Embedded Sensor Data Research Articles

Sensors capabilities as a creativity tool for engineering product design

Smart and connected physical products enable numerous novel value creations based on embedded sensor data. However, during the product design process, it appears that these value-creation opportunities are not sufficiently explored. To address this gap, a general and accessible ideation tool is proposed to structure a systematic exploration. The tool has been developed from the data sheets of a large number of various embedded sensors. A non-exhaustive list of 14 main sensor capabilities was thus structured to form the core of the tool. During the creative phases of product design, these capabilities are combined with a convenient set of inputs to support the generation of value-creation concepts. A focus group to evaluate the tool was carried out with a medium-sized manufacturer of connected shared city bikes. Expert product designers generated concepts with and without the tool. The results of the experiment suggest that the tool enables the generation of concepts that are more novel and of better quality in comparison to traditional ideation approaches. In addition, participants reported a high level of appreciation for the tool. They also noted a high level of creative exploration and collaboration facilitated by the tool.

TS2ACT

Human Activity Recognition (HAR) based on embedded sensor data has become a popular research topic in ubiquitous computing, which has a wide range of practical applications in various fields such as human-computer interaction, healthcare, and motion tracking. Due to the difficulties of annotating sensing data, unsupervised and semi-supervised HAR methods are extensively studied, but their performance gap to the fully-supervised methods is notable. In this paper, we proposed a novel cross-modal co-learning approach called TS2ACT to achieve few-shot HAR. It introduces a cross-modal dataset augmentation method that uses the semantic-rich label text to search for human activity images to form an augmented dataset consisting of partially-labeled time series and fully-labeled images. Then it adopts a pre-trained CLIP image encoder to jointly train with a time series encoder using contrastive learning, where the time series and images are brought closer in feature space if they belong to the same activity class. For inference, the feature extracted from the input time series is compared with the embedding of a pre-trained CLIP text encoder using prompt learning, and the best match is output as the HAR classification results. We conducted extensive experiments on four public datasets to evaluate the performance of the proposed method. The numerical results show that TS2ACT significantly outperforms the state-of-the-art HAR methods, and it achieves performance close to or better than the fully supervised methods even using as few as 1% labeled data for model training. The source codes of TS2ACT are publicly available on GitHub1.

An Auto-Encoder Based TinyML Approach for Real-Time Anomaly Detection

<div class="section abstract"><div class="htmlview paragraph">Condition monitoring plays a crucial role in the automotive space because they reduce the downtime and maintenance costs by preventing sudden catastrophic breakdown of vehicles. Condition monitoring solutions primarily monitor onboard sensor data to detect anomalies. However, with vehicles becoming more complex each day, the number of sensors to be monitored is also growing. This increases the data volume to be processed to make decisions. It is not feasible to send all the embedded sensor data captured to the cloud for processing. The network bandwidth, latency for transferring the data and finally the cost associated with data transfer are the factors which impede us from taking this approach. Much of the previous work done to address these issues has proposed Deep Learning driven onboard anomaly detection approaches. The deployment of these implementations requires power hungry and costly hardware with high computational resources. The recent advances in the field of Tiny Machine Learning have made it possible to design and deploy Deep Neural Networks on resource constrained low-cost embedded hardware. In this paper, we propose an Auto-Encoder based approach for anomaly detection in time-series vibration sensor data. The designed Auto-Encoder model has a 7.5 KB footprint and was finally deployed on a highly resource constrained ARM Cortex-M4 microcontroller with 256KB of SRAM and 1MB Flash. The model has been validated on the previous machine data. It has achieved an accuracy and precision close to 80%. Currently, by using post training quantization we are trading-off model accuracy for a reduction in model size. In future, we plan to use Quantization Aware Training which will help us in achieving even higher model accuracy.</div></div>

Severe slugging flow identification from topological indicators

In this work, topological data analysis is used to identify the onset of severe slug flow in offshore petroleum production systems. Severe slugging is a multiphase flow regime known to be very inefficient and potentially harmful to process equipment and it is characterized by large oscillations in the production fluid pressure. Time series from pressure sensors in subsea oil wells are processed by means of Takens embedding to produce point clouds of data. Embedded sensor data is then analyzed using persistent homology to obtain topological indicators capable of revealing the occurrence of severe slugging in a condition-based monitoring approach. A large dataset of well events consisting of both real and simulated data is used to demonstrate the possibilty of authomatizing severe slugging detection from live data via topological data analysis. Methods based on persistence diagrams are shown to accurately identify severe slugging and to classify different flow regimes from pressure signals of producing wells with supervised machine learning.

