Search results

The purpose of this study is to monitor the progress of construction activities in an automated way by using sensor-based technologies for tracking multiple resources that are used in building construction.

An automated on-site progress monitoring approach was proposed and a proof-of-concept prototype was developed, followed by a field experimentation study at a high-rise building construction site. The developed approach was used to integrate sensor data collected from multiple resources used in different steps of an activity. It incorporated the domain-specific heuristics that were related to the site layout conditions and method of activity.

The prototype estimated the overall progress with 95% accuracy. More accurate and up-to-date progress measurement was achieved compared to the manual approach, and the need for visual inspections and manual data collection from the field was eliminated. Overall, the field experiments demonstrated that low-cost implementation is possible, if readily available or embedded sensors on equipment are used.

Previous studies either monitored one particular piece of equipment or the developed approaches were only applicable to limited activity types. This study demonstrated that it is technically feasible to determine progress at the site by fusing sensor data that are collected from multiple resources during the construction of building superstructure. The rule-based reasoning algorithms, which were developed based on a typical work practice of cranes and hoists, can be adapted to other activities that involve transferring bulk materials and use cranes and/or hoists for material handling.

This paper aims to propose a deployment optimization and efficient synchronous acquisition method for compressive stress sensors used by stress distribution law research based on the genetic algorithm and numerical simulations. The authors established a new method of collecting the mining compressive stress-strain distribution data to address the problem of the number of sensors and to optimize the sensor locations in physical similarity simulations to improve the efficiency and accuracy of data collection.

First, numerical simulations were used to obtain the compressive stress distribution curve under specific mining conditions. Second, by comparing the mean square error between a fitted curve and simulation data for different numbers of sensors, a genetic algorithm was used to optimize the three-dimensional (3D) spatial deployment of sensors. Third, the authors designed an efficient synchronous acquisition module to allow distributed sensors to achieve synchronous and efficient acquisition of hundreds of data points through a built-in on-board database and a synchronous sampling communication structure.

The sensor deployment scheme was established through the genetic algorithm, A synchronous and selective data acquisition method was established for reduced the amount of sensor data required under synchronous acquisition and improved the system acquisition efficiency. The authors obtained a 3D compressive stress distribution when the advancement was 200 m on a large-scale 3D physical similarity simulation platform.

The proposed method provides a new optimization method for sensor deployment in physical similarity simulations, which improves the efficiency and accuracy of system data acquisition, providing accurate acquisition data for experimental data analysis.

The paper aims to develop a novel method for the classification of different physical activities of a human being, using fabric sensors. This method focuses mainly on classifying the physical activity between normal action and violent attack on a victim and verifies its validity.

The system is realized as a protective jacket that can be worn by the subject. Stretch sensors, pressure sensors and a 9 degree of freedom accelerometer are strategically woven on the jacket. The jacket has an internal bus system made of conductive fabric that connects the sensors to the Flora chip, which acts as the data acquisition unit for the data generated. Different activities such as still, standing up, walking, twist-jump-turn, dancing and violent action are performed. The jacket in this study is worn by a healthy subject. The main phases which describe the activity recognition method undertaken in this study are the placement of sensors, pre-processing of data and deploying machine learning models for classification.

The effectiveness of the method was validated in a controlled environment. Certain challenges are also faced in building the experimental setup for the collection of data from the hardware. The most tedious challenge is to collect the data without noise and error, created by voltage fluctuations when stretched. The results show that the support vector machine classifier can classify different activities and is able to differentiate normal action and violent attacks with an accuracy of 98.8%, which is superior to other methods and algorithms.

This study leads to an understanding of human physical movement under violent activity. The results show that data compared with normal physical motion, which includes even a form of dance is quite different from the data collected during violent physical motion. This jacket construction with woven sensors can capture every dimension of the physical motion adding features to the data on which the machine learning model will be built.

Unlike other studies, where sensors are placed on isolated parts of the body, in this study, the fabric sensors are woven into the fabric itself to collect the data and to achieve maximum accuracy instead of using isolated wearable sensors. This method, together with a fabric pressure and stretch sensors, can provide key data and accurate feedback information when the victim is being attacked or is in a normal state of action.

The purpose of this paper is to describe how healthy performance of facilities can be monitored and performance data delivered as information flow according to specific user groups' needs.

