• Korean Chemical Engineering Research
• /
• v.62 no.3
• /
• pp.214-224
• /
• 2024

Valves play an essential role in a chemical plant such as regulating fluid flow and pressure. Therefore, optimal selection of the valve size and type is essential task. Valve size and type have been selected based on theoretical formulas about calculating valve sizing coefficient (Cv). However, this approach has limitations such as requiring expert knowledge and consuming substantial time and costs. Herein, this study developed a model for predicting valve sizes and types using machine learning. We developed models using four algorithms: ANN, Random Forest, XGBoost, and Catboost and model performances were evaluated using NRMSE & R² score for size prediction and F1 score for type prediction. Additionally, a case study was conducted to explore the impact of phases on valve selection, using four datasets: total fluids, liquids, gases, and steam. As a result of the study, for valve size prediction, total fluid, liquid, and gas dataset demonstrated the best performance with Catboost (Based on R², total: 0.99216, liquid: 0.98602, gas: 0.99300. Based on NRMSE, total: 0.04072, liquid: 0.04886, gas: 0.03619) and steam dataset showed the best performance with RandomForest (R²: 0.99028, NRMSE: 0.03493). For valve type prediction, Catboost outperformed all datasets with the highest F1 scores (total: 0.95766, liquids: 0.96264, gases: 0.95770, steam: 1.0000). In Engineering Procurement Construction industry, the proposed fluid-specific machine learning-based model is expected to guide the selection of suitable valves based on given process conditions and facilitate faster decision-making.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.69-79
• /
• 2024

Field geotechnical data are obtained from various field and laboratory tests and are documented in geotechnical investigation reports. For efficient design and construction, digitizing these geotechnical parameters is essential. However, current practices involve manual data entry, which is time-consuming, labor-intensive, and prone to errors. Thus, this study proposes an automatic data extraction method from geotechnical investigation reports using image-based deep learning models and text-mining techniques. A deep-learning-based page classification model and a text-searching algorithm were employed to classify geotechnical investigation report pages with 100% accuracy. Computer vision algorithms were utilized to identify valid data regions within report pages, and text analysis was used to match and extract the corresponding geotechnical data. The proposed model was validated using a dataset of 205 geotechnical investigation reports, achieving an average data extraction accuracy of 93.0%. Finally, a user-interface-based program was developed to enhance the practical application of the extraction model. It allowed users to upload PDF files of geotechnical investigation reports, automatically analyze these reports, and extract and edit data. This approach is expected to improve the efficiency and accuracy of digitizing geotechnical investigation reports and building geotechnical databases.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1307-1307
• /
• 2024

Recent research on heavy equipment has been conducted for the purposes of enhanced safety, productivity improvement, and carbon neutrality at construction sites. A sensor-based approach is being explored to monitor the location and movements of heavy equipment in real time. However, it poses significant challenges in terms of time and cost as multiple sensors should be installed on numerous heavy equipment at construction sites. In addition, there is a limitation in identifying the collaboration or interference between two or more heavy equipment. In light of this, a vision-based deep learning approach is being actively conducted to effectively respond to various working conditions and dynamic environments. To enhance the performance of a vision-based activity recognition model, it is essential to secure a sufficient amount of training datasets (i.e., video datasets collected from actual construction sites). However, due to safety and security issues at construction sites, there are limitations in adequately collecting training dataset under various situations and environmental conditions. In addition, the videos feature a sequence of multiple activities of heavy equipment, making it challenging to clearly distinguish the boundaries between preceding and subsequent activities. To address these challenges, this study proposed a domain adaptation in vision-based transfer learning for automated excavator activity recognition utilizing 3D ResNet (residual deep neural network). Particularly, this study aimed to identify the optimal depth of 3D ResNet (i.e., the number of layers of the feature extractor) suitable for domain adaptation via fine-tuning process. To achieve this, this study sought to evaluate the activity recognition performance of five 3D ResNet models with 18, 34, 50, 101, and 152 layers, which used two consecutive videos with multiple activities (5 mins, 33 secs and 10 mins, 6 secs) collected from actual construction sites. First, pretrained weights from large-scale datasets (i.e., Kinetic-700 and Moment in Time (MiT)) in other domains (e.g., humans, animals, natural phenomena) were utilized. Second, five 3D ResNet models were fine-tuned using a customized dataset (14,185 clips, 60,606 secs). As an evaluation index for activity recognition model, the F1 score showed 0.881, 0.689, 0.74, 0.684, and 0.569 for the five 3D ResNet models, with the 18-layer model performing the best. This result indicated that the activity recognition models with fewer layers could be advantageous in deriving the optimal weights for the target domain (i.e., excavator activities) when fine-tuning with a limited dataset. Consequently, this study identified the optimal depth of 3D ResNet that can maintain a reliable performance in dynamic and complex construction sites, even with a limited dataset. The proposed approach is expected to contribute to the development of decision-support systems capable of systematically managing enhanced safety, productivity improvement, and carbon neutrality in the construction industry.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1322-1322
• /
• 2024