Human Activity Recognition Based on Embedded Sensor Data Fusion for the Internet of Healthcare Things.

Nowadays, the emerging information technologies in smart handheld devices are motivating the research community to make use of embedded sensors in such devices for healthcare purposes. In particular, inertial measurement sensors such as accelerometers and gyroscopes embedded in smartphones and smartwatches can provide sensory data fusion for human activities and gestures. Thus, the concepts of the Internet of Healthcare Things (IoHT) paradigm can be applied to handle such sensory data and maximize the benefits of collecting and analyzing them. The application areas contain but are not restricted to the rehabilitation of elderly people, fall detection, smoking control, sportive exercises, and monitoring of daily life activities. In this work, a public dataset collected using two smartphones (in pocket and wrist positions) is considered for IoHT applications. Three-dimensional inertia signals of thirteen timestamped human activities such as Walking, Walking Upstairs, Walking Downstairs, Writing, Smoking, and others are registered. Here, an efficient human activity recognition (HAR) model is presented based on efficient handcrafted features and Random Forest as a classifier. Simulation results ensure the superiority of the applied model over others introduced in the literature for the same dataset. Moreover, different approaches to evaluating such models are considered, as well as implementation issues. The accuracy of the current model reaches 98.7% on average. The current model performance is also verified using the WISDM v1 dataset.

IoTwins: Toward Implementation of Distributed Digital Twins in Industry 4.0 Settings

While the digital twins paradigm has attracted the interest of several research communities over the past twenty years, it has also gained ground recently in industrial environments, where mature technologies such as cloud, edge and IoT promise to enable the cost-effective implementation of digital twins. In the industrial manufacturing field, a digital model refers to a virtual representation of a physical product or process that integrates data taken from various sources, such as application program interface (API) data, historical data, embedded sensor data and open data, and that is capable of providing manufacturers with unprecedented insights into the product’s expected performance or the defects that may cause malfunctions. The EU-funded IoTwins project aims to build a solid platform that manufacturers can access to develop hybrid digital twins (DTs) of their assets, deploy them as close to the data origin as possible (on IoT gateway or on edge nodes) and take advantage of cloud-based resources to off-load intensive computational tasks such as, e.g., big data analytics and machine learning (ML) model training. In this paper, we present the main research goals of the IoTwins project and discuss its reference architecture, platform functionalities and building components. Finally, we discuss an industry-related use case that showcases how manufacturers can leverage the potential of the IoTwins platform to develop and execute distributed DTs for the the predictive-maintenance purpose.

Comparison of Embedded Sensor Data for Long-Term Care Residents Before and After Onset of the COVID-19 Pandemic

Older adults have experienced greater isolation and mental health concerns during the COVID-19 pandemic. In long-term care (LTC) settings, residents have been particularly impacted due to strict lockdown policies. Little is known about how these policies have impacted older adults. This study leveraged existing research with embedded sensors installed in LTC settings, and analyzed sensor data of residents (N=30) two months pre/post the onset of the U.S. COVID-19 pandemic (1/13/20 to 3/13/20, 03/14/20 to 5/13/20). Data from three sensors (bed sensors, depth sensors, and motion sensors) were analyzed for each resident using paired t-tests, which generated information on the resident’s pulse, respiration, sleep, gait, and motion in entering/exiting their front door, living rooms, bedrooms, and bathrooms. A 14.4% decrease was observed in front door motion in the two months post-onset of the pandemic, as well as a 2.4% increase in average nighttime respiration, and a 7.6% increase in nighttime bed restlessness. Over half of our sample (68%) had significant differences (p<0.05) in restlessness. These results highlight the potential impact of the COVID-19 pandemic and social distancing policies on older adults living in LTC. While it is not surprising that significant differences were found in the front door motion sensor, the bed sensor data can potentially shed light on how sleep was impacted during this time. As older adults experienced additional mental health concerns during this time, their normal sleep patterns could have been affected. Implications could help inform LTC staff, healthcare providers, and self-management of health approaches among older adults.

Smartphone-Based Passive Sensing for Behavioral and Physical Monitoring in Free-Life Conditions: Technical Usability Study.

