• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.472-478
• /
• 2009

The scopes of the supply chain management in construction projects has expanded from the field management focusing on field storage, transportation, and lifting to the whole supply chain from the materials to field. The expansion of the supply chain management can raise the possibilities of leaner production, which enables shortened lead time of the difficult-to-operate materials, and prevents the work interference or delay. However, the expanded management range requires more information and management than an existing management style currently used for factory production of iron frame, curtain wall, PC, etc. In addition, there are limitations that expand the existing management style into the new supply chain management in construction projects and therefore it is required to automate the existing management style in order to extend the management range. The objective of this study is to propose the process and equipment that can manage the supply chain of the materials which range from the factory production to the field storage based on RFID/USN techniques, introducing small-sized transportation equipment(intelligent pallet), the vehicle tool kit(intelligent trailer), and in-and-out management equipment(Gate Sensor) as a prototype to effectively develop the appliances for operating the proposed process, and present the application possibility of the appliances. The full paper will present then the test results that the proposed appliances for the supply chain management automatically transmit and receive the generated information between the appliances or the appliance and sever under various wireless network circumstances such as zigbee, wibro, Wi-Fi, and CDMA.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.353-360
• /
• 2022

Due to the dense and complicated working environment, the construction industry is susceptible to many accidents. Worker's fall is a severe problem at the construction site, including falling into holes or openings because of the inadequate coverings as per the safety rules. During the construction or demolition of a building, openings and holes are formed in the floors and roofs. Many workers neglect to cover openings for ease of work while being aware of the risks of holes, openings, and gaps at heights. However, there are safety rules for worker safety; the holes and openings must be covered to prevent falls. The safety inspector typically examines it by visiting the construction site, which is time-consuming and requires safety manager efforts. Therefore, this study presented a worker-driven approach (the worker is involved in the reporting process) to facilitate safety managers by developing integrated computer vision and inertia sensors-based mobile applications to identify openings. The TensorFlow framework is used to design Convolutional Neural Network (CNN); the designed CNN is trained on a custom dataset for binary class openings and covered and deployed on an android smartphone. When an application captures an image, the device also extracts the accelerometer values to determine the inclination in parallel with the classification task of the device to predict the final output as floor (openings/ covered), wall (openings/covered), and roof (openings / covered). The proposed worker-driven approach will be extended with other case scenarios at the construction site.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.411-414
• /
• 2021

One of the elements of technology that has become extremely critical within the field of education today is Deep learning. It has been especially used in the area of natural language processing, with some word-representation vectors playing a critical role. However, some of the low-resource languages, such as Swahili, which is spoken in East and Central Africa, do not fall into this category. Natural Language Processing is a field of artificial intelligence where systems and computational algorithms are built that can automatically understand, analyze, manipulate, and potentially generate human language. After coming to discover that some African languages fail to have a proper representation within language processing, even going so far as to describe them as lower resource languages because of inadequate data for NLP, we decided to study the Swahili language. As it stands currently, language modeling using neural networks requires adequate data to guarantee quality word representation, which is important for natural language processing (NLP) tasks. Most African languages have no data for such processing. The main aim of this project is to recognize and focus on the classification of words in English, Swahili, and Korean with a particular emphasis on the low-resource Swahili language. Finally, we are going to create our own dataset and reprocess the data using Python Script, formulate the syllabic alphabet, and finally develop an English, Swahili, and Korean word analogy dataset.

• Journal of Yeungnam Medical Science
• /
• v.40 no.2
• /
• pp.156-163
• /
• 2023

Background: Interest in digital medical information has increased because it allows doctors to easily access a patient's medical records and provide appropriate medical care. Blockchain technology ensures data safety, reliability, integrity, and transparency by distributing medical data to all users over a peer-to-peer network. This study attempted to assess pediatricians' thoughts and attitudes toward introducing blockchain technology into the medical field. Methods: This study used a questionnaire survey to examine the thoughts and attitudes of 30- to 60-year-old pediatricians regarding the introduction of blockchain technology into the medical field. Responses to each item were recorded on a scale ranging from 1 (never agree) to 7 (completely agree). Results: The scores for the intentions and expectations of using blockchain technology were 4.0 to 4.6. Pediatricians from tertiary hospitals responded more positively (4.5-4.9) to the idea of using blockchain technology for hospital work relative to the general population (4.3-4.7). However, pediatricians working in primary and secondary hospitals had a slightly negative view of the application of blockchain technology to hospital work (p=0.018). Conclusion: When introducing the medical records of related pediatric and adolescent patients using blockchain technology in the future, it would be better to conduct a pilot project that prioritizes pediatricians in tertiary hospitals. The cost, policy, and market participants' perceptions are essential factors to consider when introducing technology in the medical field.

