Dawud Gordon

Dawud Gordon

About

Detail

CEO & Co-Founder
New York, United States

Timeline

work
Job
school
Education
folder
Project
flag
Award
auto_stories
Publication

Résumé

Jobs verified_user 0% verified
  • Entrepreneurs Roundtable Accelerator
    Cohort #12
    Entrepreneurs Roundtable Accelerator
    Jan 2017 - May 2017 (5 months)
  • Twosense
    CEO & Co-Founder
    Twosense
    Jan 2016 - Current (10 years 9 months)
    Using AI and Machine Learning for Continuous Authentication.
  • T
    CEO & Co-Founder
    TwoSense LLC
    Oct 2013 - Dec 2016 (3 years 3 months)
  • ETH Zurich
    Visiting Researcher
    ETH Zurich
    Sep 2012 - Nov 2012 (3 months)
    Period as a Visiting Researcher at the Wearable Computing Lab under the advisement of Prof. Gerhard Tröster and Dr. Daniel Roggen.

    Research Focus:
    Social group affiliation detection from mobile and wearable sensor signals.
  • Karlsruhe Institute of Technology KIT
    Researcher
    Karlsruhe Institute of Technology KIT
    May 2010 - Sep 2013 (3 years 5 months)
    KIT is one of Germany's most prestigious universities for Computer Science and Engineering.

