Deep support vector neural networks

Díaz-Vico, David; Prada, J.; Omari, Adil; Dorronsoro, José R.

doi:10.3233/ica-200635

Cited by 17 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, a new pavement crack detection method was proposed to improve the detection accuracy by combining 2D grayscale images and 3D laser scanning data (Du et al., 2022; Huang et al., 2014; Weng et al., 2022). Some other advanced models were also proposed, such as functional brain network (Hua et al., 2019), parameter sharing‐based deep network (Reyes & Ventura, 2019), deep support vector neural networks (Diaz‐Vico et al., 2020), and so on.…”

Section: Literature Reviewmentioning

confidence: 99%

Spatiotemporal matching method for tracking pavement distress using high‐frequency detection data

Pan

Liu

et al. 2022

Computer aided Civil Eng

View full text Add to dashboard Cite

Various algorithms based on deep learning have achieved promising results in pavement distress detection. However, the detected distresses are not tracked throughout the life cycle. In long‐term application scenarios, pavement distresses may take on different forms due to image acquisition mode, distress development, and environmental change, which make tracking distresses a tough question. We present in this study a spatiotemporal matching method based on high‐frequency real pavement distress datasets. Pavement distresses of fixed routes were collected 30 times over 5 months, and distresses with spatiotemporal information were obtained at time series. We apply image rectification, stitching and distress class, and bounding box generation algorithms for pre‐processing to align the collected images to the same‐detail level and angle. A four‐step spatiotemporal matching module is designed, including global positioning system (GPS) filtering, class filtering, relative position filtering, and distress feature filtering. The results reveal that the comprehensive rank‐3 hit rate of the matching method reaches 88.73%, and the method is robust to environmental factors, which helps show performance decay of distresses and the effect of maintenance operations. It is concluded that the spatiotemporal matching method is convenient to operate, and it lays the foundation for an agency to track distress evolution and make timely treatment of distresses in the life cycle.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Spatiotemporal matching method for tracking pavement distress using high‐frequency detection data

Pan

Liu

et al. 2022

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…These professional suggestions provided a useful reference and inspiration for the research and development of later detection algorithms. Besides, some other advanced models have been proposed, such as deep support vector neural networks (Díaz-Vico et al, 2020), functional brain network (Hua et al, 2019), parameter sharing-based deep network (Reyes & Ventura, 2019), and so on.…”

Section: F I G U R E 1 Different Image Sources For Pavement Distress Detectionmentioning

confidence: 99%

Cross‐scene pavement distress detection by a novel transfer learning framework

Che

Liu

et al. 2021

Computer aided Civil Eng

View full text Add to dashboard Cite

Deep learning has achieved promising results in pavement distress detection. However, the training model's effectiveness varies according to the data and scenarios acquired by different camera types and their installation positions. It is time consuming and labor intensive to recollect labeled data and retrain a new model every time the scene changes. In this paper, we propose a transfer learning pipeline to address this problem, which enables a distress detection model to be applied to other untrained scenarios. The framework consists of two main components: data transfer and model transfer. The former trains a generative adversarial network to transfer existing image data into a new scene style. Then, attentive CutMix and image melding are applied to insert distress annotations to synthesize the new scene's labeled data. After data expansion, the latter step transfers the feature extracted by the existing model to the detection application of the new scene through domain adaptation. The effects of varying degrees of knowledge transfer are also discussed. The proposed method is evaluated on two data sets from two different scenes with more than 40,000 images totally. This method can reduce the demand for training data by at least 25% when the model is applied in a new scene. With the same number of training images, the proposed method can improve the model accuracy by 26.55%.

show abstract

“…Recently, machine-learning algorithms, in particular deep neural networks (Díaz-Vico et al, 2020;Lara-Benıteza et al, 2020;Lozano et al, 2020;Yang et al, 2019), have been used for damage detection of structures (Ni et al, 2020;Wu et al, 2019). Abdeljaber et al (2018)…”

Section: Vibration-based Structural Health Monitoringmentioning

confidence: 99%

Integrating structural control, health monitoring, and energy harvesting for smart cities

2021

View full text Add to dashboard Cite

Cities that are adopting innovative and technology-driven solutions to improve the city's efficiency are considered smart cities. With the increased attention on smart cities with self-driving vehicles, drones, and robots, designing smart infrastructure is only a natural extension. Smart infrastructures aim to self-diagnose, self-power, selfadapt, and self-heal during normal and extreme operating conditions. Structural vibration control (SVC) and structural health monitoring (SHM) technologies, in particular, are expected to play pivotal roles in the development of modern smart and resilient structures. SVC methodologies intend to provide supplemental damping and reduce the structural dynamic responses during normal and extreme events. SHM methodologies offer valuable information about the structure's condition that is useful for maintenance purposes and rapid damage detection in post-hazard events. The collapse of the 12-story Champlain Towers South, a beachfront condominium in the Miami suburb of Surfside, Florida, could have been known in advance with an embedded SHM technology. More recently, the integrated structural control and health monitoring (ISCHM) systems have shown promise in the development of smart cities of the future. The integrated architecture incorporates the control and health monitoring components as complementary technologies and simultaneously takes advantage of both technologies. This article provides a state-of-the-art review of ISCHM ideas and systems. It presents recent significant developments in structural control, SHM, and energy harvesting that are paving the way towards the advent of integrated ISCHM systems, including damage-tolerant control systems. This article also identifies future promising research areas for designing the next generation of autonomous ISCHM systems for smart cities.

show abstract

Deep support vector neural networks

Cited by 17 publications

References 23 publications

Spatiotemporal matching method for tracking pavement distress using high‐frequency detection data

Spatiotemporal matching method for tracking pavement distress using high‐frequency detection data

Cross‐scene pavement distress detection by a novel transfer learning framework

Integrating structural control, health monitoring, and energy harvesting for smart cities

Contact Info

Product

Resources

About