Reinforced concrete (RC) , a major contributor to resource depletion and harmful emissions, fuels research on optimizing its design. Optimizing RC structures is challenging due to the mix of discrete and continuous variables, hindering traditional differentiation-based methods. Thus, this study aims to optimize RC structures cost-effectively using deep reinforcement learning. When the Agent selects design variables, Environment checks design criteria based on KDS 14-20 code (South Korea) and calculates reward. The Agent updates its Neural Network with this reward. Target for optimization is a simply supported doubly RC beam, with design variables including cross-section dimensions, sizes and quantities of tension and compression reinforcement, and size of stirrups. We used 200,000 training sets and 336 test sets, each with live load, dead load, beam length variables. To exclude labeled data, multiple training iterations were conducted. In the initial training, the reward was the ratio of maximum possible cost at beam length to the designed structure's cost. Next iterations used the ratio of optimal values by the previous Agent to the current Agent as the reward. Training ended when the difference between optimal values from the previous and current Agent was within 1% for test data. Brute Force Algorithm was applied to the test set to calculate the actual cost-optimal design for validation. Results showed within 10% difference from actual optimal cost, indicating successful deep reinforcement learning application without labeled data. This study benefits the rapid and accurate calculation of optimized designs and construction processes in Building Information Modeling (BIM) applications.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.71-89
• /
• 2016

Sentiment analysis is used for identifying emotions or sentiments embedded in the user generated data such as customer reviews from blogs, social network services, and so on. Various research fields such as computer science and business management can take advantage of this feature to analyze customer-generated opinions. In previous studies, the star rating of a review is regarded as the same as sentiment embedded in the text. However, it does not always correspond to the sentiment polarity. Due to this supposition, previous studies have some limitations in their accuracy. To solve this issue, the present study uses a supervised sentiment classification model to measure a more accurate sentiment polarity. This study aims to propose an advanced sentiment classifier and to discover the correlation between movie reviews and box-office success. The advanced sentiment classifier is based on two supervised machine learning techniques, the Support Vector Machines (SVM) and Feedforward Neural Network (FNN). The sentiment scores of the movie reviews are measured by the sentiment classifier and are analyzed by statistical correlations between movie reviews and box-office success. Movie reviews are collected along with a star-rate. The dataset used in this study consists of 1,258,538 reviews from 175 films gathered from Naver Movie website (movie.naver.com). The results show that the proposed sentiment classifier outperforms Naive Bayes (NB) classifier as its accuracy is about 6% higher than NB. Furthermore, the results indicate that there are positive correlations between the star-rate and the number of audiences, which can be regarded as the box-office success of a movie. The study also shows that there is the mild, positive correlation between the sentiment scores estimated by the classifier and the number of audiences. To verify the applicability of the sentiment scores, an independent sample t-test was conducted. For this, the movies were divided into two groups using the average of sentiment scores. The two groups are significantly different in terms of the star-rated scores.

