• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.590-598
• /
• 2022

Benchmarking is an important tool to assess the performance of capital projects in the construction industry. Incorporating cost-related metrics into a benchmarking system requires an effective cost normalization process to enable meaningful comparisons among projects that were executed at different locations and times. Projects in the downstream and chemicals sector have unique characteristics compared to other types of construction projects, they require a distinctive cost normalization framework to be developed to benchmark their absolute cost performance. The purpose of this study is to develop such a framework to be used for the case of benchmarking the downstream and chemical projects for their performance assessment. The research team started with a review of existing cost normalization methodologies adopted in benchmarking systems and conducted 7 interviews to identify the current cost normalization practices used by industrial professionals. A panel of 12 experts was then convened and it held 6 review sessions to accomplish the framework development. The cost normalization framework for benchmarking downstream and chemical projects was established as a three-step procedure and it adopts a 4-element cost breakdown structure to accommodate projects submitted by both owners and contractors. It also incorporated 5 published cost indexes that are compatible with downstream and chemical projects and they were embedded into 2 options to complete the normalization process. The framework was then pilot-tested on 4 completed projects to validate its functional practicality and the downstream and chemical use case in the benchmarking system.

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.164-172
• /
• 2023

In this study, we identify the recognition of 'The First Slam Dunk', which is gaining popularity as a sports-based cartoon through big data analysis of social media channels, and provide basic data for the development and development of various contents in the sports industry. Social media channels collected detailed social big data from news provided on Naver and Google sites. Data were collected from January 1, 2023 to February 15, 2023, referring to the release date of 'The First Slam Dunk' in Korea. The collected data were 2,106 Naver news data, and 1,019 Google news data were collected. TF and TF-IDF were analyzed through text mining for these data. Through this, semantic network analysis was conducted for 60 keywords. Big data analysis programs such as Textom and UCINET were used for social big data analysis, and NetDraw was used for visualization. As a result of the study, the keyword with the high frequency in relation to the subject in consideration of TF and TF-IDF appeared 4,079 times as 'The First Slam Dunk' was the keyword with the high frequency among the frequent keywords. Next are 'Slam Dunk', 'Movie', 'Premiere', 'Animation', 'Audience', and 'Box-Office'. Based on these results, 60 high-frequency appearing keywords were extracted. After that, semantic metrics and centrality analysis were conducted. Finally, a total of 6 clusters(competing movie, cartoon, passion, premiere, attention, Box-Office) were formed through CONCOR analysis. Based on this analysis of the semantic network of 'The First Slam Dunk', basic data on the development plan of sports content were provided.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.701-720
• /
• 2023

Aerial objects are more challenging to segment than normal objects, which are usually smaller and have less textural detail. In the process of segmentation, target objects are easily omitted and misdetected, which is problematic. To alleviate these issues, we propose local aggregation feature pyramid networks (LAFPNs) and pyramid integrated context modules (PICMs) for aerial object segmentation. First, using an LAFPN, while strengthening the deep features, the extent to which low-level features interfere with high-level features is reduced, and numerous dense and small aerial targets are prevented from being mistakenly detected as a whole. Second, the PICM uses global information to guide local features, which enhances the network's comprehensive understanding of an entire image and reduces the missed detection of small aerial objects due to insufficient texture information. We evaluate our network with the MS COCO dataset using three categories: airplanes, birds, and kites. Compared with Mask R-CNN, our network achieves performance improvements of 1.7%, 4.9%, and 7.7% in terms of the AP metrics for the three categories. Without pretraining or any postprocessing, the segmentation performance of our network for aerial objects is superior to that of several recent methods based on classic algorithms.

