Zeljko Medenica

Zeljko Medenica

Birmingham, Michigan, United States
696 followers 500+ connections

Join to view profile

About

Team-player with hands-on mentality and a proven track record of applying creative and…

Activity

Join now to see all activity

Experience

  • MathWorks Graphic

    MathWorks

    Novi, Michigan, United States

  • -

    Plymouth, Michigan, United States

  • -

    Vienna, Austria

  • -

    Plymouth, Michigan, USA

  • -

    Plymouth, MI, USA

  • -

    Munich, Germany

  • -

    Southfield, MI, USA

  • -

    Burlington, MA, USA

  • -

    Durham, NH, USA

  • -

    Cambridge, MA, USA

  • -

    Cambridge, MA, USA

  • -

    Redmond, WA and Durham, NH

Education

Publications

  • Integrating a Real Vehicle into a Physics-Based Driving Simulator for Human-Machine Interaction Research

    IEEE International Conference on Human System Interaction (IEEE HSI)

    Driving simulators allow quick, safe and repeatable way of testing how a particular system behavior or design would be accepted by drivers. This is especially important when testing Human-Machine Interaction (HMI). As the fidelity of a driving simulator is increased, the quality of obtained data increases as well. However, high-fidelity driving simulators typically require significant financial investments and may not be very flexible in integrating with existing systems. In this paper we…

    Driving simulators allow quick, safe and repeatable way of testing how a particular system behavior or design would be accepted by drivers. This is especially important when testing Human-Machine Interaction (HMI). As the fidelity of a driving simulator is increased, the quality of obtained data increases as well. However, high-fidelity driving simulators typically require significant financial investments and may not be very flexible in integrating with existing systems. In this paper we intend to reach middle ground by proposing a medium-fidelity driving simulator, which provides both flexibility and reusability of the commonly used automotive components.

    Other authors

  • V2X Applications Using Collaborative Perception

    2018 IEEE 88th Vehicular Technology Conference (VTC-Fall)

    This paper describes an implementation of a collaborative environmental perception system. Our system combines V2X communication with several sensing devices: GPS, DSRC, and forward-looking camera. We present the system using four cooperative safety applications: EEBL, IMA, BSW and LTA. Our results show that collaborative perception may indeed enhance perceived V2X market penetration. This conclusion is supported by comparing collaborative perception data with pure DSRC data. Even with a…

    This paper describes an implementation of a collaborative environmental perception system. Our system combines V2X communication with several sensing devices: GPS, DSRC, and forward-looking camera. We present the system using four cooperative safety applications: EEBL, IMA, BSW and LTA. Our results show that collaborative perception may indeed enhance perceived V2X market penetration. This conclusion is supported by comparing collaborative perception data with pure DSRC data. Even with a government mandate, it will take many years before enough vehicles have V2X devices on-board. This technology has the potential to enhance V2X market penetration, which will enable all its safety benefits.

    See publication

  • Human Machine Interaction, Book Chapter in Connected Vehicles: Intelligent Transportation Systems

    Springer International Publishing

    The intention of this chapter is to describe what Human-Machine Interaction is, why it is important in the automotive context and how connected vehicles can benefit from it.

  • Using Convolutional Neural Networks for Distance Estimation between Dedicated Short-Range Communications Equipped Vehicles

    2018 IEEE 87th Vehicular Technology Conference (VTC Spring)

    This work explores the feasibility of leveraging deep learning methods for performing distance estimation between two Dedicated Short-Range Communications (DSRC) equipped vehicles. Real world DSRC data was collected from mixed environments. The data was used to perform hyperparameter search for constructing and training multiple Convolutional Deep Neural Networks (CDNN). Performances of several NN configurations were compared along with Ordinary Least Squares (OLS) regression. Results show that…

    This work explores the feasibility of leveraging deep learning methods for performing distance estimation between two Dedicated Short-Range Communications (DSRC) equipped vehicles. Real world DSRC data was collected from mixed environments. The data was used to perform hyperparameter search for constructing and training multiple Convolutional Deep Neural Networks (CDNN). Performances of several NN configurations were compared along with Ordinary Least Squares (OLS) regression. Results show that for shorter distances, NN estimation performance is similar to that of OLS regression. While for longer distances, CDNN performance shows improvement over regression in the average. These results suggest that distance estimation using CDNN is plausible. This method combined with other sensors may contribute to improved positioning in challenging environments.