• Journal of radiological science and technology
• /
• v.34 no.1
• /
• pp.17-25
• /
• 2011

In this study, we examined the impact caused by chronic exposure to Mn by investigating the degree of brain activation based on the data of recognition activities using fMRI (functional magnetic resonance imaging). A questionnaire survey, blood tests, and fMRI tests were carried out with respect to two groups. Group 1 was an exposure group consisting of 15 male workers who are 34 years old or older, and who worked for longer than 10 years in a shipbuilding factory as a welder. Group 2 was a control group consisting of 15 workers in manufacturing industries with the same gender and age. The results showed that blood Mn concentration of Group 1($1.3\;{\mu}g/dl$) was significantly higher than that of Group 2($0.8\;{\mu}g/dl$)(p < 0.001), and Pallidal Index (PI) of Group 1 was also significantly higher than that of Group 2 (p < 0.001). PI value of the group whose blood Mn concentration was $0.93\;{\mu}g/dl$ or higher was significantly higher than that of the group whose blood Mn concentration was less than $0.93 \;{\mu}g/dl$ (p < 0.001). As for brain activity area within the control group, the right and the left areas of occipital cortex showed significant activity and the left area of middle temporal cortex, the right area of superior inferior frontal cortex and inferior parietal cortex showed significant activity. Unlike the control group, the exposure group showed significant activity on the right area of superior inferior temporal cortex, the left of insula area. In the comparison of brain activity areas between the two groups, the exposure group showed significantly higher activation than the control group in such areas as the right inferior temporal cortex, the left area of superior parietal cortex and occipital cortex, and cerebellum including middle temporal cortex. However, in nowhere the control group showed more activated area than the exposure group. As the final outcome, chronic exposure to Mn increased brain activity during implementation of arithmetic task. In an identical task, activation increased in superior inferior temporal cortex, and insula area. And it was discovered that brain activity increase in temporal area and occipital area was more pronounced in the exposure group than in the control group. This result suggests that chronic exposure to Mn in the work environment affects brain activation neuro-network.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.303-308
• /
• 2020

The ReLU(Rectified Linear Unit) function has been dominantly used as a standard activation function in most deep artificial neural network models since it was proposed. Later, Leaky ReLU, Swish, and Mish activation functions were presented to replace ReLU, which showed improved performance over existing ReLU function in image classification task. Therefore, we recognized the need to experiment with whether performance improvements could be achieved by replacing the RELU with other activation functions in the super resolution task. In this paper, the performance was compared by changing the activation functions in EDSR model, which showed stable performance in the super resolution task. As a result, in experiments conducted with changing the activation function of EDSR, when the resolution was converted to double, the existing activation function, ReLU, showed similar or higher performance than the other activation functions used in the experiment. When the resolution was converted to four times, Leaky ReLU and Swish function showed slightly improved performance over ReLU. PSNR and SSIM, which can quantitatively evaluate the quality of images, were able to identify average performance improvements of 0.06%, 0.05% when using Leaky ReLU, and average performance improvements of 0.06% and 0.03% when using Swish. When the resolution is converted to eight times, the Mish function shows a slight average performance improvement over the ReLU. Using Mish, PSNR and SSIM were able to identify an average of 0.06% and 0.02% performance improvement over the RELU. In conclusion, Leaky ReLU and Swish showed improved performance compared to ReLU for super resolution that converts resolution four times and Mish showed improved performance compared to ReLU for super resolution that converts resolution eight times. In future study, we should conduct comparative experiments to replace activation functions with Leaky ReLU, Swish and Mish to improve performance in other super resolution models.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.4
• /
• pp.15-24
• /
• 2007