Smartphone use is widely spreading in society. Their embedded functions and sensors may play an important role in therapy monitoring and planning. However, the use of smartphones for intrapersonal behavioral and physical monitoring is not yet fully supported by adequate studies addressing technical reliability and acceptance. The objective of this paper is to identify and discuss technical issues that may impact on the wide use of smartphones as clinical monitoring tools. The focus is on the quality of the data and transparency of the acquisition process. QuantifyMyPerson is a platform for continuous monitoring of smartphone use and embedded sensors data. The platform consists of an app for data acquisition, a backend cloud server for data storage and processing, and a web-based dashboard for data management and visualization. The data processing aims to extract meaningful features for the description of daily life such as phone status, calls, app use, GPS, and accelerometer data. A total of health subjects installed the app on their smartphones, running it for 7 months. The acquired data were analyzed to assess impact on smartphone performance (ie, battery consumption and anomalies in functioning) and data integrity. Relevance of the selected features in describing changes in daily life was assessed through the computation of a k-nearest neighbors global anomaly score to detect days that differ from others. The effectiveness of smartphone-based monitoring depends on the acceptability and interoperability of the system as user retention and data integrity are key aspects. Acceptability was confirmed by the full transparency of the app and the absence of any conflicts with daily smartphone use. The only perceived issue was the battery consumption even though the trend of battery drain with and without the app running was comparable. Regarding interoperability, the app was successfully installed and run on several Android brands. The study shows that some smartphone manufacturers implement power-saving policies not allowing continuous sensor data acquisition and impacting integrity. Data integrity was 96% on smartphones whose power-saving policies do not impact the embedded sensor management and 84% overall. The main technological barriers to continuous behavioral and physical monitoring (ie, battery consumption and power-saving policies of manufacturers) may be overcome. Battery consumption increase is mainly due to GPS triangulation and may be limited, while data missing because of power-saving policies are related only to periods of nonuse of the phone since the embedded sensors are reactivated by any smartphone event. Overall, smartphone-based passive sensing is fully feasible and scalable despite the Android market fragmentation.

MyDigitalFootprint: An extensive context dataset for pervasive computing applications at the edge

The widespread diffusion of connected smart devices has greatly contributed to the rapid expansion and evolution of the Internet at its edge, where personal mobile devices follow the behavior of their human users and interact with other smart objects located in the surroundings. In such a scenario, the user context is represented by a large variety of information that can rapidly change, and the ability of personal mobile devices to locally process this data is fundamental to make the system able to quickly adapt its behavior to the current situation. This ability, in practice, can be represented by a single elaboration process integrated in the final user application, or by a middleware platform aimed at implementing different context processing and reasoning to support third-party applications. However, the lack of public datasets that take into account the complexity of the user context in the mobile environment strongly limits the advance of the research in this field.In this paper, we present MyDigitalFootprint, a novel large-scale dataset composed of smartphone embedded sensors data, physical proximity information, and Online Social Networks interactions aimed at supporting multimodal context-recognition and social relationships modeling. The dataset includes two months of measurements and information collected from the personal mobile devices of 31 volunteer users, in their natural environment, without limiting their usual behavior. Existing public datasets generally consist of a limited set of context data, aimed at optimizing specific application domains (human activity recognition is the most common example). On the contrary, our dataset contains a comprehensive set of information describing the user context in the mobile environment. In order to demonstrate the efficacy of the proposed dataset, we present three context-aware applications based on different machine learning tasks: (i) a social link prediction algorithm based on physical proximity data, (ii) the recognition of daily-life activities based on smartphone-embedded sensors data, and (iii) a pervasive context-aware recommender system. To the best of our knowledge, this is the first large-scale dataset containing such heterogeneity of information, representing an invaluable source of data to validate new research in mobile and edge computing.

Global Sensitivity Analysis for Modeling the Free-Flight Behavior of an Artillery Projectile

A vehicle’s in-flight behavior can be represented by the Newton–Euler equations of motion: usually, such a model has a nonlinear and continuous description based on ordinary differential equations. The model structure can be altered using analytic transformations (such as transformation into a quasi-LPV structure) and, when the model is supposed to reflect an existing physical system, some of its parameters might be uncertain. This paper’s objective is twofold: first, to investigate if a quasi-LPV model does accurately replicate the physical behavior of a large-caliber spin-stabilized projectile in free flight; second, to verify if the available embedded sensors data could be used to determine nonidentifiability of uncertain model parameters. To investigate these prospects, a permutation-based global sensitivity analysis is employed. The proposed study has highlighted the nonidentifiable parameters of the model, during either the whole flight or some periods of it. These results can help to enhance the preparation of free-flight experiments at the open-range test site of the French-German Research Institute of Saint Louis.

