification in semiconductor manufacturing. One conventional approach is to extract handcrafted features from a wafer map and build an off-the-shelf classifier on top of the features. Another approach is to use a convolutional neural network that operates directly on a wafer map. These two approaches have different strengths for different classes of wafer map defect patterns. In this study, we present a hybrid method that leverages the advantages of both approaches to improve the classification accuracy. First, we build two base classifiers using each of the approaches. Then, we build a stacking ensemble that combines the outputs of these base classifiers for the final prediction. The stacking ensemble classifies a wafer map by assigning a larger weight to the output of the superior base classifier with respect to each defect class. We demonstrate the effectiveness of the proposed method using real-world data from a semiconductor manufacturer. 최근 반도체 제조 산업에서 웨이퍼 맵의 불량 범주 분류 자동화를 위해 기계학습이 효과적으로 적용되고 있다. 기존의 접근법 중 하나는 전문가 지식을 활용하여 웨이퍼 맵에서 수동으로 특성을 추출한 후, 이 특성을 이용하여 기성 분류 모델을 학습시키는 방법이다. 또 다른 접근법은 웨이퍼 맵 자체를 입력으로 사용하여 합성곱 신경망으로 학습시키는 딥러닝 방법이다. 본 연구에서는 분류 정확도를 높이기 위해 전문가 지식과 딥러닝을 결합한 하이브리드 방법을 제안한다. 먼저 수동 특성 추출한 뒤 기성 분류 모델을 학습하는 방법과 합성곱 신경망으로 학습하는 방법을 이용하여 두 개의 단일 모델을 만들었다. 그 후 단일 모델들의 예측 결과값을 이용해 스태킹 앙상블 모델을 구축하였다. 단일 모델들은 특성 추출 방식의 차이로 인해 학습 데이터셋의 크기에 따라 성능 차이가 발생하며 서로 다른 불량 범주에 대해 다른 강점을 갖는다. 따라서 제안 방법은 불량 범주마다 더 우세한 모델의 예측값에 높은 가중치를 부여함으로써 두 접근법의 장점을 모두 끌어올리며 최종적으로 예측 정확도를 향상한다. 실제 반도체 제조 현장의 데이터인 WM-811K 데이터셋을 사용하여 다양한 학습 데이터셋의 크기에 대해 제안 방법의 성능이 단일 모델에 비해 개선됨을 검증하였다.

Characteristics and restrictiveness of rules of origin in the Korea-Australia FTA : an empirical analysis

Kang, Narae Korea University 2017 국내석사

Rules of origin (RoO) are necessary and important in free trade agreements (FTAs), given the fact that their function is to prevent trade deflection. However, with the proliferation of FTAs over the last two decades, diverse RoO among the different FTAs have resulted in increases in the cost of complying with the complex requirement of RoO. In other words, RoO can play a role as trade barriers. Thus, it is critical to find out how demanding RoO are, in order not to limit exporters’ opportunities for more markets. On this ground, this paper analyzed the restrictiveness of RoO, which can be hidden protection, with the example of the bilateral FTA between Korea and Australia, using a method proposed by Estevadeordal (2000). It revealed that the restrictiveness index of the Korea-Australia FTA is 4.26, lower than those of the Korea-China FTA (4.43), the Korea-EFTA FTA (4.53), the Korea-ASEAN FTA (4.59), and the Korea-Chile FTA (4.82). This low restrictiveness index of the Korea-Australia FTA can be explained mainly by the complementary industrial and trade structure and significant amount of trade volume between the two countries. Then, examining restrictiveness of RoO for nineteen sectors, it is found that the agricultural and animal sector is the most restrictive among all the sectors, whereas the chemical and electrical equipment sectors are less restrictive. In addition, the analysis has shown that the restrictiveness of RoO in major five sectors in the Korea-Australia FTA lies between those of the China-Australia FTA and the Japan-Australia FTA. Given the results of this research, even though RoO in the Korea-Australia FTA are less restrictive than those of Korea’s other FTAs, Korea should adopt a more strategic approach to trade policy, considering the restrictiveness of RoO and Korea’s position in the Australian market vis-à-vis China and Japan. Furthermore, the Korean government needs to review these factors for renegotiation of the Korea-Australia FTA in the future.

