Search results

Current solutions for monitoring the progress of pavement construction (such as collecting, processing and analysing data) are inefficient, labour-intensive, time-consuming, tedious and error-prone. In this study, an automated solution proposes sensors prototype mounted unmanned ground vehicle (UGV) for data collection, an LSTM classifier for road layer detection, the integrated algorithm for as-built progress calculation and web-based as-built reporting.

The crux of the proposed solution, the road layer detection model, is proposed to develop from the layer change detection model and rule-based reasoning. In the beginning, data were gathered using a UGV with a laser ToF (time-of-flight) distance sensor, accelerometer, gyroscope and GPS sensor in a controlled environment. The long short-term memory (LSTM) algorithm was utilised on acquired data to develop a classifier model for layer change detection, such as layer not changed, layer up and layer down.

In controlled environment experiments, the classification of road layer changes achieved 94.35% test accuracy with 14.05% loss. Subsequently, the proposed approach, including the layer detection model, as-built measurement algorithm and reporting, was successfully implemented with a real case study to test the robustness of the model and measure the as-built progress.

The implementation of the proposed framework can allow continuous, real-time monitoring of road construction projects, eliminating the need for manual, time-consuming methods. This study will potentially help the construction industry in the real time decision-making process of construction progress monitoring and controlling action.

This first novel approach marks the first utilization of sensors mounted UGV for monitoring road construction progress, filling a crucial research gap in incremental and segment-wise construction monitoring and offering a solution that addresses challenges faced by Unmanned Aerial Vehicles (UAVs) and 3D reconstruction. Utilizing UGVs offers advantages like cost-effectiveness, safety and operational flexibility in no-fly zones.

This study aims to develop an architectural prototype of a Cyber-Physical System (CPS), as well as lay a technological foundation for future smart housing with improved health and well-being outcomes for its occupants.

This study deploys smart sensors to monitor the key environmental parameters of a house. Using Internet of Things technology, a prototype of a CPS has been developed for capturing the environmental conditions over time. A case study involving a property in New Zealand was undertaken to validate the prototype.

The study proposes a monitoring platform, enabled by the CPS and smart sensing devices, that collects, shares, stores, analyses and visualises indoor environment data. The reliability and accuracy of the monitoring system were enhanced by comparing the activity of house occupants with sensor data.

Due to limited time, the prototype was tested in one house for a period of one month. Air quality was not considered in this study. However, the work suggests that such an approach provides an effective solution for government organisations and housing agencies to collect information for the purpose of assessing building thermal performance.

This research proposes a new lens consisting of a home environment monitoring application with health and well-being implications. It could also be used to inform the future design of healthy homes and buildings, both in New Zealand and internationally.

The electronic nose is an array of chemical or gas sensors and associated with a pattern-recognition framework competent in identifying and classifying odorant or non-odorant and simple or complex gases. Despite more than 30 years of research, the robust e-nose device is still limited. Most of the challenges towards reliable e-nose devices are associated with the non-stationary environment and non-stationary sensor behaviour. Data distribution of sensor array response evolves with time, referred to as non-stationarity. The purpose of this paper is to provide a comprehensive introduction to challenges related to non-stationarity in e-nose design and to review the existing literature from an application, system and algorithm perspective to provide an integrated and practical view.

The authors discuss the non-stationary data in general and the challenges related to the non-stationarity environment in e-nose design or non-stationary sensor behaviour. The challenges are categorised and discussed with the perspective of learning with data obtained from the sensor systems. Later, the e-nose technology is reviewed with the system, application and algorithmic point of view to discuss the current status.

The discussed challenges in e-nose design will be beneficial for researchers, as well as practitioners as it presents a comprehensive view on multiple aspects of non-stationary learning, system, algorithms and applications for e-nose. The paper presents a review of the pattern-recognition techniques, public data sets that are commonly referred to as olfactory research. Generic techniques for learning in the non-stationary environment are also presented. The authors discuss the future direction of research and major open problems related to handling non-stationarity in e-nose design.

