Centre of Expertise Digital Operations & Finance

Research Group Smart Sensor Systems

About the research group

About the professor

dr. John Bolte

John graduated from Utrecht University as an Earthquake Seismologist. In 2003, he earned his PhD from the Delft University of Technology, specialising in Acoustic Imaging. Since 2002, he has been working as a scientific project manager for The Netherlands National Institute for Public Health and the Environment (RIVM). He has written, for example, a national guideline for employee protection from electromagnetic fields. At the RIVM, he earned years of experience in the development and application of wearable measuring tools. John has received numerous research grants from ZonMw and RIVM (> 1.25 million euros). He graduated from the VU University Amsterdam in 2011 with a degree in Environmental Epidemiology and was appointed a lector at The Hague University of Applied Sciences in 2016.

+31 (0) 15 - 260 63 86
Smart sensors enable us to identify the health risks of staff members at an early stage

Research lines

With static, mobile and even portable sensors(wearables) the environmental exposure as well as the biological and health effects can be measured (simultaneously). This makes it possible, for example, to monitor the exposure variations in space and over time and, if necessary, reduce them. Think of feedback systems that automatically divert traffic. In humans and animals, this allows simultaneous measurement of movement and movement behaviour, diet, personal external exposomeand health factors. This also includes the participation of citizens who measure their own exposure to a greater or lesser degree, the so-called Citizen Science, but also test their physical functions (e.g. by using a Fitbit device or smartwatches) and health parameters, the so-called Quantified Self. This makes it possible to determine the strength of any individual exposure/health relationships and to apply this knowledge tosmart and personalised medicine on the basis of prediction models and interventions. Sensors can also be used in plants to simultaneously measure environmental factors and growth factors and apply this knowledge on the basis of prediction models, feedback systems and interventions in smart sustainable and precision farming. 
The awarded RAAK MKB SCOUT Project for greenhouse measurement is along these lines. In the field of wearables there is a link with TNO and Health, Nutrition and Sports Dietetics in addition to wearables for environmental exposure, the development of wearables for measuring objective behaviour, health and biological functions will also be examined. We also have a partnership with Statistics Netherlands and Utrecht University to replace subjective questionnaire measurements with low-cost objective observations methods using sensors. These topics will be further developed in the coming academic year by a TNO employee seconded to us. We will also look at the sensitivity of specific groups of people to certain exposures, for example examining the relationship between electromagnetic fields and health. In collaboration with Medux/Digital Angel, we are also developing the Internet of Medical Things to monitor behaviour, food intake, activities and exposure of the elderly. A further cooperation agreement is underway with the Haaglanden Municipal Health Service in the field of remote CO monitoring in houses above Sisha lounges.

Ensuring Machine Health by means of timely and smart maintenance guarantees not only safety, but also an optimal production capacity. Small sensors and embedded systems provide real-time information about the wearing and lifespan of machines. Prediction models based on this sensor data over a longer time span and across multiple machines can be used to select the optimal maintenance moment. Efficiency is increased by weighing the costs due to malfunctions in the production process against the maintenance costs. Sensors and prediction models also play an important role in inspection systems and early warning systems for workers and the environment. Environmental safety is a prerequisite for carrying out high-risk business activities, e.g. in the chemical and metal industries. Safety is ensured by carrying out preventive maintenance and taking measures to reduce risks to the environment and the worker. In addition to process incidents, occupational safety also covers long-term exposure of workers, for example in the field of biological agents such as microbes and moulds, physical agents such as noise, air quality and radiation, chemical agents such as in the concentration of potentially toxic and explosive substances, and other risks which are not directly detectable. 

In the ongoing 'Measuring at the workplace’ project, involving road workers from the Leeuwenstein Group and builders from Heijmans and in collaboration with TNO, ArboUnie and RIVM, multiple exposures are measured using wearables (location, temperature, humidity, UV, noise and fine dust). The Eminent Doctoral Research is looking for optimal information provision about non-observable exposure risks among blue-collar workers.

The knowledge gained in this line of research is put to use in the Smart Health and Smart Safety studies. After all, measurements have to be taken by static or mobile systems such as drones and inspection robots, which preferably also move autonomously. In autonomous motion, the combination of various types of sensors, the so-called sensor fusion, is of great importance. The data must be collected intelligently via an optimal acquisition system, i.e. accurate enough to answer the question. This is because the following processing steps are time-consuming and costly: gathering measurements via secure wireless networks, storing, filing, and cleaning them and using big data analytics to make them suitable for observation, prediction models and feedback systems. This approach is a permanent basis for the development of other lines of research. 
The LearningLab Urbinn on the development of self-propelled vehicles brings together a series of projects such as the Twizzy and the self-propelled bin. In the Smart Wheelchair project, different sensors, such as Lidar, ultrasonic and 3D vision, are combined to create maps of static and dynamic objects, determine routes via algorithms and then drive. In the requested SIA RAAK MKB project 'Let's move IT', an integrated fleet management system will be examined. Within this project, the HHS will develop autonomous navigation systems that can operate safely in dynamic environments, for example where people and other mobile robots are involved.




URBINN is the LearningLab for autonomous transportation within urban areas (the so-called “last mile”). URBINN is developing an autonomous vehicle which will serve as a basis for further development and which can be used in a variety of other research. In the Applied Data Science minor, work is being done on real-time mapping of the environment with the use of stereo camera images. 
Read more