In the livestock domain, technologies are developed to sustainably raise animal production. However, the domain is critical, since animals are very sensitive to variables such as temperature and ...humidity, which can cause diseases and consequent production losses and discomfort. Livestock production systems then demand monitoring, reasoning, and acting on the environment so that the levels of those variables are preserved in pre-established intervals and undesired conditions are predicted, avoided, and mitigated with automated actions.
The main contribution of this article is presenting E-SECO, a software ecosystem platform, and its evolution that encapsulates a new self-adaptive component to tackle animal production decisions, named e-Livestock architecture.
Two case studies were conducted involving a real system derived from the E-SECO platform encompassing a Compost Barn production system, i.e., the environment and surrounding technology where bovine milk production takes place.
Results showed the effectiveness of E-SECO to (i) abstract disruptive technologies based on the Internet of Things (IoT) and Artificial Intelligence and accommodate them in a single architecture for that specific domain, (ii) support reuse and derivation of a self-adaptive architecture to support engineering a complex system for a livestock sub-domain (milk production), and (iii) support empirical studies in a real smart farm towards a future transfer of technology to industry.
The results showed that the E-SECO platform, which encompasses e-livestock architecture, can support monitoring, reasoning, prediction, and automated actions in a milk production/Compost Barn environment.
•Agribusiness Production Systems (APS) demand software-intensive solutions.•A Software Ecosystem architecture can abstract and accommodate the solutions.•The solutions include IoT, self-adaptation and artificial intelligence.•APS with those solutions can be derived from the software ecosystem architecture.•The APS can then monitor, reason and perform automated actions.
Prognostic and health management (PHM) effectively reduces the economic loss of sensor-equipped machine downtime caused by under-maintenance and the waste of resources resulted from over-maintenance. ...The remaining useful life (RUL) prediction is the most critical step in PHM. However, accurate RUL prediction in a multiple sensors data environment faces challenges and difficulties. In this paper, we firstly consider the change point where the sensor-equipped machine drifts from a health state (initial stage) to the degradation stage, and combine the deep learning model with the change point to construct the health indicator (HI). Then, a long short-term memory model combined with an attention mechanism (LSTM_Att) is used to iteratively predict the future HI. Additionally, the predicted RUL distribution of the studied sensor-equipped machine is estimated using the similarity method based on the HI data of historical multiple sensor-equipped machines. Then, the confidence interval of RUL is obtained. Finally, the proposed method is verified on the publicly available turbofan engine degradation data set. The experimental results show that the proposed method outperforms the state-of-art benchmark methods.
•A deep learning model with change point recognition is used to construct a health indicator.•A method is proposed to predict the future health indicator.•The sensor-equipped machine’s RUL distribution and confidence interval are estimated.
•We explore driver behaviour through driving analytics collected by smartphone sensors.•Data processing by Machine Learning algorithms yields exposure and behaviour metrics.•We develop mixed logistic ...regression models for the use of mobile phone while driving.•Mobile phone use is associated with longer trips, lower speeds, smoother driving.•The model can correctly ‘detect’ mobile phone use while driving by ∼70%.
The aim of this paper is to explore driving behaviour during mobile phone use on the basis of detailed driving analytics collected by smartphone sensors. The data came from a sample of one hundred drivers (18,850 trips) during a naturalistic driving experiment over four months. A specially developed smartphone application was used, through which driving exposure and behaviour metrics are captured by the smartphone sensors and transmitted to a back-end platform. The data are processed by Machine Learning algorithms yielding exposure (e.g. distance travelled per road type and time of day) and behaviour indicators (e.g. speeding, speed and acceleration variations, harsh braking, harsh manoeuvring, use of mobile phone etc.). Mixed binary logistic regression models were developed to investigate whether mobile phone use during a trip is correlated with other driving metrics, and can be accurately “detected” based on them. A model for all trips was developed, as well as models for trips on different road types (urban, rural, highway). Exposure metrics found to be significantly associated with the probability of mobile phone use are trip length, and driving off-morning rush. Exceeding the speed limits and the number of harsh events (particularly harsh cornering), are all negatively associated with the probability of mobile phone use. A general pattern of less speeding and smoother driving appears indicative of mobile phone use, in line with known assumptions of driver compensatory behaviour. The results suggest that mobile phone use while driving may be accurately predicted by the model in more than 70% of cases.