(A) study on high speed and low power circuit designs for asynchronized parallel wire link interface of NAND flash memory

Kang, Kyungtae Sungkyunkwan university 2019 국내박사

As higher operating frequency is required in NAND Flash Memory's application, as much more power consumption increases because the techniques to provide the stable data transfer such as DCC (Duty Cycle Corrector), per-pin de-skewing, and pre-emphasis transmitter are adopted. In this thesis paper, a study for minimizing these additional power consumption is presented by using the proposed circuits with maintain its own performance. First of all, the proposed DCC consists of a loop delay chain for edge alignment, and a falling edge modulator to enhance the phase interpolating limit. These features improved the duty offset correction range at high frequency besides low frequency with fast lock time and without degrading the signal integrity of the junction of a phase interpolator. The proposed DCC was fabricated in a TSMC 55nm CMOS technology with 1 V supply voltage, the area occupied 0.0186mm2. The measured results show that the duty cycle error of the output clock was adjusted to less than 2% when the duty cycle ratio of the input clock was changed from 80% to 20% at 1 GHz, and the lock cycle consumed only 5 cycles. At 1 GHz, the power consumption was 2.09mW and the peak-to-peak jitter was measured at 12.53 ps. Second of all, it presents an open-loop per pin skew compensation with lock fault detection. The proposed circuit employs an open-loop reference selector, a 2-stage open-loop delay lock method which is separated by a coarse and fine lock for fast lock-in time, and a lock fault detecting scheme to prevent lock fault by dead-zone of samplers. We also applied a unidirectional scan method ahead the fine lock stage to minimize pin-to-pin skew errors after calibration. The circuit was fabricated with TSMC 55nm CMOS technology with a 1V supply voltage and an area of 0.0036mm2 for one de-skewing module. The measured result shows that the skew error at 1GHz operation was reduced to less than 6 ps after skew calibration when the skew between IO pins was 230 ps, and the lock-in time was 11 clock cycles. Third of all, by modulating a post-cursor signal in 2-tap pre-emphasis transmitter, dissipation current of data transfer is reduced by 6% at 3.2Gbps, compared to conventional 2-tap pre-emphasis transmitter. This modulated post-cursor in this paper serves to reduce this static current dissipation period caused by summing two different polarity of the main and post cursor in a transmitter output driver stage. The proposed power-efficient pre-emphasis transmitter was designed in 1V supply using TSMC 55nm process and simulated under the channel environment of a multiple-stacked NAND Flash Memory.

Fabrication of solid electrolyte sheets with glass frit as a sintering aid for MLCB applications

