• Smart Structures and Systems
• /
• 제32권3호
• /
• pp.135-151
• /
• 2023

Using 3D asphalt pavement surface data, a deep and multiscale network named CrackNet-M is proposed in this paper for pixel-level crack detection for improvements in both accuracy and robustness. The CrackNet-M consists of four function-specific architectural modules: a central branch net (CBN), a crack map enhancement (CME) module, three pooling feature pyramids (PFP), and an output layer. The CBN maintains crack boundaries using no pooling reductions throughout all convolutional layers. The CME applies a pooling layer to enhance potential thin cracks for better continuity, consuming no data loss and attenuation when working jointly with CBN. The PFP modules implement direct down-sampling and pyramidal up-sampling with multiscale contexts specifically for the detection of thick cracks and exclusion of non-crack patterns. Finally, the output layer is optimized with a skip layer supervision technique proposed to further improve the network performance. Compared with traditional supervisions, the skip layer supervision brings about not only significant performance gains with respect to both accuracy and robustness but a faster convergence rate. CrackNet-M was trained on a total of 2,500 pixel-wise annotated 3D pavement images and finely scaled with another 200 images with full considerations on accuracy and efficiency. CrackNet-M can potentially achieve crack detection in real-time with a processing speed of 40 ms/image. The experimental results on 500 testing images demonstrate that CrackNet-M can effectively detect both thick and thin cracks from various pavement surfaces with a high level of Precision (94.28%), Recall (93.89%), and F-measure (94.04%). In addition, the proposed CrackNet-M compares favorably to other well-developed networks with respect to the detection of thin cracks as well as the removal of shoulder drop-offs.

• 대한안전경영과학회지
• /
• 제10권3호
• /
• pp.245-251
• /
• 2008

The research proposes three ANOVA(Analysis of Variance) tests using expected mean square(EMS) algorithms in various split-plot designs. The variance tests consist of Never-Pool test, Sometimes-Pool test and Always-Pool test. This paper also presents two EMS algorithms such as standard method and easy method. These algorithms are useful to make a decision rule for pooling. Numerical examples are illustrated for various split-plot designs such as split-plot designs, split-split-plot designs, repetition split-plot designs, and nested designs. Pragmatically, the results are summarized and compared with popular ANOVA spreadsheets and data model equations.

• Journal of information and communication convergence engineering
• /
• 제16권2호
• /
• pp.106-113
• /
• 2018

Although deep learning methods of convolutional neural networks (CNNs) and long-/short-term memory (LSTM) are widely used for text categorization, they still have certain shortcomings. CNNs require that the text retain some order, that the pooling lengths be identical, and that collateral analysis is impossible; In case of LSTM, it requires the unidirectional operation and the inputs/outputs are very complex. Against these problems, we thus improved these traditional deep learning methods in the following ways: We created collateral CNNs accepting disorder and variable-length pooling, and we removed the input/output gates when creating bidirectional LSTMs. We have used four benchmark datasets for topic and sentiment classification using the new methods that we propose. The best results were obtained by combining LTSM regional embeddings with data convolution. Our method is better than all previous methods (including deep learning methods) in terms of topic and sentiment classification.

• Journal of Preventive Medicine and Public Health
• /
• 제55권5호
• /
• pp.464-474
• /
• 2022

Objectives: We introduced the cohort studies included in the Korean Cohort Consortium (KCC), focusing on large-scale cohort studies established in Korea with a prolonged follow-up period. Moreover, we also provided projections of the follow-up and estimates of the sample size that would be necessary for big-data analyses based on pooling established cohort studies, including population-based genomic studies. Methods: We mainly focused on the characteristics of individual cohort studies from the KCC. We developed "PROFAN", a Shiny application for projecting the follow-up period to achieve a certain number of cases when pooling established cohort studies. As examples, we projected the follow-up periods for 5000 cases of gastric cancer, 2500 cases of prostate and breast cancer, and 500 cases of non-Hodgkin lymphoma. The sample sizes for sequencing-based analyses based on a 1:1 case-control study were also calculated. Results: The KCC consisted of 8 individual cohort studies, of which 3 were community-based and 5 were health screening-based cohorts. The population-based cohort studies were mainly organized by Korean government agencies and research institutes. The projected follow-up period was at least 10 years to achieve 5000 cases based on a cohort of 0.5 million participants. The mean of the minimum to maximum sample sizes for performing sequencing analyses was 5917-72 102. Conclusions: We propose an approach to establish a large-scale consortium based on the standardization and harmonization of existing cohort studies to obtain adequate statistical power with a sufficient sample size to analyze high-risk groups or rare cancer subtypes.

• 항공우주시스템공학회지
• /
• 제8권4호
• /
• pp.39-43
• /
• 2014

This paper examines the statistical process that should be performed with caution in the composite material qualification and equivalency process, and describes statistically significant considerations on outlier finding and handling process, data pooling through normalization process, review for data distributions and design allowables determination process for structural analysis. Based on these considerations, the need for guidance on statistical process for aircraft manufacturers who use the composite material properties database are proposed.