    Research Foci:
    - Machine Learning for behavior analytics (human activity recognition)
    - Embedded and distributed sensing systems
    - Mobile and wearable devices
    - Internet-of-Things (IoT)
  • Technische Universität Braunschweig
    Researcher
    Technische Universität Braunschweig
    Jun 2009 - May 2010 (1 year)
  • Miltenyi Biotec
    Intern
    Miltenyi Biotec
    Mar 2005 - Mar 2006 (1 year 1 month)
    Dawud developed intranet web applications using C# and .NET technology in the biotech industry.
  • Teledyne LeCroy
    R&D Intern
    Teledyne LeCroy
    Jan 2001 - Dec 2004 (4 years)
    Dawud developed QA scripts for the oscilloscope engineering and software dev team.
Education verified_user 0% verified
  • Karlsruhe Institute of Technology KIT
    Ph.D. (Dr.-Ing, Computer Science
    Karlsruhe Institute of Technology KIT
    Jan 2010 - Dec 2014 (5 years)
  • Universidad de Guadalajara
    Study Abroad, Artificial Neural Networks, Spanish Language
    Universidad de Guadalajara
    Jan 2007 - Dec 2007 (1 year)
  • Technische Universität Braunschweig
    Master of Science (M.Sc, Informatics
    Technische Universität Braunschweig
    Jan 2006 - Dec 2009 (4 years)
  • The Julius Maximilians University of Würzburg
    The Julius Maximilians University of Würzburg
    The Julius Maximilians University of Würzburg
    Jan 2004 - Dec 2005 (2 years)
  • University at Albany
    Bachelor of Science (BSc, Computer Science Combined with Physics
    University at Albany
    Jan 2000 - Dec 2004 (5 years)
  • G
    High School Diploma
    Green Meadow Waldorf School
    Jan 1996 - Dec 2000 (5 years)
Projects (professional or personal) verified_user 0% verified
  • T
    Towards a Mobile Hybrid Cloud
    Jan 2013 - Current (13 years 9 months)
    This project is a continuation of the 2012 project "Towards a Mobile Cloud" and has the goal to deliver concepts and tools for managing specific aspects of hybrid cloud environments, including the optimization of quality of service and resource usage, and the manageability of heterogeneous environments. My research in this project is towards improving the user experience of mobile user devices by deciding in a context-dependent manner at run-time which parts of the required functionality shall be executed on the device and which parts shall be executed in the cloud. This project was funded by the EU EIT ICT Labs.
  • P
    PHAR: Practical Human Activity Recognition
    Jan 2013 - Current (13 years 9 months)
    he goal of this project is to create practical approaches to human activity recognition (HAR). My research focus is on group activity recognition with a focus on algorithms and exploratory research.
  • T
    Towards a Mobile Cloud
    Jan 2012 - Current (14 years 9 months)
    This project conducts research in order to support next-generation elastic mobile clouds, where mobile scenarios are consistently supported by cloud environments. My research in this project is towards improving the user experience of mobile user devices by deciding in a context-dependent manner at run-time which parts of the required functionality shall be executed on the device and which parts shall be executed in the cloud. Partners included SAP Research and Ericsson Research. This project was funded by the EU EIT ICT Labs.
  • C
    CHOSeN - Cooperative Hybrid Objects Sensor Networks
    Jan 2011 - Current (15 years 9 months)
    The goal of this project was to develop adaptable, scalable wireless sensing systems for automotive (FIAT) and aeronautic (EADS/Airbus) applications. My research within this project was on developing scalable wireless communication protocols and a middleware application for the novel wireless sensor network technology developed within the project (Infineon/TU Wien). This project was funded by the European Research Council.
  • d
    dinam-mite: Platform-as-a-Service for wireless sensor network applications
    Jan 2010 - Current (16 years 9 months)
    The dinam concept is a novel approach to simplified rapid development of wireless sensor network applications as well as an according WSN platform. My research here was on embedded systems, embedded development environments (IDE) and programming methods and wireless sensor network usability. This project was funded by TU Braunschweig and later KIT.
  • S
    SenseCAST: Context Prediction for Optimisation of Network Parameters in Wireless Sensor Networks
    Jan 2010 - Current (16 years 9 months)
    The aim of the project is to develop new methods for context prediction in wireless sensor networks and to utilize these for dynamic adaptation and optimization of network behavior. My research focus was on embedded recognition and prediction algorithms, with emphasis on low-power and low-complexity execution. This project was funded by the Deutsche Forschungsgemeinschaft (German Research Foundation).
  • R
    RELATE
    Jan 2009 - Current (17 years 9 months)
    The goal of RELATE is to research spatial relationships between tangible objects that together form an interface both in P2P location hardware, software (recognition, protocols, applications) and user applications. As a student my work here was to integrate all partner contributions into a final project demonstrator of generic building blocks for a lightweight short range (room size) location system that does NOT require infrastructure, administration, configuration or management and can be integrated into everyday objects.
Awards verified_user 0% verified
  • Karlsruhe Institute of Technology
    Magna Cum Laude
    Karlsruhe Institute of Technology
    Apr 2014
  • B
    Brooklyn Startups: Elevator Pitch Competition Winner
    Jan 2014
  • F
    Best Paper Award
    Fifth International Conference on Mobile Computing Applications and Services MobiCASE
    Nov 2013
    Dawud Gordon, Sven Frauen, Michael Beigl (2013) Reconciling Cloud and Mobile Computing using Activity-Based Predictive Caching,International Conference on Mobile Computing, Applications and Services (MobiCASE) Abstract: Cloud computing has greatly increased the utility of mobile devices by allowing processing and data to be offloaded, leaving an interface with higher utility and lower resource consumption on the device. However, mobility leads to loss of connectivity, making these remote resources inaccessible, breaking that utility completely during offline periods. We present a concept for reconciling the fragile connectivity of mobile devices with the distributed nature of cloud computing. We predict periods without connectivity on the m
  • S
    Honorable Mention
    Sixteenth International Symposium on Wearable Computers ISWC
    Sep 2013
