FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034174782> ?p ?o ?g. }

• W3034174782 abstract "The motivation for this research stems from the promise of coupling multi-sensory systems and advanced data analytics to enhance holistic situational awareness and thus prevent fatal accidents in the construction industry. The construction industry is one of the most dangerous industries in the U.S. and worldwide. Occupational Safety and Health Administration (OSHA) reports that the construction sector employs only 5% of the U.S. workforce, but accounts for 21.1% (1,008 deaths) of the total worker fatalities in 2018. The struck-by accident is one of the leading causes and it alone led to 804 fatalities between 2011 and 2015. A critical contributing factor to struck-by accidents is the lack of holistic situational awareness, attributed to the complex and dynamic nature of the construction environment. In the context of construction site safety, situational awareness consists of three progressive levels: perception – to perceive the status of construction entities on the jobsites, comprehension – to understand the ongoing construction activities and interactions among entities, and projection – to predict the future status of entities on the dynamic jobsites. In this dissertation, holistic situational awareness refers to the achievement at all three levels. It is critical because with the absence of holistic situational awareness, construction workers may not be able to correctly recognize the potential hazards and predict the severe consequences, either of which will pose workers in great danger and may result in construction accidents. While existing studies have been successful, at least partially, in improving the perception of real-time states on construction sites such as locations and movements of jobsite entities, they overlook the capability of understanding the jobsite context and predicting entity behavior (i.e., movement) to develop the holistic situational awareness. This presents a missed opportunity to eliminate construction accidents and save hundreds of lives every year. Therefore, there is a critical need for developing holistic situational awareness of the complex and dynamic construction sites by accurately perceiving states of individual entities, understanding the jobsite contexts, and predicting entity movements.The overarching goal of this research is to minimizethe risk of struck-by accidents on construction jobsiteby enhancing the holistic situational awareness of the unstructured and dynamicconstruction environment through a novel data-driven approach. Towards that end, three fundamentalknowledge gaps/challenges have been identified and each of them is addressed ina specific objective in this research.Thefirst knowledge gap is the lack of methods in fusing heterogeneous data frommultimodal sensors to accurately perceive the dynamic states of constructionentities. The congested and dynamic nature of construction sites has posedgreat challenges such as signal interference and line of sight occlusion to a singlemode of sensor that is bounded by its own limitation in perceiving the site dynamics.The research hypothesis is that combining data of multimodal sensors that serveas mutual complementation achieves improved accuracy in perceiving dynamicstates of construction entities. This research proposes a hybrid framework thatleverages vision-based localization and radio-based identification for robust3D tracking of multiple construction workers. It treats vision-basedtracking as the main source to obtain object trajectory and radio-basedtracking as a supplementary source for reliable identity information. It was found that fusing visualand radio data increases the overall accuracy from 88% and 87% to 95% and 90%in two experiments respectively for 3D tracking of multiple constructionworkers, and is more robust with the capability to recoverthe same entity ID after fragmentation compared to using vision-based approachalone.Thesecond knowledge gap is the missing link between entity interaction patternsand diverse activities on the jobsite. With multiple construction workers andequipment co-exist and interact on the jobsite to conduct various activities,it is extremely difficult to automatically recognize ongoing activities onlyconsidering the spatial relationship between entities using pre-defined rules, aswhat has been done in most existing studies. The research hypothesis is thatincorporating additional features such as attentional cues better representsentity interactions and advanced deep learning techniques automates the learningof the complex interaction patterns underlying diverse activities. Thisresearch proposes a two-step long short-term memory (LSTM)approach to integrate the positional and attentional cues to identify workinggroups and recognize corresponding group activities. A series of positional andattentional cues are modeled to represent the interactions among entities, and theLSTM network is designed to (1) classify whether two entities belong to thesame group, and (2) recognize the activities they are involved in. It was foundthat by leveraging both positional and attentional cues, the accuracy increasesfrom 85% to 95% compared with cases using positional cues alone. Moreover,dividing the group activity recognition task into a two-step cascading process improvesthe precision and recall rates of specific activities by about 3%-12% comparedto simply conducting a one-step activity recognition.Thethird knowledge gap is the non-determining role of jobsite context on entitymovements. Worker behavior on a construction site is goal-based and purposeful,motivated and influenced by the jobsite context including their involvedactivities and the status of other entities. Construction workers constantlyadjust their movements in the unstructured and dynamic workspace, making itchallenging to reliably predict worker trajectory only considering theirprevious movement patterns. The research hypothesis is that combining themovement patterns of the target entity with the jobsite context more accuratelypredicts the trajectory of the entity. This research proposes acontext-augmented LSTM method, which incorporates both individualmovement and workplace contextual information, for better trajectory prediction.Contextual information regarding movements of neighboring entities, workinggroup information, and potential destination information is concatenated withmovements of the target entity and fed into an LSTM network with anencoder-decoder architecture to predict trajectory over multiple time steps. Itwas found that integrating contextual information with target movementinformation can result in a smaller final displacement error compared to thatobtained only considering the previous movement, especially when the length ofprediction is longer than the length of observation. Insights are also providedon the selection of appropriate methods.The results and findings of this dissertation will augment the holistic situational awareness of site entities in an automatic way and enable them to have a better understanding of the ongoing jobsite context and a more accurate prediction of future states, which in turn allows the proactive detection of any potential collisions." @default.
• W3034174782 created "2020-06-19" @default.
• W3034174782 creator A5091163395 @default.
• W3034174782 date "2020-06-16" @default.
• W3034174782 modified "2023-09-26" @default.
• W3034174782 title "DATA-DRIVEN APPROACH TO HOLISTIC SITUATIONAL AWARENESS IN CONSTRUCTION SITE SAFETY MANAGEMENT" @default.
