Human Factors

https://upload.wikimedia.org/wikipedia/commons/e/e6/Flickr_-_Official_U.S._Navy_Imagery_-_Doctors_perform_surgery_together..jpg

Master thesis

  • MHF1 - HUMAN BEHAVIOUR IN COOPERATIVE INTELLIGENT TRANSPORT SYSTEMS (GOUDAPPEL)

    SUPERVISORS: PROF. WILLEM VERWEY, SUPERVISORS AT GOUDAPPEL

    35EC

    INTRODUCTION

    Innovations and connected systems in traffic – also known as Cooperative Intelligent Transport Systems (C-ITS) - tend to support many policy goals, such as improving traffic flow and traffic safety, or reducing traffic emissions. Think about smart traffic lights or real-time speed advice. However, the effect of such systems strongly depends on human behaviour: How do different people react on different technological possibilities? Do they react as intended, and if not, how else do they react? And consequently, what is the effect of human behaviour on the stated policy goals?                                                                            

    ASSIGNMENT

    We want to explore realistic behavioural options related to C-ITS and their effects on traffic. Therefore, we aim at understanding how human behaviour can be integrated in models that help predicting traffic effects. We foresee an assignment that consists of a thorough (literature) study on behavioural aspects of CITS and several experiments to test hypotheses.

    The following questions are indicative for this research:

    • What are behavioural benefits and shortcomings of different C-ITS use case such as GLOSA, TTG, TTR, priority for different user groups?
    • (How) do different road users react on systems that communicate time to green or a speed advice? • What road users benefit most from C-ITS?
    • How does the success of C-ITS depend on different situations and environments?
    • How does the behaviour of misusers differ from intended use ? And how in relation to degree of C-ITS use and availability on the road?
    • If people misuse C-ITS for personal advantage, what happens, and who is disadvantaged? • How aware are drivers of C-ITS capabilities of their vehicle and how to use them?
    • HMI designs from different OEMs may differ, how does that affect behavioural response and adaptation?
    • What is the willingness to pay for C-ITS options in vehicles?
    • What benefits should C-ITS use cases provide to users in order to use attractive?
    • How can we capture the heterogeneity in responses and behaviour towards C-ITS use cases in simulation models so we can assess societal effects (traffic changes, emission changes, traffic safety changes, etc).

    Good To Know

    This assignment is very suitable for a student who is interested in human factors and new technology in the field of mobility. Moreover, this assignment is executed in an international setting with real-life case studies. Some experience with programming and modeling software (such as Matlab or Vissim) is highly recommended.

    Interested? If you are interested, please contact:
    Rick Schotman, rschotman@goudappel.nl, +31 (0) 655248152
    Martijn Legêne, mlegene@goudappel.nl, +31 (0) 611598644.

    More information on graduating at Goudappel can be found on: https://www.werkenbijgoudappel.nl/vacaturebeschrijving/afstuderen-of-stagelopen

  • MHF2 - ARTIFICIAL INTELLIGENCE CONVERSATIONAL AGENTS: A MEASURE OF SATISFACTION IN USE

    SUPERVISOR: DR. SIMONE BORSCI

    Background

    Conversational agents, such as chatbots and voice interfaces, can be used for multiple purposes e.g., support customer experience with services etc. These new tools are growing and more and more integrated into systems such as websites, social networks, cars. Smart and AI-based conversational agents are shaping the future of human-computer interaction however little is known about how to assess people reaction and satisfaction after the use of these systems.

    Goals

    Advance previous work done on a new scale to assess satisfaction with chatbots. Your experimental work will focus on the evaluation of conversational agents to further streamline the reliability and validity of the scale.

    Your work will consist of testing with a remote usability test different chatbots with a set of tools, including the new scale to perform a confirmatory factorial analysis. You should be aware of statistical methods regarding factorial analysis and be able to use R. The target is to involve at least 100 participants working (potentially) in a team.

