• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.141-151
• /
• 2022

In recent years, the industry and research communities have focused on developing autonomous crack inspection approaches, which mainly include image acquisition and crack detection. In these approaches, mobile devices such as cameras, drones or smartphones are utilized as sensing platforms to acquire structural images, and the deep learning (DL)-based methods are being developed as important crack detection approaches. However, the process of image acquisition and collection is time-consuming, which delays the inspection. Also, the present mobile devices such as smartphones can be not only a sensing platform but also a computing platform that can be embedded with deep neural networks (DNNs) to conduct on-site crack detection. Due to the limited computing resources of mobile devices, the size of the DNNs should be reduced to improve the computational efficiency. In this study, an architecture called pruned crack recognition network (PCR-Net) was developed for the detection of structural cracks. A dataset containing 11000 images was established based on the raw images from bridge inspections. A pruning method was introduced to reduce the size of the base architecture for the optimization of the model size. Comparative studies were conducted with image processing techniques (IPTs) and other DNNs for the evaluation of the performance of the proposed PCR-Net. Furthermore, a modularly designed framework that integrated the PCR-Net was developed to realize a DL-based crack detection application for smartphones. Finally, on-site crack detection experiments were carried out to validate the performance of the developed system of smartphone-based detection of structural cracks.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.53-62
• /
• 2022

The deployment of advanced structural health monitoring (SHM) systems in large-scale civil structures collects large amounts of data. Note that these data may contain multiple types of anomalies (e.g., missing, minor, outlier, etc.) caused by harsh environment, sensor faults, transfer omission and other factors. These anomalies seriously affect the evaluation of structural performance. Therefore, the effective analysis and mining of SHM data is an extremely important task. Inspired by the deep learning paradigm, this study develops a novel generative adversarial network (GAN) and convolutional neural network (CNN)-based data anomaly detection approach for SHM. The framework of the proposed approach includes three modules : (a) A three-channel input is established based on fast Fourier transform (FFT) and Gramian angular field (GAF) method; (b) A GANomaly is introduced and trained to extract features from normal samples alone for class-imbalanced problems; (c) Based on the output of GANomaly, a CNN is employed to distinguish the types of anomalies. In addition, a dataset-oriented method (i.e., multistage sampling) is adopted to obtain the optimal sampling ratios between all different samples. The proposed approach is tested with acceleration data from an SHM system of a long-span bridge. The results show that the proposed approach has a higher accuracy in detecting the multi-pattern anomalies of SHM data.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• Smart Structures and Systems
• /
• v.31 no.2
• /
• pp.183-197
• /
• 2023

For long-span bridges with a structural health monitoring (SHM) system, environmental temperature-driven responses are proved to be a main component in measurements. However, anomalous structural behavior may be hidden incomplicated recorded data. In order to receive reliable assessment of structural performance, it is important to study therelationship between temperature and monitoring data. This paper presents an application of the cointegration based methodology to detect anomalies that may be masked by temperature effects and then forecast the temperature-induced deflection (TID) of long-span suspension bridges. Firstly, temperature effects on girder deflection are analyzed with fieldmeasured data of a suspension bridge. Subsequently, the cointegration testing procedure is conducted. A threshold-based anomaly detection framework that eliminates the influence of environmental temperature is also proposed. The cointegrated residual series is extracted as the index to monitor anomaly events in bridges. Then, wavelet separation method is used to obtain TIDs from recorded data. Combining cointegration theory with autoregressive moving average (ARMA) model, TIDs for longspan bridges are modeled and forecasted. Finally, in-situ measurements of Xihoumen Bridge are adopted as an example to demonstrate the effectiveness of the cointegration based approach. In conclusion, the proposed method is practical for actual structures which ensures the efficient management and maintenance based on monitoring data.

• The Korean Journal of Franchise Management
• /
• v.14 no.2
• /
• pp.31-46
• /
• 2023

Purpose: Brand communication plays an important role in the credibility of consumer behavior as it enhances brand equity. This study investigates the effects of brand communication (firm-created communication, consumer-generated communication) on brand awareness, brand attitude, brand loyalty in the hotel business sector by applying the SOR theory (stimulus-organism-response theory). Research design, data, and methodology: This study was analyzed in a quantitative way using the survey results of 400 customers who had experience of visiting hotels. In this study, SmartPLS 4.0 was used to evaluate the research model. The reliability, convergent validity, and discriminant validity of the measurement tool were verified. Result: Result was found that consumer-generated communications had a positive effect on brand awareness and brand attitude, whereas firm-created communications had a significant effect on brand awareness. In addition, brand awareness had a positive effect on both brand attitude and brand loyalty. Finally, brand attitude was found to have a positive effect on brand loyalty. Conclusions: This study redefines the concept of where chain hotel groups should focus when providing consumers with information about their brands and services. As a result, the conceptual framework of brand communication to increase new customer visits to the hotel brand has been expanded.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.104-108
• /
• 2023