• 한국음향학회지
• /
• 제42권2호
• /
• pp.94-101
• /
• 2023

음성 향상에서 많이 사용되는 U-Net과 같이 인코더와 디코더로 구성된 심층 신경망 모델은 skip-connection을 통해 인코더의 특징을 디코더에 연결하는 구조로 구성되어 있다. Skip-connection은 디코더에서 향상된 스펙트럼을 재구성하는데 도움을 주며 인코더를 통해 손실된 정보를 보완해줄 수 있다. 이때 skip-connection을 통해 연결되는 인코더의 특징과 디코더의 특징의 의미는 서로 다르다. 본 논문에서는 복소 스펙트럼 기반 음성 향상의 성능 향상을 위해 디코더에 연결되는 인코더의 특징을 디코더 특징의 의미에 가깝게 변환해주도록 skip-connection에 Self-Attention(SA)을 적용하는 방안을 연구하였다. SA는 시퀀스-시퀀스 문제에서 출력 시퀀스를 생성할 때, 입력 시퀀스의 가중 산술 평균을 이용하여 결정적인 부분을 집중해서 볼 수 있도록 하는 기법으로, 음성 향상 분야에서도 이를 적용함으로써 성능 향상에 효과적임을 입증하는 연구가 진행되었다. SA를 skip-connection에 적용하기 위해 인코더 특징과 디코더 특징을 이용하는 총 3가지의 방법에 대해 연구하였다. TIMIT 데이터베이스를 이용한 음성 향상 실험 결과, 제안하는 방법이 기존 skip-connection으로만 연결된 Deep Complex U-Net(DCUNET)과 비교하여 모든 성능 평가 지표에서 향상된 결과를 보였다.

• Smart Structures and Systems
• /
• 제31권2호
• /
• pp.101-111
• /
• 2023

Structural health monitoring (SHM) covers a range of damage detection strategies for buildings. In real-time, SHM provides a basis for rapid decision making to optimise the speed and economic efficiency of post-event response. Previous work introduced an SHM method based on identifying structural nonlinear hysteretic parameters and their evolution from structural force-deformation hysteresis loops in real-time. This research extends and generalises this method to investigate the impact of a wide range of flag-shaped or pinching shape nonlinear hysteretic response and its impact on the SHM accuracy. A particular focus is plastic stiffness (K_p), where accurate identification of this parameter enables accurate identification of net and total plastic deformation and plastic energy dissipated, all of which are directly related to damage and infrequently assessed in SHM. A sensitivity study using a realistic seismic case study with known ground truth values investigates the impact of hysteresis loop shape, as well as added noise, on SHM accuracy using a suite of 20 ground motions from the PEER database. Monte Carlo analysis over 22,000 simulations with different hysteresis loops and added noise resulted in absolute percentage identification error (median, (IQR)) in K_p of 1.88% (0.79, 4.94)%. Errors were larger where five events (Earthquakes #1, 6, 9, 14) have very large errors over 100% for resulted K_p as an almost entirely linear response yielded only negligible plastic response, increasing identification error. The sensitivity analysis shows accuracy is reduces to within 3% when plastic drift is induced. This method shows clear potential to provide accurate, real-time metrics of non-linear stiffness and deformation to assist rapid damage assessment and decision making, utilising algorithms significantly simpler than previous non-linear structural model-based parameter identification SHM methods.

• Journal of Preventive Medicine and Public Health
• /
• 제56권1호
• /
• pp.41-49
• /
• 2023

Objectives: Rwanda reported a stunting rate of 33% in 2020, decreasing from 38% in 2015; however, stunting remains an issue. Globally, child deaths from malnutrition stand at 45%. The best options for the early detection and treatment of stunting should be made a community policy priority, and health services remain an issue. Hence, this research aimed to develop a model for predicting stunting in Rwandan children. Methods: The Rwanda Demographic and Health Survey 2019-2020 was used as secondary data. Stratified 10-fold cross-validation was used, and different machine learning classifiers were trained to predict stunting status. The prediction models were compared using different metrics, and the best model was chosen. Results: The best model was developed with the gradient boosting classifier algorithm, with a training accuracy of 80.49% based on the performance indicators of several models. Based on a confusion matrix, the test accuracy, sensitivity, specificity, and F1 were calculated, yielding the model's ability to classify stunting cases correctly at 79.33%, identify stunted children accurately at 72.51%, and categorize non-stunted children correctly at 94.49%, with an area under the curve of 0.89. The model found that the mother's height, television, the child's age, province, mother's education, birth weight, and childbirth size were the most important predictors of stunting status. Conclusions: Therefore, machine-learning techniques may be used in Rwanda to construct an accurate model that can detect the early stages of stunting and offer the best predictive attributes to help prevent and control stunting in under five Rwandan children.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.148-162
• /
• 2023

Classification systems can significantly assist the medical sector by allowing for the precise and quick diagnosis of diseases. As a result, both doctors and patients will save time. A possible way for identifying risk variables is to use machine learning algorithms. Non-surgical technologies, such as machine learning, are trustworthy and effective in categorizing healthy and heart-disease patients, and they save time and effort. The goal of this study is to create a medical intelligent decision support system based on machine learning for the diagnosis of heart disease. We have used a mixed feature creation (MFC) technique to generate new features from the UCI Cleveland Cardiology dataset. We select the most suitable features by using Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Elimination with Random Forest feature selection (RFE-RF) and the best features of both LASSO RFE-RF (BLR) techniques. Cross-validated and grid-search methods are used to optimize the parameters of the estimator used in applying these algorithms. and classifier performance assessment metrics including classification accuracy, specificity, sensitivity, precision, and F1-Score, of each classification model, along with execution time and RMSE the results are presented independently for comparison. Our proposed work finds the best potential outcome across all available prediction models and improves the system's performance, allowing physicians to diagnose heart patients more accurately.