The authors first time review the existing literature related to learning with e-nose in a non-stationary environment and existing generic pattern-recognition algorithms for learning in the non-stationary environment to bridge the gap between these two. The authors also present details of publicly available sensor array data sets, which will benefit the upcoming researchers in this field. The authors further emphasise several open problems and future directions, which should be considered to provide efficient solutions that can handle non-stationarity to make e-nose the next everyday device.

The purpose of this paper is to provide local environmental information to raise community’s environmental awareness, as a cornerstone to improve the quality of the built environment. Next to that, it provides environmental information to professionals and academia in the fields of urbanism and urban microclimate, making it available for reuse.

The wireless sensor network (WSN) consists of sensor platforms deployed at fixed locations in the urban environment, measuring temperature, humidity, noise and air quality. Measurements are transferred to a server via long range wide area network (LoRaWAN). Data are also processed and publicly disseminated via the server. The WSN is made interactive as to increase user involvement, i.e. people who pass by a physical sensor in the city can interact with the sensor platform and request specific environmental data in near real time.

Microclimate phenomena such as temperature, humidity and air quality can be successfully measured with a WSN. Noise measurements are less suitable to send over LoRaWAN due to high temporal variations.

Further testing and development of the sensor modules is needed to ensure consistent measurements and data quality.

Due to time and budget limitations for the project group, it was not possible to gather reliable data for noise and air quality. Therefore, conclusions on the effect of the measurements on the built environment cannot currently be drawn.

An autonomously working low-cost low-energy WSN gathering near real-time environmental data is successfully deployed. Ensuring data quality of the measurement results is subject for upcoming research.

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.

Behavioral pattern mining for intelligent system such as SmEs sensor data are vitally important in many applications and performance optimizations. Sensor pattern mining (SPM) is also dynamic and a hot research issue to pervasive and ubiquitous of smart technologies toward improving human life. However, in large-scale sensor data, exploring and mining pattern, which leads to detect the abnormal behavior is challenging. The paper aims to discuss these issues.

Sensor data are complex and multivariate, for example, which data captured by the sensors, how it is precise, what properties are recorded or measured, are important research issues. Therefore, the method, the authors proposed Sequential Data Mining (SDM) approach to explore pattern behaviors toward detecting abnormal patterns for smart space fault diagnosis and performance optimization in the intelligent world. Sensor data types, modeling, descriptions and SPM techniques are discussed in depth using real sensor data sets.

The outcome of the paper is measured as introducing a novel idea how SDM technique’s scale-up to sensor data pattern mining. In the paper, the approach and technicality of the sensor data pattern analyzed, and finally the pattern behaviors detected or segmented as normal and abnormal patterns.

The paper is focussed on sensor data behavioral patterns for fault diagnosis and performance optimizations. It is other ways of knowledge extraction from the anomaly of sensor data (observation records), which is pertinent to adopt in many intelligent systems applications, including safety and security, efficiency, and other advantages as the consideration of the real-world problems.

This study aims to introduce an innovative approach to predictive maintenance by integrating time-series sensor data with event logs, leveraging the synergistic potential of deep learning models. The primary goal is to enhance the accuracy of equipment failure predictions, thereby minimizing operational downtime.

The methodology uses a dual-model architecture, combining the patch time series transformer (PatchTST) model for analyzing time-series sensor data and bidirectional encoder representations from transformers for processing textual event log data. Two distinct fusion strategies, namely, early and late fusion, are explored to integrate these data sources effectively. The early fusion approach merges data at the initial stages of processing, while late fusion combines model outputs toward the end. This research conducts thorough experiments using real-world data from wind turbines to validate the approach.

The results demonstrate a significant improvement in fault prediction accuracy, with early fusion strategies outperforming traditional methods by 2.6% to 16.9%. Late fusion strategies, while more stable, underscore the benefit of integrating diverse data types for predictive maintenance. The study provides empirical evidence of the superiority of the fusion-based methodology over singular data source approaches.

This research is distinguished by its novel fusion-based approach to predictive maintenance, marking a departure from conventional single-source data analysis methods. By incorporating both time-series sensor data and textual event logs, the study unveils a comprehensive and effective strategy for fault prediction, paving the way for future advancements in the field.