Towards Real-Time Multi-Sensor Golf Swing Classification Using Deep CNNs

In recent years, smart sports equipment and body sensor systems have become popular in professional and amateur sports. One of a few remaining problems in real-time applications is the discovery of knowledge from the embedded sensors data. In sports training, such knowledge helps accelerated motor learning. The authors start with exploring the possibilities of the classification of golf swing performance with the 1-D convolutional neural network (CNN) in real-time. They thoroughly investigate multiple golf swing data classifiers based on CNNs fed with multi-sensor signals. The authors test the possibilities of real-time performance of CNN methods on the multi-length sequences. In addition, they thoroughly evaluate the performance of their well-trained CNN-based classifier on the aforementioned test set in terms of common indicators. Experiments and corresponding results show that the authors' models can satisfy the real-time requirement of the accuracy of the classification and outperform support vector machine (SVM).

Multi-Lane Pothole Detection from Crowdsourced Undersampled Vehicle Sensor Data

As smart vehicles have become more ubiquitous, the capability now exists to detect environmental road features (e.g., potholes, road incline angle, etc.) from their embedded sensor data. By aggregating data from multiple vehicles, crowdsourcing can be leveraged to detect environmental information with improved accuracy. We focus on using such data to detect and localize potholes on multi-lane roads. Extracting information from aggregated vehicle data is challenging due to undersampling sensors, sensor mobility, asynchronous sensor operation, sensor noise, vehicle and road heterogeneity, and GPS position error. GPS position error is particularly problematic in multi-lane environments since the position error is generally larger than standard lane widths. In this paper, we investigate these issues and develop a crowdsourced system to detect and localize potholes in multi-lane environments using accelerometer data from embedded vehicle sensors. Our crowdsourced system reduces the required network bandwidth by determining road incline and bank angle information in each vehicle to filter acceleration components that do not correspond to pothole conditions. We evaluate our system on simulated and real-world data, analyze tradeoffs in the number of vehicles and the amount of bandwidth required for accurate detection, and compare the results to the simpler single lane detection scenario.

Language-Based Process Phase Detection in the Trauma Resuscitation.

Process phase detection has been widely used in surgical process modeling (SPM) to track process progression. These studies mostly used video and embedded sensor data, but spoken language also provides rich semantic information directly related to process progression. We present a long-short term memory (LSTM) deep learning model to predict trauma resuscitation phases using verbal communication logs. We first use an LSTM to extract the sentence meaning representations, and then sequentially feed them into another LSTM to extract the meaning of a sentence group within a time window. This information is ultimately used for phase prediction. We used 24 manually-transcribed trauma resuscitation cases to train, and the remaining 6 cases to test our model. We achieved 79.12% accuracy, and showed performance advantages over existing visual-audio systems for critical phases of the process. In addition to language information, we evaluated a multimodal phase prediction structure that also uses audio input. We finally identified the challenges of substituting manual transcription with automatic speech recognition in trauma resuscitation.

Context‐aware Android applications through transportation mode detection techniques

AbstractIn this paper, we study the problem of how to detect the current transportation mode of the user from the smartphone sensors data, because this issue is considered crucial for the deployment of a multitude of mobility‐aware systems, ranging from trace collectors to health monitoring and urban sensing systems. Although some feasibility studies have been performed in the literature, most of the proposed systems rely on the utilization of the GPS and on computational expensive algorithms that do not take into account the limited resources of mobile phones. On the opposite, this paper focuses on the design and implementation of a feasible and efficient detection system that takes into account both the issues of accuracy of classification and of energy consumption. To this purpose, we propose the utilization of embedded sensor data (accelerometer/gyroscope) with a novel meta‐classifier based on a cascading technique, and we show that our combined approach can provide similar performance than a GPS‐based classifier, but introducing also the possibility to control the computational load based on requested confidence. We describe the implementation of the proposed system into an Android framework that can be leveraged by third‐part mobile applications to access context‐aware information in a transparent way. Copyright © 2016 John Wiley &amp; Sons, Ltd.