• 한국컴퓨터정보학회논문지
• /
• 제28권5호
• /
• pp.17-28
• /
• 2023

포장도로에서 발생하는 포트홀은 고속 주행 차량에 치명적인 영향을 미치며, 사망사고를 유발할 수 있는 도로상의 장애물이다. 이를 방지하기 위해 일반적으로는 작업자가 직접 포트홀을 탐지하는 방식을 사용해왔으나, 이는 작업자의 안전 문제와 예측하기 어려운 범주에서 발생하는 모든 포트홀을 인력으로 탐지하는 것이 비효율적이기 때문에 한계가 있다. 또한, 도로 환경과 관련된 지반 환경이 포트홀 생성에 영향을 미치기 때문에, 완벽한 포트홀 방지는 어렵다. 데이터셋 구축을 위해서는 전문가의 지도하에 라벨링 작업이 필요하지만, 이는 매우 시간과 비용이 많이 필요하다. 따라서, 본 논문에서는 Mean Teacher 기법을 사용하여 라벨링된 데이터의 샘플 수가 적더라도 지도학습보다 더욱 강인한 포트홀 이미지 분류 성능을 보여준다. 이러한 결과는 성능지표와 GradCAM을 통해 입증되었으며, 준지도학습을 사용할 때 15개의 사전 학습된 CNN 모델이 평균 90.41%의 정확도를 달성하며, 지도학습과 비교하여 2%에서 9%의 차이로 강인한 성능을 나타내는 것을 확인하였다.

• 천문학회보
• /
• 제46권1호
• /
• pp.41.2-41.2
• /
• 2021

In this study, we generate He I 1083 nm images from Solar Dynamic Observatory (SDO)/Atmospheric Imaging Assembly (AIA) images using a novel deep learning method (pix2pixHD) based on conditional Generative Adversarial Networks (cGAN). He I 1083 nm images from National Solar Observatory (NSO)/Synoptic Optical Long-term Investigations of the Sun (SOLIS) are used as target data. We make three models: single input SDO/AIA 19.3 nm image for Model I, single input 30.4 nm image for Model II, and double input (19.3 and 30.4 nm) images for Model III. We use data from 2010 October to 2015 July except for June and December for training and the remaining one for test. Major results of our study are as follows. First, the models successfully generate He I 1083 nm images with high correlations. Second, the model with two input images shows better results than those with one input image in terms of metrics such as correlation coefficient (CC) and root mean squared error (RMSE). CC and RMSE between real and AI-generated ones for the model III with 4 by 4 binnings are 0.84 and 11.80, respectively. Third, AI-generated images show well observational features such as active regions, filaments, and coronal holes. This work is meaningful in that our model can produce He I 1083 nm images with higher cadence without data gaps, which would be useful for studying the time evolution of chromosphere and coronal holes.

• 정보관리학회지
• /
• 제40권2호
• /
• pp.59-80
• /
• 2023

기존의 연구자 유형 구분 모델은 대부분 연구성과 지표를 활용해왔다. 이 연구에서는 인용 영향력이 공동연구와 관련이 있다는 점을 감안하여 인용 데이터를 활용하지 않고 공동연구 지표만으로 연구자 유형을 분석하는 새로운 방법을 모색해보았다. 공동연구 패턴과 공동연구 범위를 기준으로 연구자를 Sparse & Wide (SW) 유형, Dense & Wide (DW) 유형, Dense & Narrow (DN) 유형, Sparse & Narrow (SN) 유형의 4가지로 구분하는 모델을 제안하였다. 제안된 모델을 양자계측 분야에 적용해본 결과, 구분된 연구자 유형별로 인용지표와 공저 네트워크 지표에 차이가 있음이 통계적으로 검증되었다. 이 연구에서 제시한 공동연구 특성에 따른 연구자 유형 구분 모델은 인용정보를 필요로 하지 않으므로 연구관리 정책과 연구지원서비스 측면에서 폭넓게 활용할 수 있을 것으로 기대된다.