The context of performance in facilities is described, and a tool for the collection of performance data and communicating the data as relevant information for the facility management (FM) and other stake holders is developed.

Various user groups are utilizing the same performance data to ensure optimal and healthy conditions. The integration of performance data to deliver meaningful and exploitable results for each user requires collection of the relevant data, compilation of data into information, and delivery of user specific information to the correct instance. A performance sensing system with data management was developed into a FM tool for this purpose.

FM is enabled to real time decision making by sensor‐based performance monitoring.

The results are generic and FM tools may be built on this basis for the specific information and display needs of various FM professionals and other stakeholders.

Workplace space utilization data reveals patterns of space usage, the occupants’ presence and mobility within the office building. Nowadays, emerging technology such as smart sensors and devices can revolutionize the measurement of space utilization data, which is originally dominated by human observers with paper and pencil. However, these novel instruments are often used in an old fashion, which restricts the exploitation of their full potential. This study aims to shed new light on the benefits and limits of using smart technology in measuring space utilization data and discusses the challenges and opportunities in analyzing the data measured by smart sensors.

First, the literature regarding common methods and previous studies about office space utilization measurement was reviewed. Then, a data set consisting of space utilization data collected through Passive Infra-Red sensors for 35 meeting rooms in a bank building was carefully evaluated. Finally, the space utilization results based on methods calculated in two different granularities were compared.

The number of occupied hours calculated at an hour level was 1.32-hour larger than that calculated at a minute level. As both results show the concept of space utilization, which was the amount of time that the space was occupied, this paper revealed a gap between the two space utilization calculation methods and further discussed the issues and challenges for future space utilization data analysis and benchmarking.

To the best of the authors’ knowledge, this is the first study critically addressing office space utilization issues by comparing calculation methods in different granularity.

As the limited energy of wireless sensor networks (WSNs), energy-efficient data-gathering algorithms are required. This paper proposes a compressive data-gathering algorithm based on double sparse structure dictionary learning (DSSDL). The purpose of this paper is to reduce the energy consumption of WSNs.

The historical data is used to construct a sparse representation base. In the dictionary-learning stage, the sparse representation matrix is decomposed into the product of double sparse matrices. Then, in the update stage of the dictionary, the sparse representation matrix is orthogonalized and unitized. The finally obtained double sparse structure dictionary is applied to the compressive data gathering in WSNs.

The dictionary obtained by the proposed algorithm has better sparse representation ability. The experimental results show that, the sparse representation error can be reduced by at least 3.6% compared with other dictionaries. In addition, the better sparse representation ability makes the WSNs achieve less measurement times under the same accuracy of data gathering, which means more energy saving. According to the results of simulation, the proposed algorithm can reduce the energy consumption by at least 2.7% compared with other compressive data-gathering methods under the same data-gathering accuracy.

In this paper, the double sparse structure dictionary is introduced into the compressive data-gathering algorithm in WSNs. The experimental results indicate that the proposed algorithm has good performance on energy consumption and sparse representation.

Accidents resulting from poorly planned or setup work environments are a major concern within the construction industry. While traditional education and training of personnel offer well-known approaches for establishing safe work practices, serious games in virtual reality (VR) are increasingly being used as a complementary approach for active learning experiences. By taking full advantage of data collection and the interactions possible in the virtual environment, the education and training of construction personnel improves by using non-biased feedback and immersion.

This research presents a framework for the generation and automated assessment of VR data. The proposed approach is tested and evaluated in a virtual work environment consisting of multiple hazards. VR requires expensive hardware, technical knowledge and user acceptance to run the games effectively. An effort has been made to transfer the advantages VR gives to a physical setup. This is done using a light detection and ranging sensing system, which collects similar data and enables the same learning experiences.

Encouraging results on the participants’ experiences are presented and discussed based on actual needs in the Danish construction industry. An outlook presents future avenues towards enhancing existing learning methods.

The proposed method will help develop active learning environments, which could lead to safer construction work stations in the future, either through VR or physical simulations.

The utilization of run-time data collection and automatic analysis allows for better personalized feedback in the construction safety training. Furthermore, this study investigates the possibility of transferring the benefits of this system to a physical setup that is easier to use on construction sites without investing in a full VR setup.

