The classification of construction waste material using a deep convolutional neural network

Davis, Peter; Aziz, Fakhra; Newaz, Mohammad Tanvi; Sher, Willy; Simon, Laura

doi:10.1016/j.autcon.2020.103481

Cited by 117 publications

(43 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Rakhshan et al [142] proposed a predictive model using machine learning techniques to estimate and evaluate the economic reusability of structural elements. Furthermore, Davis et al [143] designed an on-site waste classification system using a deep learning method that can classify different categories of waste based on digital photographs taken from construction site bins. Similarly, other researchers also used deep learning-based image analysis to obtain the composition details of recycled aggregates in order to improve recycling performance [144].…”

mentioning

confidence: 99%

Circular Digital Built Environment: An Emerging Framework

2021

View full text Add to dashboard Cite

Digital technologies are considered to be an essential enabler of the circular economy in various industries. However, to date, very few studies have investigated which digital technologies could enable the circular economy in the built environment. This study specifically focuses on the built environment as one of the largest, most energy- and material-intensive industries globally, and investigates the following question: which digital technologies potentially enable a circular economy in the built environment, and in what ways? The research uses an iterative stepwise method: (1) framework development based on regenerating, narrowing, slowing and closing resource loop principles; (2) expert workshops to understand the usage of digital technologies in a circular built environment; (3) a literature and practice review to further populate the emerging framework with relevant digital technologies; and (4) the final mapping of digital technologies onto the framework. This study develops a novel Circular Digital Built Environment framework. It identifies and maps ten enabling digital technologies to facilitate a circular economy in the built environment. These include: (1) additive/robotic manufacturing, (2) artificial intelligence, (3) big data and analytics, (4) blockchain technology, (5) building information modelling, (6) digital platforms/marketplaces, (7) digital twins, (8) the geographical information system, (9) material passports/databanks, and (10) the internet of things. The framework provides a fruitful starting point for the novel research avenue at the intersection of circular economy, digital technology and the built environment, and gives practitioners inspiration for sustainable innovation in the sector.

show abstract

mentioning

confidence: 99%

Circular Digital Built Environment: An Emerging Framework

2021

View full text Add to dashboard Cite

show abstract

“…The accumulation of decoration waste has created a severe pollution problem, and turning this urban blight [1] into recycled solid waste [2,3] has become a hot issue in Europe [4][5][6] and China [7][8][9]. Some of the legislation, such as The Waste Framework Directive (2008/98/EC) [10] of the EU and the 2015 Circular Economy Promotion Plan issued by the China National Development and Reform Commission, made clear requirements for the recycling and managing of construction waste.…”

Section: Introductionmentioning

confidence: 99%

“…The D-VFFS was designed to increase the processing capacity and reduce the equipment space, material grading, transportation and equipment investment. For accurate and improved screening efficiency, the stiffness [21] of the isolation springs and shear springs were carefully designed [9]. The stiffness of the isolation springs was calculated according to the amplitude and mass of the screen, whereas the stiffness of the shear springs was calculated according to the working characteristics in the near-resonance area of the screen.…”

Section: Introductionmentioning

confidence: 99%

Study of Double-Deck Vibrating Flip-Flow Screen Based on Dynamic Stiffness Characteristics of Shear Springs

et al. 2021

View full text Add to dashboard Cite

Double-deck vibrating flip-flow screens have been widely used for the repurposing of decoration waste; however, the influence of shear spring stiffness on the screen’s vibration characteristics is under-researched. The shear spring stiffness affects the amplitude–frequency characteristics, phase–frequency characteristics, screening performance and processing capacity of the screen. In this paper, a mathematical model of the double-deck vibrating flip-flow screen is proposed based on a vibrating system with three degrees of freedom. Based on the experiments of the industrial screen, the amplitude–frequency and phase–frequency characteristics of the double-deck vibrating flip-flow screen were studied. Within the range of 25 to 75 rad/s, the amplitude of the main screen frame decreased gradually, the floating screen frames decreased at first and then increased and the amplitudes of the main and floating screen frames were dependent on the stiffness of the isolation springs and shear springs. When the frequency was 75 rad/s, the stiffness of the upper and lower shear springs was 11,440 kN/m, respectively, and the screening efficiency reached 97.09%.

show abstract

“…An intelligent waste management system architecture with IoT and CNN has achieved real-time monitoring of digestible and indigestible waste [18]. In addition, deep learning has been successfully applied in separation and classification of waste electrical and electronic equipment (WEEE) batteries [19], E-waste collection [20], construction solid waste classification [21], and automatic detection of waste in water [22]. The efficient and accurate detection of domestic waste will help the intelligent development of waste treatment.…”

Section: Introductionmentioning

confidence: 99%

Skip-YOLO: Domestic Garbage Detection Using Deep Learning Method in Complex Multi-scenes

Zhao

Pan

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

In In the field of garbage intelligent identification, similar garbage are difficult to be effectively detected due to different kinds of characteristics. This paper proposes a Skip-YOLO model for garbage detection in real life through the visual analysis of feature mapping in different neural networks. First of all, the receptive field of the model is enlarged through the large-size convolution kernel, which enhanced the shallow information of images. Secondly, the high-dimensional feature mappings of garbage is extracted by dense convolutional blocks. The sensitivity of similar features in the same type of garbage is enhanced by strengthening the sharing of shallow low semantics and deep high semantics information. Finally, the multi-scale high-dimensional feature mappings is integrated and sent to the YOLO layer to predict the type and location of garbage. Experimental results show that compared with the YOLOv3, the overall detection precision is increased by 22.5%, and the average recall rate is increased by 18.6%. In qualitative comparison, it successfully detects domestic garbage in complex multi-scenes. In addition, our approach alleviates the overfitting problem of deep residual blocks. The application case of waste sorting production line is used to further highlight the model generalization performance of our method.

show abstract

The classification of construction waste material using a deep convolutional neural network

Cited by 117 publications

References 62 publications

Circular Digital Built Environment: An Emerging Framework

Circular Digital Built Environment: An Emerging Framework

Study of Double-Deck Vibrating Flip-Flow Screen Based on Dynamic Stiffness Characteristics of Shear Springs

Skip-YOLO: Domestic Garbage Detection Using Deep Learning Method in Complex Multi-scenes

Contact Info

Product

Resources

About