.01

ABOUT ME

Personal details
+31 53 489 6434 (work)
Hello and welcome to my personal page. I am a third year PhD candidate located in the Netherlands currently attempting to achieve my PhD dream early 2023. Take a look around to see my interests, and do not hesitate to reach out with questions, suggestions for collaborations, or career opportunities for me. :)

bio

About me

I finished my B.Sc in Technical Computer Science at the University of Twente in 2016 with research being done in wireless sensor networks (flexible sensors in sports applications). In 2018, I received my M.Sc. (cum laude) in Technical Computer Science (Wireless and Sensor Systems) with research in deep learning and device-free sensing.

My current research still continues this trend, by actively doing research into RF-based device-free sensing in multiple domains and applying deep learning in real-life settings. I am also trying to actively increase my knowledge in antenna design, radio-wave/signal propagation at a physics level, and advancing the mathematical frameworks in deep learning.

I am also actively involved in my old Bachelor programme, B-TCS, as a mentor for first-year students and participating as a lecturer and supervisor in multiple BSc courses. Since 2019, I also actively help in and contribute to the M.Sc. course Pervasive Computing at the University of Twente.

.02

MY RESEARCH

Research interests
  • Channel state information
  • Radio-wave propgation
  • Digital signal processing
  • Deep learning
  • Convolution Neural Networks
  • Joint Communication and Sensing
  • e-Health
  • Biodiversity
  • Light pollution
  • mmWave
  • Software defined radios
  • Multipath propagation
  • Sensors
  • Wireless sensor networks
  • Internet-of-Things
  • Communication and networking
  • Wireless optical communication
  • Machine learning

Ongoing research focus
.03

publications

List of publications
6
Oct
2021

Implementation of Unobtrusive Sensing Systems for Older Adult Care

Journal of Medical Internet Research

This scoping review aims to examine the literature to identify current USSs for monitoring human activities and behaviors and assess their implementation readiness for older adult care.

  • Journal
Sharma, N., Klein Brinke, J., Gemert-Pijnen, J.E.W.C.V., & Braakman-Jansen, L.M.A.
17
Feb
2021

Personal Hygiene Monitoring Under the Shower Using WiFi CSI

Delft, the Netherlands

This paper leverages the 802.11n channel state information to monitor different shower-related activities and the degree to which some of these can be monitored, as well estimating different water pressures used while showering.

  • Workshop
Klein Brinke, J., Chiumento, A., & Havinga, P.J.M.
10
Nov
2019

CSI Analysis for Predictive Maintenance using CNN

New York, United States of America

This paper focuses on the classification of CSI signals influenced by rotating motors at different speeds. As WiFi CSI technology is still not mature, we focus on data collection and study the sensitivity and reliability of data for this type of applications. We observe that CNNs are suitable to classify the speeds of motors.

  • Workshop
Bagave, P., Linssen, J., Teeuw, W., Klein Brinke, J., & Meratnia, N.
10
Nov
2019

Scaling HAR using CSI through CNN and Transfer Learning

New York, United States of America

This paper focuses on two aspects. First, convolutional networks are used across multiple participants, days and activities and analysis is done based on these results. Secondly, it looks into the possibility of applying transfer learning based on raw channel state information over multiple participants and activities over multiple days. Results show channel state information is accurate for single participants (F1-score of 0.90).

  • Workshop
Klein Brinke, J., & Meratnia, N.
10
Nov
2019

Channel State Information for Different Activities, Participants and Days

New York, United States of America

While most research focuses on analysis of individuals or clustered data, little to no research has gone into the analysis of channel state information of multiple people over multiple days for different and comparable activities. This dataset contains data of nine different participants over three different days, with an two participants repeating the activities over an additional three days.

  • Workshop
Klein Brinke, J., & Meratnia, N.
.04

assignments

List of assignments
Bachelor level

WiPi: Contactless sensing using a Raspberry Pi and NEXMON

20% Implementation, 20% Data gathering, 40% Data analysis, 20% Writing

Current device-free methods that use channel state information (currently WiFi) for monitoring activity recognition are based on specific hardware, which is often outdated. This is a challenge for the future, as it gets incredibly more difficult to find the proper resources.

Still available (currently working: 0)
Bachelor level

Luistervinq: Activity recognition in nature using sound and AI

20% Theory, 60% Implementation, 20% Writing

Design and evaluate a prototype that can record audio, process raw audio on an embedded device (AI edge computing), and transmit the classified activity via a wireless medium. Identify open issues.