    Key references

    • Coperich, K., Cudney, E., & Nembhard, H. Continuous Improvement Study of Chatbot Technologies using a Human Factors Methodology.
    • Duijst, D. (2017). Can we Improve the User Experience of Chatbots with Personalisation? MSc Information Studie, Amsterdam. 
    • Følstad, A., & Brandtzæg, P. B. (2017). Chatbots and the new world of HCI. interactions, 24(4), 38-42.
    • Hill, J., Ford, W. R., & Farreras, I. G. (2015). Real conversations with artificial intelligence: A comparison between human–human online conversations and human–chatbot conversations. Computers in Human Behavior, 49, 245-250.
  • MHF3 - THE VIGILANT BRAIN IN A DRIVING SIMULATOR

    SUPERVISORS: DR. ROB VAN DER LUBBE, DR. SIMONE BORSCI

    35EC

    In recent MA-projects, we focused on the relevance of different measures derived from the EEG to measure the vigilant state of individuals. With these measures, the major idea was to determine what analysis method is most effective in predicting lapses of attention, which in for example driving conditions may lead to serious accidents. The goal of the current research is to use functional near infrared spectroscopy (fNIRS) in combination with a driving simulator and examine whether fNIRS is possibly better able than EEG to predict errors that in real life situations would have led to serious accidents.

  • MHF4 - USING EMG TO OBSERVE COMPLEX MOTOR LEARNING IN BRONCHOSCOPY

    SUPERVISORS: DR. MARTIN SCHMETTOW, DR. RUSSELL CHAN

    Bronchoscopy is the inspection of the lungs using an endoscope camera. Bronchoscopy requires not only good anatomical knowledge, but also rests on the development of fine-motor skills for effectively and safely navigating the camera. Acquiring these skills on real patients puts these at risk.

    In the ongoing project MISTA (Minimally invasive surgery training and assessment, in collaboration with TechMed), the possibilities to design effective surgery simulator trainings are explored. Previous studies have shown that learning curve analysis is useful in this context. However, high-level performance measures, such as time-on-task or number of errors have limited value for understanding the learning process.

    The aim of this thesis project is to explore the possibilities of capturing motor patterns during learning, by using electromyography (EMG). During this project, you will:

    1.       Develop a basic EMG sensor array using Arduino or MicroPython
    2.       Develop a basic data collection and analysis protocol
    3.       Design a pilot study and collect data
    4.       Explore methods to extract useful measures from single-sensor EMG data
    5.       Explore methods to extract useful measures from multi-senor EMG data
    6.       Collect data in a learning experiment
    7.       Perform a learning curve analysis

    This is a thesis project for a team of two students. If only one student signs up, the scope will be adjusted, accordingly. During the project you will collaborate with TechMed with additional support by BMSLab. Furthermore, the possibility exists to split the project into an internship and a thesis part.

    First supervisor: Martin Schmettow

    Second supervisor: Russell Chan

    External supervisor: Evelyne Gerretsen

    Literature:

    Cold, K. M., Svendsen, M. B. S., Bodtger, U., Nayahangan, L. J., Clementsen, P. F., & Konge, L. (2021). Automatic and Objective Assessment of Motor Skills Performance in Flexible Bronchoscopy. Respiration, 100(4), 347–355. https://doi.org/10.1159/000513433

    http://essay.utwente.nl/73211/

    https://schmettow.github.io/New_Stats/LCM.html

  • MHF5 – THE ESCAPEROOM THAT SAVES LIVES

    SUPERVISORS: DR. MARTIN SCHMETTOW, DR. MARLEEN GROENIER

    An escape-room for intensive care professionals to improve teamwork and train Human Factors.

    Current situation

    In a critical medical environment, patients are threatened by the risk of human error. Miscommunication, failures when preparing and delivering medication, technical difficulties in combination with emotional stress and time pressure renders the ICU a vulnerable environment. Medical doctors and nurses, both with different backgrounds and skills, working in high-critical situations under time pressure have to collaborate optimally to create the safest environment for the patient. In order to guarantee and improve patient safety, we work according to principles of “Crew resource management” (CRM). CRM and the understanding of human factors was developed as a result of critical incidents in aviation. After implementing the principles of CRM, aviation has become safer. Nowadays CRM is considered the gold standard method in improving safety through professional communication in critical environments like healthcare, aviation, nuclear power plants, army environment etc.