Enhanced registered nurse care coordination with sensor technology: Impact on length of stay and cost in aging in place housing

BackgroundWhen planning the Aging in Place Initiative at TigerPlace, it was envisioned that advances in technology research had the potential to enable early intervention in health changes that could assist in proactive management of health for older adults and potentially reduce costs. PurposeThe purpose of this study was to compare length of stay (LOS) of residents living with environmentally embedded sensor systems since the development and implementation of automated health alerts at TigerPlace to LOS of those who are not living with sensor systems. Estimate potential savings of living with sensor systems. MethodsLOS for residents living with and without sensors was measured over a span of 4.8 years since the implementation of sensor-generated health alerts. The group living with sensors (n = 52) had an average LOS of 1,557 days (4.3 years); the comparison group without sensors (n = 81) was 936 days (2.6 years); p = .0006. Groups were comparable based on admission age, gender, number of chronic illnesses, SF12 physical health, SF12 mental health, Geriatric Depression Scale (GDS), activities of daily living, independent activities of daily living, and mini-mental status examination scores. Both groups, all residents living at TigerPlace since the implementation of health alerts, receive registered nurse (RN) care coordination as the standard of care. DiscussionResults indicate that residents living with sensors were able to reside at TigerPlace 1.7 years longer than residents living without sensors, suggesting that proactive use of health alerts facilitates successful aging in place. Health alerts, generated by automated algorithms interpreting environmentally embedded sensor data, may enable care coordinators to assess and intervene on health status changes earlier than is possible in the absence of sensor-generated alerts. Comparison of LOS without sensors TigerPlace (2.6 years) with the national median in residential senior housing (1.8 years) may be attributable to the RN care coordination model at TigerPlace. Cost estimates comparing cost of living at TigerPlace with the sensor technology vs. nursing home reveal potential saving of about $30,000 per person. Potential cost savings to Medicaid funded nursing home (assuming the technology and care coordination were reimbursed) are estimated to be about $87,000 per person. ConclusionsEarly alerts for potential health problems appear to enhance the current RN care coordination care delivery model at TigerPlace, increasing LOS for those living with sensors to nearly twice that of those who did not. Sensor technology with care coordination has cost saving potential for consumers and Medicaid.

Damage detection with streamlined structural health monitoring data.

The huge amounts of sensor data generated by large scale sensor networks in on-line structural health monitoring (SHM) systems often overwhelms the systems’ capacity for data transmission and analysis. This paper presents a new concept for an integrated SHM system in which a streamlined data flow is used as a unifying thread to integrate the individual components of on-line SHM systems. Such an integrated SHM system has a few desirable functionalities including embedded sensor data compression, interactive sensor data retrieval, and structural knowledge discovery, which aim to enhance the reliability, efficiency, and robustness of on-line SHM systems. Adoption of this new concept will enable the design of an on-line SHM system with more uniform data generation and data handling capacity for its subsystems. To examine this concept in the context of vibration-based SHM systems, real sensor data from an on-line SHM system comprising a scaled steel bridge structure and an on-line data acquisition system with remote data access was used in this study. Vibration test results clearly demonstrated the prominent performance characteristics of the proposed integrated SHM system including rapid data access, interactive data retrieval and knowledge discovery of structural conditions on a global level.

Automated Health Alerts Using In-Home Sensor Data for Embedded Health Assessment.

We present an example of unobtrusive, continuous monitoring in the home for the purpose of assessing early health changes. Sensors embedded in the environment capture behavior and activity patterns. Changes in patterns are detected as potential signs of changing health. We first present results of a preliminary study investigating 22 features extracted from in-home sensor data. A 1-D alert algorithm was then implemented to generate health alerts to clinicians in a senior housing facility. Clinicians analyze each alert and provide a rating on the clinical relevance. These ratings are then used as ground truth for training and testing classifiers. Here, we present the methodology for four classification approaches that fuse multisensor data. Results are shown using embedded sensor data and health alert ratings collected on 21 seniors over nine months. The best results show similar performance for two techniques, where one approach uses only domain knowledge and the second uses supervised learning for training. Finally, we propose a health change detection model based on these results and clinical expertise. The system of in-home sensors and algorithms for automated health alerts provides a method for detecting health problems very early so that early treatment is possible. This method of passive in-home sensing alleviates compliance issues.