In this paper the authors investigate the problems of predicting the fuel consumption and of providing the best value for the trim of a vessel in real operations based on data measured by the onboard ...automation systems. Three different approaches for the prediction of the fuel consumption are compared: White, Black and Gray Box Models. White Box Models (WBM) are based on the knowledge of the physical underling processes. Black Box Models (BBMs) build upon statistical inference procedures based on the historical data collection. Finally, the authors propose two different Gray Box Model (GBM) which are able to exploit both mechanistic knowledge of the underlying physical principles and available measurements. Based on these predictive models of the fuel consumption a new strategy for the optimisation of the trim of a vessel is proposed. Results on real world operational data show that the BBM is able to remarkably improve a state-of-the-art WBM, while the GBM is able to encapsulate the a-priory knowledge of the WBM into the BBM so to achieve the same performance of the latter but requiring less historical data. Moreover, results show that the GBM can be used as an effective tool for optimising the trim of a vessel in real operational conditions.
•Three different approaches for the prediction of the fuel consumption are compared.•Real data analysis of operational data for a Handymax chemical/product tanker.•A new strategy for the optimisation of the trim of a vessel is proposed.•Proposal improves a state-of-the-art tools performances.
Energy-efficient buildings have gained increasing interest in the last decades as they provide optimal energy management. With the emergence of smart homes, many smart tools have been developed to ...optimize energy efficiency such as activities recognition (AR) and occupancy estimation (OE). The creation of these smart building tools may be disrupted by the scarcity of labeled data. Indeed, data labeling is a tedious and time-consuming task and, it can be very expensive for building objectives. However, labeled data scarcity can be solved by sharing knowledge from different domains using unsupervised domain adaptation techniques. Also, privacy issues can emerge and prevent the use of certain types of data that share residents’ attitudes. However, data privacy can be preserved by considering approaches that do not have direct access to original data. In this research, we provide a comparative analysis between unsupervised domain adaptation (UDA) methods, applied to the tasks of AR and OE, with and without direct access to source domain data. We have 6 adapted approaches for UDA with access to labeled source data: domain separation networks (DSN), cluster alignment with a teacher (CAT), CAT+ gradient reversal (RevGrad), CAT + robust RevGrad (rRevGrad), Auxiliary Target Domain-Oriented Classifier (ATDOC) with nearest centroid classifier (NC), and ATDOC with neighborhood aggregation (NA). Also, we have 6 adapted methods for UDA without labeled source data: confidence score weighting adaptation using joint model data structure (CoWA-JMDS), CoWA-JMDS without weights mixup, divide and contrast (DaC), attracting and dispersing (AaD), source hypothesis transfer with information maximization (SHOT-IM), and source hypothesis transfer with self-supervised pseudo-labeling (SHOT-Pseudo-labeling). All the considered methods have been tested on AR and OE datasets collected using ambient sensors. The comparative analysis made in this work has shown us impressive findings and has given great ideas about the type of approaches (with access or without access to the source data) that we should consider for real-world smart building applications.
•A comparative analysis between unsupervised domain adaptation methods is performed.•Using sensor data, five activities and three levels of occupancy have been predicted.•Unsupervised domain adaptation without access to source data solves privacy issues.•Poor performance caused by unbalanced label proportions has been considered.•UDA solves the problem of labeled data scarcity with accuracy up to 89%.
Head acceleration measurement sensors are now widely deployed in the field to monitor head kinematic exposure in contact sports. The wealth of impact kinematics data provides valuable, yet ...challenging, opportunities to study the biomechanical basis of mild traumatic brain injury (mTBI) and subconcussive kinematic exposure. Head impact kinematics are translated into brain mechanical responses through physics-based computational simulations using validated brain models to study the mechanisms of injury. First, this article reviews representative legacy and contemporary brain biomechanical models primarily used for blunt impact simulation. Then, it summarizes perspectives regarding the development and validation of these models, and discusses how simulation results can be interpreted to facilitate injury risk assessment and head acceleration exposure monitoring in the context of contact sports. Recommendations and consensus statements are presented on the use of validated brain models in conjunction with kinematic sensor data to understand the biomechanics of mTBI and subconcussion. Mainly, there is general consensus that validated brain models have strong potential to improve injury prediction and interpretation of subconcussive kinematic exposure over global head kinematics alone. Nevertheless, a major roadblock to this capability is the lack of sufficient data encompassing different sports, sex, age and other factors. The authors recommend further integration of sensor data and simulations with modern data science techniques to generate large datasets of exposures and predicted brain responses along with associated clinical findings. These efforts are anticipated to help better understand the biomechanical basis of mTBI and improve the effectiveness in monitoring kinematic exposure in contact sports for risk and injury mitigation purposes.