• 통상정보연구
• /
• 제15권2호
• /
• pp.71-82
• /
• 2013

자동차 공급망은 자동차기업들이 글로벌화되어 아웃소싱이 일반화되고 해외생산기지를 구축함에 따라 지속적으로 복잡하게 되었다. 자동차산업에서 순환물류용기 (RPC: Returnable Plastic Container) 의 사용은 물류효율과 비용절감 측면에서 매우 일반화되어 있으나 주로 내수용으로 활용하고 있으며 국제무역용으로는 절대적인 운송거리가 길고 운영관리가 복잡해져 크게 활용되지 않고 있다. 이 연구는 시뮬레이션을 통하여 1회용기와 반복사용이 가능한 순환물류용기를 pooling system으로 적용하는 경우 기업에 미치는 경제적 영향을 비교하였다. 결론적으로 미국과 같은 장거리 국제물류에서는 순환물류용기의 사용이 어려우나 중국과 일본과 같이 비교적 단거리 국제무역에서는 pooling 시스템의 도입으로 경제적으로 타당한 것으로 나타났다. 이 연구결과는 국제공급망 환경에 따라 경제적으로 최적의 포장방법과 형태의 변화가 필요함을 밝혔다. 다만, 국제무역상 발생하는 통관상의 복잡함, 관세, 국내와 해외 물류환경의 상이로 인한 효율성 저하 등의 문제는 하기 위해서는 보다 많은 연구가 필요하다.

• Applied Microscopy
• /
• 제48권3호
• /
• pp.55-61
• /
• 2018

The synaptic vesicle is a specialized structure in presynaptic terminals that stores various neurotransmitters. The actin filament has been proposed for playing an important role in mobilizing synaptic vesicles. To understand the role of actin filament on synaptic vesicle pooling, we characterized synaptic vesicles and actin filament after treatment of brain-derived neurotrophic factor (BDNF) or Latrunculin A on primary cultured neuron from rat embryo hippocampus. Western blots revealed that BDNF treatment increased the expression of synapsin I protein, but Latrunculin A treatment decreased the synapsin I protein expression. The increased expression of synapsin I after BDNF disappeared by the treatment of Latrunculin A. Three-dimensional (3D) tomography of synapse showed that more synaptic vesicles localized near the active zone and total number of synaptic vesicles increased after treatment of BDNF. But the number of synaptic vesicle was 2.5-fold reduced in presynaptic terminals and the loss of filamentous network was observed after Latrunculin A application. The treatment of Latruculin A after preincubation of BDNF group showed that synaptic vesicle number was similar to that of control group, but filamentous structures were not restored. These data suggest that the actin filament plays a significant role in synaptic vesicles pooling in presynaptic terminals.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제7권10호
• /
• pp.935-943
• /
• 2017

많은 양의 데이터 기반으로 학습하는 neural network 중 이미지 분류나 음성 인식 등에 사용되어 지고 있는 CNN(Convolution neural network)는 현재까지도 우수한 성능을 가진 구조로 계속적으로 발전되고 있다. 제한된 자원을 가진 임베디드 시스템에서 활용하기에는 많은 어려움이 있다. 그래서 미리 학습된 가중치를 사용하지만 여전히 한계점이 있기 때문에 이를 해결하기 위해 GPU의 범용 연산을 위해서 사용하는 GP-GPU(General-Purpose computing on Graphics Processing Units)를 활용하는 추세다. CNN은 단순하고 반복적인 연산을 수행하기 때문에 SIMT(Single Instruction Multiple Thread)기반의 GPGPU에서 스레드 할당과 활용 방법에 따라 연산 속도가 많이 달라진다. 스레드로 Convolution 연산과 Pooling 연산을 수행할 때 쉬어야 하는 스레드가 발생하는 데 이러한 문제를 해결하기 위해 남은 스레드가 다음 피쳐맵과 커널 계산에 활용되는 방법을 사용함으로써 연산 속도를 증가시켰다.

• 한국국방경영분석학회지
• /
• 제8권2호
• /
• pp.3-16
• /
• 1982

Under the assumption that the size of military expenditures is largely determined by economic potential and military requirements as well, this paper conducts an econometric analysis for the purpose of predicting Korea's military expenditures using a technique of pooling time-series data (1967-1976) and cross-section data(95 countries) on the percentage of military expenditures to GNP (Cross National Product) and economic growth rate.

• 아시안잔디학회지
• /
• 제9권2호
• /
• pp.131-136
• /
• 1995

The herb, shrub, understory and canopy strata, which arbitrarily delineated by size classes, were sampled separately. The former one were sampled by the pin-point quadrat method. And remaining three by size quadrats, diversity (H= =$\Sigma$ Pi log Pi) of of each stratum was estimated for each set of census data. Species diversity within a stratum was independent of sample plot size above a minimum cumulative area. Diversity based on plotless and plot samples could he determined by the same equation, and by pooling the data needed to estimate diversity of each stratum.