This paper deals with research on innovative systems using Python-based artificial intelligence technology in the field of plant growth monitoring. The importance of monitoring and analyzing the health status and growth environment of plants in real time contributes to improving the efficiency and quality of crop production. This paper proposes a method of processing and analyzing plant image data using computer vision and deep learning technologies. The system was implemented using Python language and the main deep learning framework, TensorFlow, PyTorch. A camera system that monitors plants in real time acquires image data and provides it as input to a deep neural network model. This model was used to determine the growth state of plants, the presence of pests, and nutritional status. The proposed system provides users with information on plant state changes in real time by providing monitoring results in the form of visual or notification. In addition, it is also used to predict future growth conditions or anomalies by building data analysis and prediction models based on the collected data. This paper is about the design and implementation of Python-based plant growth monitoring systems, data processing and analysis methods, and is expected to contribute to important research areas for improving plant production efficiency and reducing resource consumption.

• Journal of Distribution Science
• /
• v.20 no.3
• /
• pp.95-106
• /
• 2022

Purpose: This study aims to verify the effects of omnichannel characteristics on pleasure, resistance and repurchase intention in the omnichannel situation in order to provide the innovative commercial business. Research design, data and methodology: The study examined relations between research concepts centered on previous studies, set hypotheses, developed a research model, and verified the model through a questionnaire survey. A total of 297 questionnaires were used for the final analysis, excluding the questionnaires showing insincere or outliers. Results: First, Omnichannel showed multi-dimensional characteristics consisting of consistency, innovation, economy, and integration. Second, innovation and economic feasibility had a positive effect on pleasure. Third, only economic feasibility had a negative effect on user resistance. Fourth, consumers' shopping pleasure had a negative effect on user resistance. Fifth, repurchase intention of consumers was positively affected by innovation. Conclusions: This research contributed to extend academic framework of distribution research by examining causal relationship through adoption of economic and innovation factors as new characteristics from the integrated perspective beyond the research frame of the existing omnichannel distribution environment. Companies should provide meaningful experiences by resolving concerns about side effects caused by human-computer interaction and providing smart information that matches the products most suitable for consumer needs.

• The Korean Journal of Franchise Management
• /
• v.14 no.4
• /
• pp.17-33
• /
• 2023

Purpose: This study divides choice attributes that can help strengthen the competitiveness of traditional markets into product, price, personnel, and physical evidence. This study also examines which choice attributes affect customer value perception, satisfaction, and loyalty. Research design, data, and methodology: The data were collected from 542 traditional customers aged 20 or older who frequently visit traditional markets across the country and analyzed using the Smart PLS 4.0 program. The survey was conducted with the help of an online survey company for a total of 14 days from April 7, 2023 to April 20, 2023. Result: First, product, price, and employee quality have a positive impact on utilitarian and hedonic value, but physical evidence does not. Second, product, price, and employee quality have a positive impact on hedonic and hedonic value. Second, utilitarian value has a positive impact on satisfaction and revisit intention. Third, hedonic value has a positive impact on satisfaction, but does not on revisit intention. Lastly, satisfaction has a positive impact on revisit intention. Conclusions: Based on the S-O-R model and the theory of consumption value, this study proposed and examined an integrated framework in which satisfaction leads to revisit intention through selection attributes acting on perceived value.

• The Journal of Information Systems
• /
• v.32 no.3
• /
• pp.165-181
• /
• 2023

Purpose Digital platforms, together with the innovative technologies of modern society, are accelerating the digital innovation of the entire economy and society. Although social media platforms are gradually integrated into daily life, due to social media overload, users limit their use of the platform for a certain period of time or eventually choose to stop using it. In the context of social media platform, the purpose of this paper is to study the effects of information overload, social overload and system function overload on users' unintentional avoidance behavior, mediated by fatique and dissatisfaction. Design/methodology/approach This study empirically examines the influence of social media overload characteristics on users' unintentional avoidance behavior of platform utilization using the S-O-R framework. Data from 236 Chinese social media users were collected through a questionnaire survey, and the hypotheses were validated by evaluating the research model using the SmartPLS 4.0 program using Partial Least Square (PLS) method. Findings According to the empirical analysis result, based on the S-O-R model, first, it is confirmed that information overload and system feature overload have significant positive(+) effects on fatigue. Second, this study finds that information overload, social overload and fatigue have significant positive(+) effects on dissatisfaction. Thirdly, fatigue and dissatisfaction have significant positive(+) effects on unintentional avoidance. In addition, social overload has no significant effect on fatigue, while system feature overload has no significant effect on dissatisfaction.