Still available (currently working: 0)
Master level

CommuniFi: Data transmission during device-free sensing of human activities

30% Implementation, 20% Data gathering, 30% Data analysis, 20% Writing

Your task is to implement a networking system (using AX210 chips) that can adapt to channel obstructions and networking requirements while gathering data regarding human activity recognition. After this, you will be asked to investigate how fast and reliably you can transmit this data, while also analysing how this affects the device-free monitoring of activities.

Still available (currently working: 0)
Master level

VariFi: Variable networking parameters during device-free sensing

10% implementation, 70% Data analysis, 20% Writing

Your task is to use a state-of-the-art dataset (channel state information) and to analyse what happens when you variate the networking parameters. You will need to write a piece of code to simulate the variable data rates. After this, the idea is that you look into how different sampling frequencies affect the accuracy (preferably deep learning), but also look into opportunities to deal with real-time classification with an unpredictable data stream.

Still available (currently working: 0)
Bachelor level

WiFi vs. Sensors: Face-off between wearable and radio-wave sensing

40% Data gathering, 40% Data analysis, 20% Writing

You will be given state-of-the-art devices to collect wireless traces (known as channel state information)/mmWave radar and access to a sensor-enabled chair or other high end wearables to collect data from both and compare the accuracies to help answer the ultimate question: Can wireless signals beat physical sensors for human activity recognition?

Still available (currently working: 1)
.05

teaching

qualifications

university teaching qualification

The UTQ is a mark of quality used by all Dutch universities. It functions as a reliable frame of reference with respect to your didactic skills. The UTQ track consists of a series of modules, allowing lecturers to assess and develop all facets of teaching.
current

Course organization

Organizing the MSc course Pervasive Computing. This includes organizing the administritive tasks, as well as examination and assessment, and communication with the students (supervision and lecturing).

Mentorship and head of mentors

Experience in mentoring (large) group of students due to the House-system. Also functioned as the head of these mentors, organizing and promoting connections between study advisors, course organizers, and programme directors.

Teaching assistent (PhD)

Helping out in different quartiles and courses as a teaching assistent in both the form of (guest) lecturer, supervisor, and grader. These courses include Academic Skills, Internet-of-Things, and the final graduation projects of various MSc/BSc studies.
history

Teaching assistent (student)

Helping out in different quartiles and courses as a teaching assistent during my time as both a BSc and MSc student for Technical Computer Science.
.07

skills

academic skills
Paper writing >I have high standards for my papers and other publications. I am highly proficient at academic writing, structuring a paper, and targeting an audience and maintain their focus throughout my writings. I enjoy writing papers and I am always looking for ways to improve.
85
LEVEL : ADVANCED EXPERIENCE : 3 YEARS
  • LaTex
  • English fluency
  • Structure
Data science >A big interest of mine is to work with the gathered data; my favourite tool for this is deep learning (Tensorflow) and the mathematics behind deep learning. I have followed multiple courses on digital signals and the processing of these. I am good at visualizing the data to make others understand what is happening.
80
LEVEL : PROFICIENT EXPERIENCE : 5 YEARS
  • Deep learning
  • Digital signal processing
  • Data filtering
  • Tensorflow
  • MATLAB
  • Data visualization
Data gathering >Since my BSc thesis I have had to set up experiments involving humans. Soon this will be expanded to insects and animals. I have experience with (controlled) experiment plans, human surveys, informed consent, and data management plans. I successfully got ethical approval from the board on multiple occassions.
70
LEVEL : INTERMEDIATE EXPERIENCE : 5 YEARS
  • Ethical approval
  • Experiment plans
  • Data management
Proposal writing >While my writing is an advantage, I have not had the fortune yet to write many proposals and I would like to get more experience in this. I did supportive writing in the form of discussing state-of-the-art, methodology, and a (global) planning. I sat in on meetings where stakeholders and funding were discussed.
45
LEVEL : BEGINNER EXPERIENCE : 1 YEARS
  • LaTex
  • Finding literature
  • Methodology
programming skills
Software development >I am very passionate about programming in multiple domains, such as research (data science, optimizing for lightweight devices), hobby (smart home, robotics), and even web design (as this website shows). I am very quick at analyzing the 'digital puzzle' and finding a way to make it work.
85
LEVEL : ADVANCED EXPERIENCE : 8 YEARS
  • Python
  • C
  • Java
  • Testing
  • Debugging
  • Problem-solving
  • SDR
  • Sensors
  • jQuery/Javascript
  • Flask web framework
Hardware development >Developing hardware is a hobby of mine and I often tinker around with sensor systems on my own. My current interest lies in antennas and the design thereof, in order to fully connect my research from low-level antenna design to analyzing the signal propagation for information extraction.
75
LEVEL : PROFICIENT EXPERIENCE : 5 YEARS
  • Soldering
  • TinyCAD
  • Testing
  • Problem-solving
  • Creative
management skills
Communication > I firmly believe that the key in any communication is expectation management. My presentation and group interaction skills are often perceived as good and inviting. I am heavily trying to improve even more on the interpersonal skills, as this is one of the more important aspects within my field.
90
LEVEL : ADVANCED EXPERIENCE : 5+ YEARS
  • Presentation
  • Group interaction
  • Body language
  • Interpersonal communication
Mentorship >I enjoy mentoring students and I have had a large variety of students so far, ranging from first-year Bachelor students (both HBO and university) to graduating Master-level student. I am familiar with mentoring students individually (those who require more aid), as well as efficiently and effectively mentoring in larger groups.
80
LEVEL : PROFICIENT EXPERIENCE : 8 YEARS
  • University students
  • HBO students
  • Groups
  • Individuals
  • Diversity
  • Conflict management
Forward planning and organisation >I am very familiar with the concepts of agile work and SCRUM and I enjoy keeping an overview of a project and set out a course to maintain. Part of supervising students is leading them and planning ahead stategically and to think outside the box to always have a backup plan ready.
70
LEVEL : INTERMEDIATE EXPERIENCE : 8 YEARS
  • SCRUM
  • Agile working
  • Project lead
  • Strategic planning
language skills
Dutch >Dutch is my native language, but we do not always get along well. It was my worst subject in high school and while I am fluent at it, it is mostly based on instinct rather than knowing the actual grammar rules and the exceptions by heart (oops). Nevertheless, I do like Dutch and I am happy that it is my native language.
95
LEVEL : EXPERT EXPERIENCE : 28 YEARS
English >At a very young age I was already interested in the English literature, such as Harry Potter and the Lord of the Rings. I would often attempt to read these in English, with a dictionary at my side. When I got into gaming at a young age, my English skills grew from there. While never doing official tests, I would estimate my level to be at C2.
95
LEVEL : EXPERT EXPERIENCE : 20+ YEARS
.08