    From 2010 all new ICU personnel involved in patient care at our department undergo a basic 2-day awareness training by a professional CRM training organization (www.wingsofcare.nl). Additionally, we developed an ICU simulation training program with a focus on CRM in daily clinical situations. Finally, we implemented a one-day CRM refresh course that has to be completed every three years. In doing so we have become a reference center in the Netherlands.

    After implementing the above-mentioned principles of CRM for 10 years now, research has indeed shown reduced morbidity and mortality in our units.

    The problem

    The CRM program of the Radboudumc is well organized and they have become one of the CRM reference centers in the Netherlands. However, after several years we experienced that teamwork is the most difficult skill to practice and implement. Sharing thoughts, speaking up, giving and receiving feedback, taking leadership and followership are the most important issues with regard to CRM to teach but the hardest to get done. Both the simulation education and the refresh course served us well but have become inadequate for reaching a higher level of CRM and thus safety. We feel the need for a higher, more advanced, and more versatile level of training to let medical ICU teams work together in solving problems as fast and safe as possible.

    In search of an alternative and more adequate method we encountered the "escape room" as an environment for this purpose. For instance, the Royal Dutch Navy uses this as a tool for team training.

    We believe this out of the box environment might create powerful possibilities to train a team of medical intensive care professionals to solve a (non) medical problem by using each other’s expertise and the skills mentioned above. The main goal of this training environment is to create a critical atmosphere where the team needs to communicate, share their thoughts, split tasks and help one another to get to the answer of a certain problem under pressure within a limited time. By using the desired behavior learned during the previous basic CRM training they can beat other teams. It should also become a course much different from the ones already existing and therefore challenging and daring. By building an escape room we hope to not only teach the skills but also force to use them while having fun together. It could be the perfect way to create team building, teamwork, and learning.

    In the minor High Tech Human Touch Science2Society a team of bachelor students has worked on a first prototype that is now ready to be tested with the target group. The current project aims to evaluate and incrementally develop this prototype into a full scale Escape Room.

    In this way it could be of great value to help increase CRM skills. Such an escape room could save the lives of vulnerable patients in the ICU!

    The Radboudumc Intensive care unit

    The Radboud university medical center in Nijmegen is a university teaching hospital and provides patient care, medical education and medical research. Our intensive care department admits and treats over 3000 critically ill adults and children each year. We treat patients with varying life-threatening disorders in a demanding high-tech environment using the latest medical technologies including extra corporal life support. The intensive care department employs approximately 30 intensivists, 300 medical nurses and additional medical residents and fellows in intensive care medicine.

    What do we expect from you?

    We expect a hands-on mentality and excellent communication skills. You will collaborate closely with the intensivists from the Radboudumc. Regular meetings (online or in Nijmegen) are required. The intensivists will support you with their knowledge and experience with CRM training.

    Supervisors

    Dr. Martin Schmettow

    Dr. Marleen Groenier (TechMed Centre)

    Contacts Radboudumc ICU

    Twiggy Walk, MD, pediatrician - pediatric intensivist and CRM trainer. twiggy.walk@radboudumc.nl

    Joris Lemson, MD PhD, anesthesiologist - pediatric intensivist and medical director pediatric intensive care. joris.lemson@radboudumc.nl        

    Radboud university medical center
    Department of intensive care medicine
    P.O. Box 9101, 6500 HB Nijmegen, The Netherlands Geert Grooteplein-Zuid 10 (route 707)

    References

    1. https://www.wingsofcare.nl

    2. Haerkens MH, Jenkins DH, Hoeven H van der: Crew resource management in the ICU: the need for culture change. Ann Intensive Care 2012; 2:39. https://annalsofintensivecare.springeropen.com/articles/10.1186/2110-5820-2-39

    3. Haerkens MHTM, Kox M, Lemson J, Houterman S, Hoeven JG van der, Pickkers P: Crew Resource Management in the Intensive Care Unit: a prospective 3-year cohort study. Acta Anaesth Scand 2015; 59:1319–29

    4. https://magazines.defensie.nl/allehens/2018/07/08_escaperoom