Anomaly prediction is an important aspect of predictive maintenance for port machinery and equipment. Traditional anomaly prediction techniques process the raw time- or frequency-domain data, which ...makes time-series data difficult to reconstruct. In particular, time-series data with weak features, such as sensor data, are difficult to model. Furthermore, the absence of sufficient fault-labeled data for industrial processes means that classification models are difficult to train. Therefore, this study introduces an advanced temporal anomaly prediction model, which uses a gated recurrent unit (GRU) autoencoder to process time- and frequency-domain data in parallel. The feature match and temporal consistency of the data are modeled using a bidomain competitive attention module and bidirectional loss function, respectively, which reduces the mean squared error (MSE) by 15.43%. Weak fault features in the sensor data are enhanced using dynamics simulations, which address the problem of missing fault labels by using a threshold diagnostic model instead of supervised learning. Thus, the recall rate is increased by 9.04%. An attention storage pool approach is also used to mitigate the prediction decay caused by external variables. Overall, the proposed method can improve the efficiency and safety of industrial machinery by addressing the challenges involved in modeling time-series sensor data with weak features.
The robotic manipulators are highly complex coupling dynamic systems, which require a mathematical model for planning and controlling the robotic motions. It is imperative to calculate the kinematic ...parameters such as rotational matrix, joint angles, angular velocity, and angular acceleration, which determines the control performance of the models. For this purpose, a multiple-sensor-based Mathematical approach that utilizes inertial measurement unit (IMU) and triple-axis accelerometer is presented in this paper. A combination of one IMU and three triple-axis accelerometers is affixed to each of the two rigid bodies for real-time determination of parameters and the robotic arm orientation. Additionally, the model incorporates an Extended Kalman filter (EKF) fusion technique to combine data from various sensors, mitigate measurement noise, and adapt in real-time to changing environments. To implement this approach, a MATLAB code is developed to read, preprocess sensors data, and simulation of the proposed model. All the results are presented graphically and indicate that the motion parameters and pose measurements are calculated accurately and effectively.
Road safety is an important topic of interest around the world. The road traffic accidents claim more than 1.2 million lives and cause as many as 50 million injuries each year without forgetting ...their huge impact on health and development. Several factors may result in the high number of accidents among which we can state the driving behavior. This paper focused on the study of drivers' behavior and aimed to help reduce the number of accidents and consequently improve road safety. To this end, the driving behavior was classified into three categories (normal, drowsy and aggressive) based on smartphone sensors data. A new stacked Long Short-Term Memory (stacked LSTM) Recurrent Neural Networks architecture was proposed for the driving behaviors classification. The accuracy of the obtained drivers' states results was improved with the use of the Dempster-Shafer (DS) theory of belief functions that overcame the uncertainty of data. The obtained results are clearly better than those existing in other driving behavior classification studies since the obtained F1-measure score achieves 97%.
This study introduces the idea of using vehicles as weather sensors to identify real-time weather on freeways in the same context as Road Weather Information System (RWIS) but in a continuous, ...trajectory-level, and for road segments allocated in the vehicles paths. The study developed a novel approach to detect snowy and clear weather conditions by utilizing real-time data collected from vehicles' external sensors and CANbus. The proposed approach used time series datasets from the SHRP2 Naturalistic Driving Study (NDS), collected during normal driving conditions on freeways. Trips occurring in snowy weather alongside matched trips in clear weather were segmented into time- and distance-based segments such as a one-minute, one-mile, and half a mile. Three assemblies of the input data are considered in the modeling step: data collected from external sensors, CANbus data, and these two data combined. Data analysis was implemented using the Deep Learning Artificial Neural Network, Decision Tree, Random Forest, and Gradient Boosted Trees models. The results indicate that using different segmentation levels provides decent results in detecting snowy weather. The accuracy in estimating the real-time snowy weather was in ranges of 80% to 85%, 71% to 79%, and 73% to 83% for the one-minute, one-mile, and half mile segmentation types, respectively. The GBT model performed the best among all models based on the area under the Receiver Operating Characteristics (ROC) curve, the highest cumulative percentage in estimating the snowy weather using the lower portion of the population, and the highest overall accuracy. Results indicated that an accuracy of 83% in estimating snowy weather conditions could be accomplished using the data collected from external sensors only without accessing CANbus data.
•This study developed a novel approach to detect snowy and clear weather conditions by utilizing real-time data collected from vehicles' external sensors and CANbus.•It aims to illustrate the importance of employing vehicles as weather sensors in Connected and Autonomous Vehicle applications to improve traffic safety on freeways.•The results of this study indicate that using different segmentation levels provides decent results in detecting snowy weather.•Study results proved that using sensors to collect data would provide similar results to these results derived from using CANbus data and sensors data.•The study findings suggest that valuable results can still be attained using external vehicle-based sensors.