Autonomous driving depends on the collection, processing and analysis of environmental information and vehicle information. Environmental perception and processing are important prerequisite for the safety of self-driving of vehicles; it involves road boundary detection, vehicle detection, pedestrian detection using sensors such as laser rangefinder, video camera, vehicle borne radar, etc.

Subjected to various environmental factors, the data clock information is often out of sync because of different data acquisition frequency, which leads to the difficulty in data fusion. In this study, according to practical requirements, a multi-sensor environmental perception collaborative method was first proposed; then, based on the principle of target priority, large-scale priority, moving target priority and difference priority, a multi-sensor data fusion optimization algorithm based on convolutional neural network was proposed.

The average unload scheduling delay of the algorithm for test data before and after optimization under different network transmission rates. It can be seen that with the improvement of network transmission rate and processing capacity, the unload scheduling delay decreased after optimization and the performance of the test results is the closest to the optimal solution indicating the excellent performance of the optimization algorithm and its adaptivity to different environments.

In this paper, the results showed that the proposed method significantly improved the redundancy and fault tolerance of the system thus ensuring fast and correct decision-making during driving.

Indoor air quality monitoring is extremely important in urban, industrial areas. Considering the devastating effect of declining quality of air in major part of the countries like India and China, it is highly recommended to monitor the quality of air which can help people with respiratory diseases, children and elderly people to take necessary precautions and stay safe at their homes. The purpose of this study is to detect air quality and perform predictions which could be part of smart home automation with the use of newer technology.

This study proposes an Internet-of-Things (IoT)-based air quality measurement, warning and prediction system for ambient assisted living. The proposed ambient assisted living system consists of low-cost air quality sensors and ESP32 controller with new generation embedded system architecture. It can detect Indoor Air Quality parameters like CO, PM2.5, NO2, O3, NH3, temperature, pressure, humidity, etc. The low cost sensor data are calibrated using machine learning techniques for performance improvement. The system has a novel prediction model, multiheaded convolutional neural networks-gated recurrent unit which can detect next hour pollution concentration. The model uses a transfer learning (TL) approach for prediction when the system is new and less data available for prediction. Any neighboring site data can be used to transfer knowledge for early predictions for the new system. It can have a mobile-based application which can send warning notifications to users if the Indoor Air Quality parameters exceed the specified threshold values. This is all required to take necessary measures against bad air quality.

The IoT-based system has implemented the TL framework, and the results of this study showed that the system works efficiently with performance improvement of 55.42% in RMSE scores for prediction at new target system with insufficient data.

This study demonstrates the implementation of an IoT system which uses low-cost sensors and deep learning model for predicting pollution concentration. The system is tackling the issues of the low-cost sensors for better performance. The novel approach of pretrained models and TL work very well at the new system having data insufficiency issues. This study contributes significantly with the usage of low-cost sensors, open-source advanced technology and performance improvement in prediction ability at new systems. Experimental results and findings are disclosed in this study. This will help install multiple new cost-effective monitoring stations in smart city for pollution forecasting.

Digital documentation techniques of tunneling excavations at archaeological sites are becoming more common. These methods, such as photogrammetry and LiDAR (Light Detection and Ranging), are able to create precise three-dimensional models of excavations to complement traditional forms of documentation with millimeter to centimeter accuracy. However, these techniques require either expensive pieces of equipment or a long processing time that can be prohibitive during short field seasons in remote areas. This article aims to determine the effectiveness of various low-cost sensors and real-time algorithms to create digital scans of archaeological excavations.

The authors used a class of algorithms called SLAM (Simultaneous Localization and Mapping) along with depth-sensing cameras. While these algorithms have largely improved over recent years, the accuracy of the results still depends on the scanning conditions. The authors developed a prototype of a scanning device and collected 3D data at a Maya archaeological site and refined the instrument in a system of natural caves. This article presents an analysis of the resulting 3D models to determine the effectiveness of the various sensors and algorithms employed.

While not as accurate as commercial LiDAR systems, the prototype presented, employing a time-of-flight depth sensor and using a feature-based SLAM algorithm, is a rapid and effective way to document archaeological contexts at a fraction of the cost.

The proposed system is easy to deploy, provides real-time results and would be particularly useful in salvage operations as well as in high-risk areas where cultural heritage is threatened.

This article compares many different low-cost scanning solutions for underground excavations, along with presenting a prototype that can be easily replicated for documentation purposes.