Activity identification in modular construction using audio signals and machine learning

Rashid, Khandakar M.; Louis, Joseph

doi:10.1016/j.autcon.2020.103361

Cited by 48 publications

(39 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this method, a significant proportion of construction work is conducted in a factory rather than onsite, resulting in reduced civil complaints, construction duration, waste, and cost while providing higher quality. Therefore, this method is considered an effective and sustainable solution for dealing with the growing housing demand in urban areas [2,9,10]. In particular, modular construction is being used in cities such as Hong Kong, Singapore, and Melbourne to rapidly and efficiently construct buildings in both the private and the public sectors [10,11].…”

Section: Introductionmentioning

confidence: 99%

Framework for Long-Term Public Housing Supply Plan Focusing on Small-Scale Offsite Construction in Seoul

et al. 2021

View full text Add to dashboard Cite

The public housing demand in Seoul has been continuously increasing, but the available land for housing is insufficient. To meet the demand, the Seoul government is planning to develop small-scale housing in urban areas through various methods. Construction activities for increasing housing capacity cause negative environmental impacts, and this inevitably leads to an increase in the number of civil complaints. The complaints can be mitigated by using offsite construction (OSC) for fabricating components. However, OSC remains underdeveloped in Korea owing to concerns over high project costs. To promote OSC, the government must develop a long-term plan to secure demand for OSC. For such a plan, the number and feasibility of applicable sites in Seoul must be estimated. This study suggests a two-stage research framework: (1) estimate the number of applicable sites in Seoul using GIS and (2) conduct feasibility analyses of these sites through architectural planning. The estimated number of sites was equal to the expected supply of small-scale housing units in Seoul for 8 years, and the selected case sites were identified to be feasible. Therefore, the use of OSC for developing small-scale housing units in Seoul is reasonable. This research differs from previous studies in that the previous use of qualitative studies to promote modular construction was replaced with a quantitative analysis that included the entire Seoul area. Using the research framework, the Seoul government can develop a specific long-term plan based on the quantitative research analysis. Furthermore, manufacturers can develop plans based on the government plan and deliver returns on the higher initial costs. The contractors can reduce the higher project cost and doing so is expected to mitigate the negative perception and to promote modular construction in Korea.

show abstract

Section: Introductionmentioning

confidence: 99%

Framework for Long-Term Public Housing Supply Plan Focusing on Small-Scale Offsite Construction in Seoul

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Several different features are used across the publications. Rashid and Louis (2020) utilize four domain-specific feature sets for their classification: time-, frequency-, cepstral-, and wavelet-domain features. Their algorithm was used to classify activities: nailing with nail-gun, hammering, table-saw cutting, and drilling.…”

Section: Audio-based Methodsmentioning

confidence: 99%

“…As the experiments differ in activities classified, experimental setup, and data quantities, it is impossible to compare these to each other, which is also why it is impossible to state which features are the most important when using audio-based methods for classifying activities. However, Rashid and Louis (2020), who use in total 318 features, shows that for their experiments, cepstral-domain features contribute the most to the algorithm's performance and wavelet-domain features contribute the least.…”

Section: Audio-based Methodsmentioning

confidence: 99%

Automating the Estimation of Productivity Metrics for Construction Workers Using Deep Learning and Kinematics

Jacobsen¹,

Teizer²

2022

Proceedings of the 29th EG-ICE International Workshop on Intelligent Computing in Engineering

View full text Add to dashboard Cite

In this study, a novel method for direct work estimation is used to classify whether a painteris performingdirect workor not.The aim is to build an accurate and reliable work classification algorithmthatcanhelp monitorconstruction sites.The method utilizes adeep learning algorithmusing convolutional and long short-term memory layersto classify multivariate time-series data collected from five inertial measurement units (IMUs)mounted on the workers’arms, torso,and legs.Three models are developed, differing in window sizes from 3 seconds to 7 seconds.Thebest performingmodel achieves an accuracy of 90%and anF1-score of 87.6%. This is thefirst step towards a general model that canclassify productivity measures for workers on construction sites, which will be a valuableinput formonitoringconstruction sitesandfuture analyses.

show abstract

“…In this generation process of image data, time series from tests are transformed into frequency spectrums by using short-time Fourier transform (STFT). For an original discrete signal sequence x(n), a pre-determined window function is used to divide the time series into many segments, and it is assumed the signal is pseudo-stationary over a short interval, and then Fourier transform is carried out on each window length (Bendory et al, 2017;Rashid and Louis, 2020). The transform process of STFT is shown in Figure 3.…”

Section: Generation Of Spectrum Image Datamentioning

confidence: 99%

A Novel Piezoceramic-Based Sensing Technology Combined With Visual Domain Networks for Timber Damage Quantification

et al. 2021

View full text Add to dashboard Cite

Early detection of timber damage is essential for the safety of timber structures. In recent decades, wave-based approaches have shown great potential for structural damage assessment. Current damage assessment accuracy based on sensing signals in the time domain is highly affected by the varied boundary conditions and environmental factors in practical applications. In this research, a novel piezoceramic-based sensing technology combined with a visual domain network was developed to quantitatively evaluate timber damage conditions. Numerical and experimental studies reveal the stress wave propagation properties in different cases of timber crack depths. Through the spectrogram visualization process, all sensing signals in the time domain were transferred to images which contain both time and frequency features of signals collected from different crack conditions. A deep neural network (DNN) was adopted for image training, testing, and classification. The classification results show high efficiency and accuracy for identifying crack conditions for timber structures. The proposed technology can be further integrated with a fielding sensing system to provide real-time monitoring of timber damage in field applications.

show abstract

Activity identification in modular construction using audio signals and machine learning

Cited by 48 publications

References 42 publications

Framework for Long-Term Public Housing Supply Plan Focusing on Small-Scale Offsite Construction in Seoul

Framework for Long-Term Public Housing Supply Plan Focusing on Small-Scale Offsite Construction in Seoul

Automating the Estimation of Productivity Metrics for Construction Workers Using Deep Learning and Kinematics

A Novel Piezoceramic-Based Sensing Technology Combined With Visual Domain Networks for Timber Damage Quantification

Contact Info

Product

Resources

About