Kang Min Lee 고려대학교 대학원 2025 국내석사

The multilayer ceramic battery (MLCB) has recently gained significant interest as a promising solid-state energy storage system for compact and microelectronic devices. However, the widely adopted oxide-based solid electrolyte, Li₁.₃Al₀.₃Ti₁.₇(PO₄)₃ (LATP), generally requires a high sintering temperature exceeding 1000 °C, which imposes critical limitations on co-sintering with electrode materials and restricts scalability toward large-area fabrication. To overcome this challenge, a novel low-temperature sintering aid composed of Li₂O–B₂O₃–V₂O₅ (LVBO) glass was synthesized through a spray pyrolysis method, yielding uniform, spherical particles with clean surfaces. The synthesized LVBO glass exhibited a low glass transition temperature in the range of 550–650 °C, which enabled partial liquid-phase formation during sintering, thereby facilitating particle rearrangement and densification of the LATP matrix at reduced temperatures. Upon incorporating 1 wt% of LVBO powder into the LATP, dense electrolyte pellets were successfully fabricated at a significantly lower sintering temperature of 650 °C. Additionally, the tape casting technique was employed to produce a green ceramic electrolyte sheet with an initial thickness of 50 μm, which was reduced to approximately 15 μm following thermal processing. The resulting LATP–LVBO composite exhibited a high ionic conductivity of 9.249 × 10⁻⁶ S/cm, along with excellent mechanical integrity and a uniform microstructure. These findings demonstrate the effectiveness of spray-pyrolyzed LVBO glass as a sintering additive for promoting low-temperature densification of LATP. Moreover, the compatibility of this material with scalable techniques such as tape casting and multilayer stacking confirms its feasibility for integration into large-area MLCB devices. 다층 세라믹 전지(MLCB)는 소형 및 마이크로 전자기 기기용 차세대 고체 에너지 저장장치로 주목받고 있다. 그러나 대표적인 고체 산화물 전해질인 Li₁.₃Al₀.₃Ti₁.₇(PO₄)₃(LATP)는 일반적으로 1000 °C 이상의 고온 소결을 요구하며, 이는 전극 재료와의 동시 소결(co-sintering) 및 대면적 공정 적용에 있어 큰 제약으로 작용한다. 이러한 문제를 해결하기 위해, 본 연구에서는 분무 열분해(Spray Pyrolysis) 공정을 통해 Li₂O–B₂O₃–V₂O₅(LVBO) 기반의 유리계 소결 보조제를 합성하였다. 합성된 LVBO 유리는 균일한 입자 크기와 깨끗한 표면을 가지며, 약 550–650 °C의 낮은 유리전이온도(glass transition temperature, Tg)를 나타낸다. 이는 저온 소결 시 부분적인 액상 상을 형성하여 입자 재배열 및 치밀화 과정을 촉진함으로써, 낮은 온도에서도 고체 전해질층의 조밀한 형성을 가능하게 한다. LATP 분말에 1 wt%의 LVBO를 첨가함으로써, 650 °C의 낮은 소결 온도에서 고밀도의 LATP 펠릿 제조에 성공하였다. 또한, 테이프 캐스팅 공정을 통해 초기 50 μm 두께의 세라믹 전해질 시트를 제작하였으며, 최종적으로15 μm 두께의 얇은 고체 전해질층을 구현하였다. LATP–LVBO 복합체는 약 9.249 × 10⁻⁶  S/cm 수준의 우수한 이온전도도, 충분한 기계적 강도 및 균질한 미세구조를 나타냈다. 본 연구는 분무 열분해 공정으로 합성된 LVBO 유리가 LATP 고체 전해질의 저온 치밀화에 효과적인 소결 보조제로 작용함을 확인하였으며, 테이프 캐스팅 및 다층 적층 공정을 통해 대면적 MLCB 제조에 응용 가능함을 입증하였다.

Anti-cancer mechanisms of MICA nanoparticle or PDE4D inhibitor in human cancer cells

강태욱 Seoul National University 2016 국내박사

Multilayered nano film fabrication using geometric electrodes and free-standing electrospinning technology

강동희 Chonnam National University 2018 국내석사

Electrospinning is a nano-scale fiber production method with various polymer materials. This technique allows simple fiber diameters control by changing the physical conditions such as applied voltage and polymer solution viscosity during the fabrication process. The electrospun polymer fibers form a thin porous film with high surface area to volume ratio. Due to these unique characteristics, it is widely used for many application fields such as textiles, filters, biomedicine, drug delivery, energy, and sensors. For the electrospun film fabrication, typical electrospinning process is based on planar substrate equipment. In planar substrate based electrospinning method purpose to produce fiber with regular diameter that is necessary to uniform electric field on planar surfaces. Planar substrate based electrospinning process has obstacles to apply non-planar and conductive material surface. To solve this problem, substrate-free electrospinning method has to be developed. In the electrospinning history, various wire-based electrodes have been proposed for specific nano-porous film fabrication and applications. A simple physics in electrospinning technique offer the possibilities for using wire-based electrodes such as circle, rectangular, parallel wires and so on. However, experimental approaches are limited due to difficulties to find exact working condition and control the physical variables. Here, we investigate a circle electrode in the electrospinning process for the fabrication of substrate-free, freestanding nanofiber films. Circle electrode-based electrospinning is controlled by varying the applied voltage and the metal needle tip-to-collector distance. A hollow cylinder is used as the circle electrode to ensure stable electrostatic conditions on the top surface of the cylinder collector. Numerical simulation is used to determine the electric field in the electrospinning process for quantitative analysis. The freestanding electrospun film can be transferred as a coating to a non-planar surface without using additional processes. Thus, the electrospinning process using the circle electrode collector was successfully optimized for freestanding film fabrication. Substrate-free electrospun films can be applied to multifunctional filters for dust filtration with humidity blocking. Regarding future applications, the circle electrode-based electrospinning process verified the potential for integrating freestanding electrospun films into organs-on-chip, biochemical sensors, and microfluidic analysis systems.