    Other authors

  • Long Text Reading in a Car

    16th International Conference, HCI International

    We present here the results of a study focused on text reading in a car. The purpose of this work is to explore how machine synthesized reading is perceived by users. Are the users willing to tolerate deficiencies of machine synthesized speech and trade it off for more current content? What is the impact of listening to it on driver’s distraction? How do the answers to the questions above differ for various types of text content? Those are the questions we try to answer in the presented study…

    We present here the results of a study focused on text reading in a car. The purpose of this work is to explore how machine synthesized reading is perceived by users. Are the users willing to tolerate deficiencies of machine synthesized speech and trade it off for more current content? What is the impact of listening to it on driver’s distraction? How do the answers to the questions above differ for various types of text content? Those are the questions we try to answer in the presented study. We conducted the study with 12 participants, each facing three types of tasks. The tasks differed in the length and structure of the presented text. Reading out a fable represented an unstructured pleasure reading text. The news represented more structured short texts. Browsing a car manual was an example of working with structured text where the user looks for particular information without much focusing on surrounding content. The results indicate relatively good user acceptance for the presented tasks. Distraction of the driver was related to the amount of interaction with the system. Users opted for controlling the system by buttons on the steering wheel and made little use of the system’s display.

    Other authors

  • Video Call, or not, that is the Question

    CHI 2012, Extended abstracts

    New technologies have made video calling in vehicles possible. Results from a driving simulator experiment indicate that video calling reduces visual attention on the road. While in some situations drivers would refrain from engaging in this activity, our results should serve as a warning to interface designers, lawmakers, transportation officials, and drivers that video calling presents a real distraction from driving.

    Other authors
    See publication

  • Augmented Reality vs. Street Views: A Driving Simulator Study Comparing Two Emerging Navigation Aids

    MobileHCI 2011

    Prior research has shown that when drivers look away from the road to view a personal navigation device (PND), driving performance is affected. To keep visual attention on the road, an augmented reality (AR) PND using a heads-up display could overlay a navigation route. In this paper, we compare the AR PND, a technology that does not currently exist but can be simulated, with two PND technologies that are popular today: an egocentric street view PND and the standard map-based PND. Using a…

    Prior research has shown that when drivers look away from the road to view a personal navigation device (PND), driving performance is affected. To keep visual attention on the road, an augmented reality (AR) PND using a heads-up display could overlay a navigation route. In this paper, we compare the AR PND, a technology that does not currently exist but can be simulated, with two PND technologies that are popular today: an egocentric street view PND and the standard map-based PND. Using a high-fidelity driving simulator, we examine the effect of all three PNDs on driving performance in a city traffic environment where constant, alert attention is required. Based on both objective and subjective measures, experimental results show that the AR PND exhibits the least negative impact on driving. We discuss the implications of these findings on PND design as well as methods for potential improvement.

    Other authors
    See publication

  • Contextual push-to-talk: shortening voice dialogs to improve driving performance

    MobileHCI 2010

    We present a driving simulator-based evaluation of a new technique for simplifying in-vehicle device interactions and thereby improving driver safety. We show that the use of multiple, contextually linked push-to-talk buttons (Multi-PTT) shortens voice dialog duration versus the use of a conventional, single push-to-talk button (Single-PTT). This benefit comes without detriment to driving performance or visual attention to the forward roadway. Test subjects also preferred the Multi-PTT approach…

    We present a driving simulator-based evaluation of a new technique for simplifying in-vehicle device interactions and thereby improving driver safety. We show that the use of multiple, contextually linked push-to-talk buttons (Multi-PTT) shortens voice dialog duration versus the use of a conventional, single push-to-talk button (Single-PTT). This benefit comes without detriment to driving performance or visual attention to the forward roadway. Test subjects also preferred the Multi-PTT approach over the conventional approach, and reported that it imposed a lower cognitive workload.

    Other authors
    See publication

Patents

  • Apparatus and methods for providing vehicle driving information

    US 10150410

    Other inventors

  • System for alerting a driver and method thereof

    US 9669758

    Other inventors
    • Craig Mitchell
    • Bradford D. Kent
    • Jeffrey Grix

  • Vehicular communications network and methods of use and manufacture thereof

    US 10081357

    Other inventors

Courses

  • Data Analysis

    -

  • Image and Video Processing

    -

  • Machine Learning

    -

Languages

  • German (A2)

    Elementary proficiency

  • English

    Full professional proficiency

  • Serbian

    Native or bilingual proficiency

Recommendations received

2 people have recommended Zeljko

Join now to view

More activity by Zeljko

View Zeljko’s full profile

  • See who you know in common
  • Get introduced
  • Contact Zeljko directly
Join to view full profile

Other similar profiles

Explore more posts

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More