resume

education
  Enschede, NL

Computer Science and Engineering - PhD

University of Twente

Research direction into joint communication and device free sensing for biodiversity and human health monitoring. Using WiFi channel state information for real-life adoption and optimizing channel prediction and sensing at once.
  Enschede, NL

Technical Computer science - MSc

University of Twente

Specalization in Wireless and Sensor Systems, graduated Cum laude Thesis: Analyzing Human Behaviour Through CSI using Neural Networks
  Enschede, NL

Technical Computer science - BSc

University of Twente

Thesis: Wireless Flex Sensors: Possibility of Detecting Improper Posture of a Runner's Arm
industry
  Enschede, NL

Software programmer/Data scientist

No nonsence technical solutions

Programming the microcontrollers for IoT devices and networking, as well as solving the Computer Science puzzles within projects while maintaining an overview of the data streams within the project.
  Enschede, NL

Web/Software developer

WWW Committee, Inter-/Actief/

Help maintaining the main website and several other IT projects within Inter-Actief.
qualifications
  Enschede, NL

University Teaching Qualification

University of Twente

The UTQ is a mark of quality used by all Dutch universities. It functions as a reliable frame of reference with respect to your didactic skills. The UTQ track consists of a series of modules, allowing lecturers to assess and develop all facets of teaching.
honors and awards
  Delft, NL

Best Talk Award

1st Workshop on Computer Human Interaction in IoT Applications

Achieved for the virtual presentation on Personal Hygine Monitoring Under the Shower Using WiFi Channel State Information
  Enschede, NL

Achieving Cum laude in Technical Computer Science, MSc

University of Twente

Achieving an average of 8.5 (out of 10) or higher for all courses and achieving a 9.0 or higher for the final thesis.
  Enschede, NL

Research Hounour's Programme

University of Twente

This individually tailored, extra-curricular track offers you additional knowledge and skills in the areas of research management, research publishment, and (PhD) research proposal development, aiming at excellent UT master students.
.09

contact

Work location

Office information

Location and room

Zilverling (ZI), room 5023, University of Twente
Hallenweg 19, 7552 NH Enschede
The Netherlands


Working hours and availability

Mon, Wed, Thu in office from 8:00 to 17:00
Tue, Fri at home (or office) from 8:00 to 17:00
Meetings scheduled between 9:00 and 16:00


Professional contact information

E-mail: [email protected]
Phone: +31 53 489 6434


Get in touch

Your message is on your way to me!

Thank you very much for your message. I will try to get back to you as soon as possible. Have a nice morning, afternoon, or evening wherever you are from!
- Jeroen