• International conference on construction engineering and project management
• /
• 2017.10a
• /
• pp.281-290
• /
• 2017

As various stakeholders are involved in construction projects, disputes between the parties are more likely to occur, which is a very important issue for the participants in the projects. Claims in construction projects, however, are very complex and thus difficult to manage. In particular, as the cause of a claim in the preceding stage that has not been resolved in a timely manner has an effect on the cause of a claim in the following stage, it is difficult to find a point of compromise regarding a claim caused by the relationship between the causes that occur in the preceding and following stages. In this regard, this study sought to examine the rules for the generation of change order claims, which occur most frequently among the construction claims, and thus to select the key management targets through the analysis of the relationship between the causes of claims arising in the preceding and following stages for the efficient management of claims. It is expected that the use of rules for the generation of change order claims as well as of representative and similar cases will help the construction practitioners in judging claims, considering the relationships among the causes of the claims. Meanwhile, in this study, association analysis was conducted regarding the causes of the occurrence of change order claims in a design-build delivery method, and therefore, it is necessary to verify the effectiveness of the method when applied to other delivery methods.

• International conference on construction engineering and project management
• /
• 2017.10a
• /
• pp.32-41
• /
• 2017

Accidents on offshore oil and gas platforms (OOGPs) usually cause serious fatalities and financial losses considering demanding environment platforms locate and complex topsides structure platforms own. Evacuation planning on platforms is usually challenging. The computational tool is a good choice to plan evacuation by emergency simulation. However, the complex structure of platforms and varied evacuation behaviors usually weaken the advantages of computational simulation. Therefore, this study developed a simulation model for OOGPs to evaluate different evacuation plans to improve evacuation performance by integrating building information modeling (BIM) and agent-based model (ABM). The developed model consists of four parts: evacuation model input, simulation environment modeling, agent definition, and simulation and comparison. Necessary platform information is extracted from BIM and then used to model simulation environment by integrating matrix model and network model. During agent definition, in addition to basic characteristics, environment sensing and dynamic escape path planning functions are also developed to improve simulation performance. An example OOGP BIM topsides with different emergent scenarios is used to illustrate the developed model. The results showed that the developed model can well simulate evacuation on OOGPs and improve evacuation performance. The developed model was also suggested to be applied to other industries such as the architecture, engineering, and construction industry.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.313-322
• /
• 2020

The recognition of the risk hazards is a vital step to effectively prevent accidents on a construction site. The advanced development in computer vision systems and the availability of the large visual database related to construction site made it possible to take quick action in the event of human error and disaster situations that may occur during management supervision. Therefore, it is necessary to analyze the risk factors that need to be managed at the construction site and review appropriate and effective technical methods for each risk factor. This research focuses on analyzing Occupational Safety and Health Agency (OSHA) related to risk zone identification rules that can be adopted by the image recognition technology and classify their risk factors depending on the effective technical method. Therefore, this research developed a pattern-oriented classification of OSHA rules that can employ a large scale of safety hazard recognition. This research uses joint reasoning of risk zone Identification and numeric input by utilizing a stereo camera integrated with an image detection algorithm such as (YOLOv3) and Pyramid Stereo Matching Network (PSMNet). The research result identifies risk zones and raises alarm if a target object enters this zone. It also determines numerical information of a target, which recognizes the length, spacing, and angle of the target. Applying image detection joint logic algorithms might leverage the speed and accuracy of hazard detection due to merging more than one factor to prevent accidents in the job site.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.463-481
• /
• 2020

Cutter suction dredgers (CSDs) are widely used in various dredging constructions such as channel excavation, wharf construction, and reef construction. During a CSD construction, the main operation is to control the swing speed of cutter to keep the slurry concentration in a proper range. However, the slurry concentration cannot be monitored in real-time, i.e., there is a "time-lag effect" in the log of slurry concentration, making it difficult for operators to make the optimal decision on controlling. Concerning this issue, a solution scheme that using real-time monitored indicators to predict current slurry concentration is proposed in this research. The characteristics of the CSD monitoring data are first studied, and a set of preprocessing methods are presented. Then we put forward the concept of "index class" to select the important indices. Finally, an ensemble learning algorithm is set up to fit the relationship between the slurry concentration and the indices of the index classes. In the experiment, log data over seven days of a practical dredging construction is collected. For comparison, the Deep Neural Network (DNN), Long Short Time Memory (LSTM), Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and the Bayesian Ridge algorithm are tried. The results show that our method has the best performance with an R² of 0.886 and a mean square error (MSE) of 5.538. This research provides an effective way for real-time predicting the slurry concentration of CSDs and can help to improve the stationarity and production efficiency of dredging construction.

• Journal of Wetlands Research
• /
• v.25 no.4
• /
• pp.284-290
• /
• 2023

Domestic water supply and sewage facilities are rapidly aging and maintenance difficulties such as aging of operation and management personnel are overlapping, so Digital Twin technology is attracting attention as an intelligent means of process management. Digital twin projects for domestic water treatment processes include the smart sewage treatment project promoted by the Ministry of Environment, projects independently promoted by some local governments, and digital twin purification plant projects promoted by K-water. However, the content of digital twin promotion is different for each institution. Therefore, in the water treatment process, technological standardization and step-by-step implementation methods for digital twins must be preceded to reduce trial and error in future business promotion. This study aims to provide an efficient promotion plan by prescribing the digital twin element technology and composition method in the water treatment process and reviewing the contents currently being promoted by the Ministry of Environment, local governments, and K-Water individually.