Internet of things with bio-inspired co-evolutionary deep-convolution neural-network approach for detecting road cracks
- PDF / 2,969,077 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 69 Downloads / 146 Views
(0123456789().,-volV)(0123456789(). ,- volV)
S.I.: BIO-INSPIRED COMPUTING FOR DLA
Internet of things with bio-inspired co-evolutionary deep-convolution neural-network approach for detecting road cracks in smart transportation Osama Alfarraj1 Received: 4 July 2020 / Accepted: 24 September 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Internet of things (IoT) primarily aims to realize valuable services such as smart homes, smart buildings, and smart transport. To this end, smart applications are faced with different challenges, particularly in the implementation of a smart transportation system, which requires maximum road and travel safety. Road crack detection has been extensively studied and presented with various solutions; however, these approaches are limited by the inhomogeneity in the crack intensity and background complexity, such as a shadow with similar intensity and pavement contrast, which are known obstacles in the accurate prediction of road cracks. To overcome these issues, an IoT system with a bio-inspired deep learning approach was introduced herein for accurate road crack detection. In the proposed approach, transportation images are first collected using a smart mobile sensor, then processed by a bio-inspired self-learning co-evolutionary deep-convolution neural network. The optimized neural networks provide the required framework by analyzing the collected images to detect cracks more accurately. The efficiency of the proposed system was confirmed in different metrics, including the per-pixel accuracy (99.04%), Jaccard index (98.42%), loss error rate (0.03), precision (99.25%), recall (99.24%), and prediction accuracy (99.72%) metrics. Keywords Internet of things (IoT) Deep learning network Smart mobile sensors Smart transportation Road cracks Deep-convolution networks
1 Introduction Internet of Things (IoT) refers to a set of interrelated devices, digital machines, and mechanical devices that are connected via a unique identifier [1]. These interconnected devices, particularly sensors, help transmit information, such as health data and ambient temperature, via the network without the aid of human–computer interaction or human–human intervention [2]. This IoT-based data transmission process has been linked to improvement in customer service, business value maximization, and enhanced decision-making in different applications. Indeed, IoT assists people to gain control over their daily
& Osama Alfarraj [email protected] 1
Computer Science Department, Community College, King Saud University, Riyadh 11437, Saudi Arabia
lives and live in both sophistication and comfort in addition to performing various logistics operations [3]. Furthermore, the introduction of IoT devices in industries has enabled every process to achieve minimum labor costs and reasonable expenses for customer goods delivery. Accordingly, the various advantages of IoT devices have been gradually utilized in smart city applications in the form of smart homes, smart buildings, smart trans
Data Loading...