The recognition of postal address images is indispensable for the automatic sorting of postal envelopes. The process of the address image recognition is composed of three steps-address image preprocessing, character recognition, address interpretation. The extracted character images from the preprocessing step are forwarded to the character recognition step, in which multiple candidate characters with reliability scores are obtained for each character image extracted. aracters with reliability scores are obtained for each character image extracted. Utilizing those character candidates with scores, we obtain the final valid address for the input envelope image through the address interpretation step. The envelope sorting rate depends on the performance of all three steps, among which character recognition step could be said to be very important. The good character recognizer would be the one which could produce valid candidates with very reliable scores to help the address interpretation step go easy. In this paper, we propose the method of generating character candidates with reliable recognition scores. We utilize the existing MLP(multilayered perceptrons) neural network of the address recognition system in the current automatic postal envelope sorters, as the classifier for the each image from the preprocessing step. The MLP is well known to be one of the best classifiers in terms of processing speed and recognition rate. The false alarm problem, however, might be occurred in recognition results, which made the address interpretation hard. To make address interpretation easy and improve the envelope sorting rate, we propose promising methods to reestimate the recognition score (confidence) of the existing MLP classifier: the generation method of the statistical recognition properties of the classifier and the method of the combination of the MLP and the subspace classifier which roles as a reestimator of the confidence. To confirm the superiority of the proposed method, we have used the character images of the real postal envelopes from the sorters in the post office. The experimental results show that the proposed method produces high reliability in terms of error and rejection for individual characters and non-characters.

• Journal of Korea Water Resources Association
• /
• v.56 no.2
• /
• pp.75-89
• /
• 2023

As the Mekong River basin is a nationally shared river, it is difficult to collect precipitation data, and the quantitative and qualitative quality of the data sets differs from country to country, which may increase the uncertainty of hydrological analysis results. Recently, with the development of remote sensing technology, it has become easier to obtain grid-based precipitation products(GPPs), and various hydrological analysis studies have been conducted in unmeasured or large watersheds using GPPs. In this study, rainfall-runoff simulation in the Mekong River basin was conducted using the SWAT model, which is a quasi-distribution model with three satellite GPPs (TRMM, GSMaP, PERSIANN-CDR) and two GPPs (APHRODITE, GPCC). Four water level stations, Luang Prabang, Pakse, Stung Treng, and Kratie, which are major outlets of the main Mekong River, were selected, and the parameters of the SWAT model were calibrated using APHRODITE as an observation value for the period from 2001 to 2011 and runoff simulations were verified for the period form 2012 to 2013. In addition, using the ConvAE, a convolutional neural network model, spatio-temporal correction of original satellite precipitation products was performed, and rainfall-runoff performances were compared before and after correction of satellite precipitation products. The original satellite precipitation products and GPCC showed a quantitatively under- or over-estimated or spatially very different pattern compared to APHPRODITE, whereas, in the case of satellite precipitation prodcuts corrected using ConvAE, spatial correlation was dramatically improved. In the case of runoff simulation, the runoff simulation results using the satellite precipitation products corrected by ConvAE for all the outlets have significantly improved accuracy than the runoff results using original satellite precipitation products. Therefore, the bias correction technique using the ConvAE technique presented in this study can be applied in various hydrological analysis for large watersheds where rain guage network is not dense.

• Journal of the Korean Society of Radiology
• /
• v.83 no.2
• /
• pp.344-359
• /
• 2022

Purpose To develop a denoising convolutional neural network-based image processing technique and investigate its efficacy in diagnosing breast cancer using low-dose mammography imaging. Materials and Methods A total of 6 breast radiologists were included in this prospective study. All radiologists independently evaluated low-dose images for lesion detection and rated them for diagnostic quality using a qualitative scale. After application of the denoising network, the same radiologists evaluated lesion detectability and image quality. For clinical application, a consensus on lesion type and localization on preoperative mammographic examinations of breast cancer patients was reached after discussion. Thereafter, coded low-dose, reconstructed full-dose, and full-dose images were presented and assessed in a random order. Results Lesions on 40% reconstructed full-dose images were better perceived when compared with low-dose images of mastectomy specimens as a reference. In clinical application, as compared to 40% reconstructed images, higher values were given on full-dose images for resolution (p < 0.001); diagnostic quality for calcifications (p < 0.001); and for masses, asymmetry, or architectural distortion (p = 0.037). The 40% reconstructed images showed comparable values to 100% full-dose images for overall quality (p = 0.547), lesion visibility (p = 0.120), and contrast (p = 0.083), without significant differences. Conclusion Effective denoising and image reconstruction processing techniques can enable breast cancer diagnosis with substantial radiation dose reduction.