모니터링과 제어를 위한 사출성형 파라미터 인터페이스에 관한 연구

Recently, monitoring systems, such as POP, take a core role in scheduling or planning of manufacturing facilities for production, maintenance, and so on. Such monitoring systems require functionalities for real-time parameter monitoring and controlling to maximize efficiency of facilities. However, vendors usually do not provide internal communication protocols or interface to access the machine controller. Therefore, the values of parameters related to machine operations and controls cannot be easily accessed from external devices. In this paper, we propose an interface methodology for a real-time monitoring and controlling of injection molding machine parameters such as user input parameters, embedded sensor data and injection molding status information.

Enhancing vibration analysis by embedded sensor data validation technologies

The ability to predict and understand the responses of an airframe with simultaneous external influences acting on its elements is a challenging effort. Moreover, although considerable research has been devoted to monitoring structures within the aerospace industry (commercial, military, and space), successful field implementations have not been widely achieved. Breakthroughs for in-flight measurement techniques and processing tools are thus required for enhancing flight research and to ultimately boost operations, increase safety, and reduce costs. This article presents an embedded approach based on a high performance vibration-based diagnostic framework using validated data from low power miniature smart sensors. The architecture is divided into two levels, with the low level built on smart sensors capable of self-diagnostics, robust data acquisition, and vibration analysis, and the high level comprising a computation system with a graphical user interface, feature extraction toolset, and artificial neural network diagnostics. The goal is a system consisting of smart sensors and intelligent processing to be deployed in aircraft for the detection and isolation of global and incipient failures.

Editorial

Being a reliability engineer has some interesting side effects. Many reliability engineers (I have heard many similar stories from many colleagues) have developed a sixth sense for all kinds of, often weak, signals relating to a systems reliability. When I am, for example, driving a car, I have the habit of, probably even partly subconsciously, registering all kinds of signals that may relate to the cars reliability. The sound of slipping V-belts is probably an obvious example, but also all other kinds of squeaking sounds, unusual vibrations, or other unusual phenomena immediately ring an alarm bell that something is not working well and that failures could be imminent somewhen in the near future. Although some people may call this paranoia, it is, to my experience, an indication that systems contain many signals indicating a systems condition and that, provided that these signals can be picked up and that adequate models are available, these signals can be used as strong indicators for a systems reliability. And that people with the ability to interpret these (publicly broadcasted) signals may use them. Whereas in the examples given earlier it could be considered a coincidence that signals, indicating a systems condition, could be registered without any further aid outside the system, recent technological developments enable far more sophisticated forms of condition monitoring. With the development of modern sensors, it is now possible to pick up all kinds of signals with little effort. Modern signal processing algorithms allow the real-time combination of a wide range of signals into high-level diagnostics of processes taking place in a system. Modern communication techniques allow the real-time dissemination of this information to all relevant parties independent of their location. This advanced form of condition monitoring enables an entire new type of real-time reliability engineering. Already existing examples of this advanced condition monitoring are in ships where models are detailed enough to determine from a drive shafts vibration that, for example, a new drive shaft should be brought to port X because, of course with a certain likelihood and margin of error, failure before that is unlikely but after that could occur at sea; a situation most fleet owners want to avoid. These new possibilities create, for us as reliability engineers, a very promising and new field, but it raises also many interesting new questions. One important question is: who owns the data? Although quite a few of these modern applications of condition monitoring are understandable or even laudable, the underlying principles raise quite few questions. Given the fact that (combinations of) real-time embedded sensor data can provide detailed information on a systems (changes in) condition, information that has a high intrinsic value for many different parties, it becomes highly relevant to define who owns this data, who has access to this data, and for what purposes this data can be used. Personally, I see that, with the new technological possibilities, condition monitoring will be one of the main drivers for new methods and models in reliability engineering; it will move reliability engineering from being dominated by post-mortem statistics to being strongly influenced by real-time condition analysis. It is, however, crucial that in parallel, legal and ethical frameworks are developed to address the aforementioned issues. In the future, the following interesting scenario could happen. A person is walking in the street, and suddenly, next to him, an ambulance stops and starts unloading cardiopulmonary resuscitation equipment. The person asks: why are you doing this; I do not have a heart attack? Where the paramedic answers: not yet; please step into the car so we can prevent it. It would be certainly interesting to have these detailed models available. This issue is, of course, do end-users want it?