• W3034174782 cites W2033819227 @default.
• W3034174782 cites W2064675550 @default.
• W3034174782 cites W2065465218 @default.
• W3034174782 cites W2089253196 @default.
• W3034174782 cites W2096122410 @default.
• W3034174782 cites W2109192831 @default.
• W3034174782 cites W2110285718 @default.
• W3034174782 cites W2194775991 @default.
• W3034174782 cites W2415953079 @default.
• W3034174782 cites W2424778531 @default.
• W3034174782 cites W2761342458 @default.
• W3034174782 cites W2782274301 @default.
• W3034174782 cites W2802595503 @default.
• W3034174782 cites W2891223819 @default.
• W3034174782 cites W2941570898 @default.
• W3034174782 cites W2953751569 @default.
• W3034174782 doi "https://doi.org/10.25394/pgs.12412808.v1" @default.
• W3034174782 hasPublicationYear "2020" @default.
• W3034174782 type Work @default.
• W3034174782 sameAs 3034174782 @default.
• W3034174782 citedByCount "0" @default.
• W3034174782 crossrefType "dissertation" @default.
• W3034174782 hasAuthorship W3034174782A5091163395 @default.
• W3034174782 hasConcept C107053488 @default.
• W3034174782 hasConcept C112930515 @default.
• W3034174782 hasConcept C127413603 @default.
• W3034174782 hasConcept C144133560 @default.
• W3034174782 hasConcept C145804949 @default.
• W3034174782 hasConcept C146978453 @default.
• W3034174782 hasConcept C15744967 @default.
• W3034174782 hasConcept C166957645 @default.
• W3034174782 hasConcept C169760540 @default.
• W3034174782 hasConcept C17744445 @default.
• W3034174782 hasConcept C199539241 @default.
• W3034174782 hasConcept C205649164 @default.
• W3034174782 hasConcept C26760741 @default.
• W3034174782 hasConcept C2778139618 @default.
• W3034174782 hasConcept C2779343474 @default.
• W3034174782 hasConcept C2984708878 @default.
• W3034174782 hasConcept C39549134 @default.
• W3034174782 hasConcept C41008148 @default.
• W3034174782 hasConcept C56739046 @default.
• W3034174782 hasConcept C66938386 @default.
• W3034174782 hasConcept C75630572 @default.
• W3034174782 hasConcept C77805123 @default.
• W3034174782 hasConcept C86804380 @default.
• W3034174782 hasConcept C9114305 @default.
• W3034174782 hasConceptScore W3034174782C107053488 @default.
• W3034174782 hasConceptScore W3034174782C112930515 @default.
• W3034174782 hasConceptScore W3034174782C127413603 @default.
• W3034174782 hasConceptScore W3034174782C144133560 @default.
• W3034174782 hasConceptScore W3034174782C145804949 @default.
• W3034174782 hasConceptScore W3034174782C146978453 @default.
• W3034174782 hasConceptScore W3034174782C15744967 @default.
• W3034174782 hasConceptScore W3034174782C166957645 @default.
• W3034174782 hasConceptScore W3034174782C169760540 @default.
• W3034174782 hasConceptScore W3034174782C17744445 @default.
• W3034174782 hasConceptScore W3034174782C199539241 @default.
• W3034174782 hasConceptScore W3034174782C205649164 @default.
• W3034174782 hasConceptScore W3034174782C26760741 @default.
• W3034174782 hasConceptScore W3034174782C2778139618 @default.
• W3034174782 hasConceptScore W3034174782C2779343474 @default.
• W3034174782 hasConceptScore W3034174782C2984708878 @default.
• W3034174782 hasConceptScore W3034174782C39549134 @default.
• W3034174782 hasConceptScore W3034174782C41008148 @default.
• W3034174782 hasConceptScore W3034174782C56739046 @default.
• W3034174782 hasConceptScore W3034174782C66938386 @default.
• W3034174782 hasConceptScore W3034174782C75630572 @default.
• W3034174782 hasConceptScore W3034174782C77805123 @default.
• W3034174782 hasConceptScore W3034174782C86804380 @default.
• W3034174782 hasConceptScore W3034174782C9114305 @default.
• W3034174782 hasLocation W30341747821 @default.
• W3034174782 hasOpenAccess W3034174782 @default.
• W3034174782 hasPrimaryLocation W30341747821 @default.
• W3034174782 hasRelatedWork W133112532 @default.
• W3034174782 hasRelatedWork W1527614998 @default.
• W3034174782 hasRelatedWork W1775016707 @default.
• W3034174782 hasRelatedWork W1971656544 @default.
• W3034174782 hasRelatedWork W2124294631 @default.
• W3034174782 hasRelatedWork W2124601375 @default.
• W3034174782 hasRelatedWork W2128956787 @default.
• W3034174782 hasRelatedWork W2519205862 @default.
• W3034174782 hasRelatedWork W2560683968 @default.
• W3034174782 hasRelatedWork W2765196628 @default.
• W3034174782 hasRelatedWork W2901301243 @default.
• W3034174782 hasRelatedWork W2903548495 @default.
• W3034174782 hasRelatedWork W2904102527 @default.
• W3034174782 hasRelatedWork W2946705317 @default.
• W3034174782 hasRelatedWork W2996874072 @default.
• W3034174782 hasRelatedWork W3094473933 @default.
• W3034174782 hasRelatedWork W3117476796 @default.
• W3034174782 hasRelatedWork W343450280 @default.
• W3034174782 hasRelatedWork W638212880 @default.
• W3034174782 hasRelatedWork W282341694 @default.

• next