The construction industry remains one of the most hazardous industries worldwide, with a higher number of fatalities and injuries each year. The safety and well-being of workers at a job site are paramount as they face both immediate and long-term risks such as falls and musculoskeletal disorders. To mitigate these dangers, sensor-based technologies have emerged as a crucial tool to promote the safety and well-being of workers on site. The implementation of real-time sensor data-driven monitoring tools can greatly benefit the construction industry by enabling the early identification and prevention of potential construction accidents. This study aims to explore the innovative method of prototype development regarding a safety monitoring system in the form of smart personal protective equipment (PPE) by taking advantage of the recent advances in wearable technology and cloud computing.

The proposed smart construction safety system has been meticulously crafted to seamlessly integrate with conventional safety gear, such as gloves and vests, to continuously monitor construction sites for potential hazards. This state-of-the-art system is primarily geared towards mitigating musculoskeletal disorders and preventing workers from inadvertently entering high-risk zones where falls or exposure to extreme temperatures could occur. The wearables were introduced through the proposed system in a non-intrusive manner where the safety vest and gloves were chosen as the base for the PPE as almost every construction worker would be required to wear them on site. Sensors were integrated into the PPE, and a smartphone application which is called SOTER was developed to view and interact with collected data. This study discusses the method and process of smart PPE system design and development process in software and hardware aspects.

This research study posits a smart system for PPE that utilises real-time sensor data collection to improve worksite safety and promote worker well-being. The study outlines the development process of a prototype that records crucial real-time data such as worker location, altitude, temperature and hand pressure while handling various construction objects. The collected data are automatically uploaded to a cloud service, allowing supervisors to monitor it through a user-friendly smartphone application. The worker tracking ability with the smart PPE can help to alleviate the identified issues by functioning as an active warning system to the construction safety management team. It is steadily evident that the proposed smart PPE system can be utilised by the respective industry practitioners to ensure the workers' safety and well-being at construction sites through monitoring of the workers with real-time sensor data.

The proposed smart PPE system assists in reducing the safety risks posed by hazardous environments as well as preventing a certain degree of musculoskeletal problems for workers. Ultimately, the current study unveils that the construction industry can utilise cloud computing services in conjunction with smart PPE to take advantage of the recent advances in novel technological avenues and bring construction safety management to a new level. The study significantly contributes to the prevailing knowledge of construction safety management in terms of applying sensor-based technologies in upskilling construction workers' safety in terms of real-time safety monitoring and safety knowledge sharing.

The purpose of this paper is to discuss an online sensor-based support system which the authors believe can be useful in such scenarios. Persons with a cognitive impairment, such as those with Alzheimer’s disease, suffer from deficiencies in cognitive skills which reduce their independence; such patients can benefit from the provision of further assistance such as reminders for carrying out instrumental activities of daily living (IADLs).

The system proposed processes data from a network of sensors that have the capability of sensing user interactions and on-going IADLs in the living environment itself. A probabilistic learning model is built that computes joint probability distributions over different activities representing users’ behavioural patterns in performing activities. This probability model can underpin an intervention framework that prompts the user with the next step in the IADL when inactivity is being observed. This prompt for the next step is inferred from the conditional probability taken into consideration the IADL steps that have already been completed, in addition to contextual information relating to the time of day and the amount of time already spent on the activity. The originality of the work lies in combining partially observed sensor sequences and duration data associated with the IADLs. The prediction of the next step is then adjusted as further steps are completed and more time is spent towards the completion of the activity, thus updating the confidence that the prediction is correct. A reminder is only issued when there has been sufficient inactivity on the part of the patient and the confidence is high that the prediction is correct.

The results of this study verify that by including duration information the prediction accuracy of the model is increased and the confidence level for the next step in the IADL is also increased. As such, there is approximately a 10 per cent rise in the prediction performance in the case of single sensor activation in comparison to an alternative approach which did not consider activity durations.

Duration information to a certain extent has been widely ignored by activity recognition researchers and has received a very limited application within smart environments.

This study concludes that incorporating progressive duration information into partially observed sensor sequences of IADLs has the potential to increase performance of a reminder system for patients with a cognitive impairment, such as Alzheimer’s disease.