Spatially integrated densely enhanced relay system for next generation mobile communication : performance analysis and optimization

강혜중 Korea University 2014 국내박사

Activity-based dynamic lifecycle assessment in building construction project

강고운 Korea University 2018 국내박사

LCA is an intuitive and quantitative tool for assessing environmental impacts and is also widely applied for environmental assessment of buildings. Despite the high variability of buildings due to their long life span, existing research and evaluation tools mainly derive the building environmental impact as a single deterministic value. Point forecast is useful for short-term prediction, but band forecast is more effective for long-term strategy. The band forecast is appropriate for the whole life environmental impact assessment of buildings with long life span. In particular, band forecast based on stochastic approaches are also useful for quantitative environmental risks analysis. Current point forecast of the environmental impact of buildings is due to the limitations of the static methodology in traditional LCA. Overcoming the methodological obstacle, the concept and expression of dynamic LCA came up and related research has received more and more attention by several researchers. In addition, the effects of recurrent intervention activities over the building lifespan are often overlooked in current LCA. Due to the increasing building assets, the facility management and asset management is becoming critical. Nowadays, maintenance is as important as the initial construction. Still lots of current research of LCA focuses on the initial construction and deconstruction in embodied impact. Recurrent embodied impact associated with the replacement of building materials and components is directly affected by the service life of building materials and buildings themselves, which is related to the performance or condition of them. However, the significance of building performance and recurrent embodied emission on the whole life environmental impact of a building is not well understood. Toward the improvement of reliability in environmental impact assessment in buildings, understanding the structure and behavior of emission in building system is the first step. The shortcomings in current methodology result in a vague display of emission sources according to the deterministic approach and aggregated information. In this paper, two main obstacles through the review in current building LCA and carbon estimation methodology identified in author’s philosophy would be addressed; (1) uncomprehensive breakdown structure and (2) little consideration of interrelationship among the time-varying factors. The objective of the research is to develop a methodology for a better understanding of the dynamic interaction of parameters used in building LCA and the long-term behavior of the components’ environmental impact in the entire building system. This research is conducted according to the following step. First, limitation in building LCA and theoretical knowledge is discussed through the literature review. Second, activity-based LCA approach is proposed and dynamic model for recurrent embodied impacts in usage stage is described. Third, collecting the field data and establishing the assumptions based on literature, a case study is performed for operability of the proposed methodology. This study has an academic contribution in that it suggests a methodology for proper assumption related to the dynamic factors in the embodied environmental impact analysis of the building and review of the assumption through the systematic analysis. Maintenance activities mainly depend on changes in building performance over time, but the static methodology of traditional LCA does not take this variability into account. This study presents a dynamic analysis method of the environmental impact of buildings combining dynamic simulation technique. As a result of the analysis, it was found that the environmental impacts changed by more than 10% according to the variation of the maintenance strategy intensity and the required performance level. This application of the developed methodology can contribute to long-term behavior understanding of the embodied environmental impact and probabilistic estimation in future building LCA. In particular, this study defined the feedback relationship between building performance and maintenance activities dealing with dynamic LCA through system thinking, which is closely related to the facility management applying condition-based maintenance principles. It is expected the relationship between building performance and maintenance activities found in this study can contribute to maintenance planning and lifecycle cost estimation. Furthermore, the results of this study can contribute to the industry displaying the information in detail―the environmental impact for each trade or object, the effect of dynamic factors on emissions, etc.―which was not known in the existing analysis. In order to find mitigation alternative, it is possible to readily analyze the emissions for material type and quantity variation. In addition, from the viewpoint of policy makers of the certification regulation, It support to determine the rational value of the baseline building standard for strengthening the regulations through the probabilistic estimation that reflects the dynamic factors.