A Hybrid Kinematic-Acoustic System for Automated Activity Detection of Construction Equipment

Sherafat, Behnam; Rashidi, Abbas; Lee, Yong-Cheol

doi:10.3390/s19194286

Cited by 33 publications

(18 citation statements)

References 66 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) SPECTRAL FLUX Spectral flux (SF) [44] measures the rate with which the power spectrum of a signal changes. The power spectrum from one window has been compared with the power spectrum from a preceding window of the signal.…”

Section: Figure 5 Renyi Entropy For Standing Sitting Picking Up An Ob...mentioning

confidence: 99%

MS-DLD: Multi-Sensors Based Daily Locomotion Detection via Kinematic-Static Energy and Body-Specific HMMs

et al. 2022

View full text Add to dashboard Cite

More adaptable and user-independent techniques are required for multi-sensors based daily locomotion detection (MS-DLD). This research study proposes a couple of locomotion detection methods using body-worn multi-sensors to successfully categorize several locomotion transitions, including falling, walking, jogging, and jumping, along with bodyspecific sensors based on the modified hidden Markov models (HMMs) approach. This research presents both standard and state-of-the-art methods for MS-DLD. Conventionally, to improve MS-DLD process, the proposed methodology consists of a wavelet transformed Quaternion-based filter for the inertial signals, patterns recognition in the form of kinematic-static energies, and state-of-the-art multi-features extraction. These features include entropy, spectral, and cepstral coefficients domains. Then, fuzzy logic-based optimization has been introduced in order to achieve the selective features by converting them into codewords. This paper also introduces another state-of-the-art way to model daily locomotion detection and derives body-specific modified HMMs. The model divides the sensor data into three active body-specific parts including head sensors, mid-body sensors, and lower body sensors. Body-specific modified HMMs have been provided with raw data for the three active body-specific sensors and gave better results with less computational complexities when compared to the conventional methods. The proposed systems have been experimentally assessed and trialed over three diverse publicly available datasets: the UP-Fall dataset consisting of falling and other daily life activities, the IM-WSHA dataset comprising everyday locomotion actions, and the ENABL3S gait and locomotion dataset consisting of multiple gait movements. Experimental outcomes indicate that the proposed conventional technique achieved improved results and outperformed existing systems based on detection accuracies of 90.0% and 87.5% over UP-Fall, 86.0% and 88.3% over IM-WSHA, and 86.7% and 90.0% over ENABL3S datasets for kinematic and static energy patterns, respectively. Further, the results show that the state-of-the-art body-specific modified HMMs method achieved 94.3% and 95.0% over UP-Fall, 92.0% and 93.3% over IM-WSHA, and 90.0% and 95.0% over ENABL3S datasets for kinematic and static patterned signals, respectively. The results of state-of-theart efficient system show a significant increase in detection accuracy when compared to standard systems.

show abstract

Section: Figure 5 Renyi Entropy For Standing Sitting Picking Up An Ob...mentioning

confidence: 99%

MS-DLD: Multi-Sensors Based Daily Locomotion Detection via Kinematic-Static Energy and Body-Specific HMMs

et al. 2022

View full text Add to dashboard Cite

show abstract

“…However, recently diverse studies investigated and showed the potentials of audiobased construction site monitoring, which can be a promising method for advanced unmanned field monitoring (Sherafat et al, 2020(Sherafat et al, , 2019. It has been found that this new approach can obtain satisfactory performance and reliability (Cho et al, 2017;Sharan & Moir, 2016;Lee et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Deep Belief Network based audio classification for construction sites monitoring

Scarpiniti

Colasante

Tanna

et al. 2021

Expert Systems with Applications

View full text Add to dashboard Cite

“…Ref. [ 10 ] proposed a sensor fusion method by configuring both kinematic and audio signals that permits the classification of the construction equipment’s activities.…”

Section: Introductionmentioning

confidence: 99%

Development of Integrative Methodologies for Effective Excavation Progress Monitoring

Abdullah

Seo

Khajepour

2021

Sensors

View full text Add to dashboard Cite

Excavation is one of the primary projects in the construction industry. Introducing various technologies for full automation of the excavation can be a solution to improve sensing and productivity that are the ongoing issues in this area. This paper covers three aspects of effective excavation progress monitoring that include excavation volume estimation, occlusion area detection, and 5D mapping. The excavation volume estimation component enables estimating the bucket volume and ground excavation volume. To achieve mapping of the hidden or occluded ground areas, integration of proprioceptive and exteroceptive sensing data was adopted. Finally, we proposed the idea of 5D mapping that provides the info of the excavated ground in terms of geometric space and material type/properties using a 3D ground map with LiDAR intensity and a ground resistive index. Through experimental validations with a mini excavator, the accuracy of the two different volume estimation methods was compared. Finally, a reconstructed map for occlusion areas and a 5D map were created using the bucket tip’s trajectory and multiple sensory data with convolutional neural network techniques, respectively. The created 5D map would allow for the provision of extended ground information beyond a normal 3D ground map, which is indispensable to progress monitoring and control of autonomous excavation.

show abstract

A Hybrid Kinematic-Acoustic System for Automated Activity Detection of Construction Equipment

Cited by 33 publications

References 66 publications

MS-DLD: Multi-Sensors Based Daily Locomotion Detection via Kinematic-Static Energy and Body-Specific HMMs

MS-DLD: Multi-Sensors Based Daily Locomotion Detection via Kinematic-Static Energy and Body-Specific HMMs

Deep Belief Network based audio classification for construction sites monitoring

Development of Integrative Methodologies for Effective Excavation Progress Monitoring

Contact Info

Product

Resources

About