    Dawud Gordon, Jurgen Czerny, Takashi Miyaki, Michael Beigl (2012) Energy-Efficient Activity Recognition Using Prediction,16th International Symposium on Wearable Computers, p. 29-36, Abstract: Energy storage is quickly becoming the limiting factor in mobile pervasive technology. For intelligent wearable applications to be practical, methods for low power activity recognition must be embedded in mobile devices. We present a novel method for activity recognition which leverages the predictability of human behavior to conserve energy. The novel algorithm accomplishes this by quantifying activity-sensor dependencies, and using prediction methods to identify likely future activities. Sensors are then identified which can be temporarily turned of
  • S
    Best Paper Nominee
    Sixteenth International Symposium on Wearable Computers ISWC
    Sep 2012
    Dawud Gordon, Jurgen Czerny, Takashi Miyaki, Michael Beigl (2012) Energy-Efficient Activity Recognition Using Prediction,16th International Symposium on Wearable Computers, p. 29-36, Abstract: Energy storage is quickly becoming the limiting factor in mobile pervasive technology. For intelligent wearable applications to be practical, methods for low power activity recognition must be embedded in mobile devices. We present a novel method for activity recognition which leverages the predictability of human behavior to conserve energy. The novel algorithm accomplishes this by quantifying activity-sensor dependencies, and using prediction methods to identify likely future activities. Sensors are then identified which can be temporarily turned of
  • N
    Best Demo Nominee
    Ninth International Conference on Pervasive Computing PERVASIVE
    Jun 2011
    Dawud Gordon, Martin Alexander Neumann, Michael Beigl (2011) Program Your Reality with dinam-mite, Demonstration at the Ninth International Conference on Pervasive Computing Pervasive11 Abstract. This demonstration will present a self-contained wireless sensor network development environment. The entire toolchain required for development is served by each sensor node, including the IDE, libraries, code, data and visualization. Conference visitors will be able to program applications using the web browser on their own laptops or mobile phones, and see for themselves how much this integration simplifies the process of WSN application development.
  • D
    Deans List
    Sep 2004
Publications verified_user 0% verified
  • A
    Group Activity Recognition Using Belief Propagation for Wearable Devices
    ACM International Symposium on Wearable Computers ISWC
    Sep 2014
    Humans are social beings and spend most of their time in groups. Group behavior is emergent, generated by members' personal characteristics and their interactions. It is therefore difficult to recognize in peer-to-peer (P2P) systems where the emergent behavior itself cannot be directly observed. We introduce 2 novel algorithms for distributed probabilistic inference (DPI) of group activities using loopy belief propagation (LBP). We evaluate their performance using an experiment in which 10 individuals play 6 team sports and show that these activities are emergent in nature through natural processes. Centralized recognition performs very well, upwards of an F-score of 0.95 for large window sizes. The distributed methods iteratively converge
  • A
    Group Affiliation Detection Using Model Divergence for Wearable Devices
    ACM International Symposium on Wearable Computers ISWC
    Sep 2014
    Methods for recognizing group affiliations using mobile devices have been proposed using centralized instances to aggregate and evaluate data. However centralized systems do not scale well and fail when the network is congested. We present a method for distributed, peer-to-peer (P2P) recognition of group affiliations in multi-group environments, using the divergence of mobile phone sensor data distributions as an indicator of similarity. The method assesses pairwise similarity between individuals using model parameters instead of sensor observations, and then interprets that information in a distributed manner. An experiment was conducted with 10 individuals in different group configurations to compare P2P and conventional centralized appro
  • I
    Reconciling Cloud and Mobile Computing Using Activity-Based Predictive Caching
    International Conference on Mobile Computing Applications and Services MobiCASE Springer Verlag
    Jan 2013
    Cloud computing has greatly increased the utility of mobile devices by allowing processing and data to be offloaded, leaving an interface with higher utility and lower resource consumption on the device. However, mobility leads to loss of connectivity, making these remote resources inaccessible, breaking that utility completely during offline periods. We present a concept for reconciling the fragile connectivity of mobile devices with the distributed nature of cloud computing. We predict periods without connectivity on the mobile devices before they occur and cache process states for applications running on distributed cloud back-ends. The goal is to maintain partial or full utility during offline periods, and thereby to enable an improved
  • J
    Activity Recognition for Creatures of Habit: Energy-Efficient Embedded Classification using Prediction
    Journal of Personal and Ubiquitous Computing Springer Verlag
    Jan 2013
    Energy storage is quickly becoming the limiting factor in mobile pervasive technology. We introduce a novel method for activity recognition which leverages the predictability of human behavior to conserve energy by dynamically selecting sensors. We further present a taxonomy of existing approaches to dynamically reducing consumption while maintaining recognition rates. The novel algorithm conserves energy by quantifying activity-sensor dependencies and using prediction methods to identify likely future activities. The approach is implemented and simulated using two activity recognition data sets, and the effects of the novel method are evaluated in terms of recognition rates, energy consumption, and prediction rates. The results indicate th
  • J
    Towards Collaborative Group Activity Recognition Using Mobile Devices
    Journal of Mobile Networks and Applications Springer Verlag
    Jan 2013
    In this paper, we present a novel approach for distributed recognition of collaborative group activities using only mobile devices and their sensors. Information must be exchanged between nodes for effective group activity recognition (GAR). Here we investigated the effects of exchanging that information at different data abstraction levels with respect to recognition rates, power consumption, and wireless communication volumes. The goal is to identify the tradeoff between energy consumption and recognition accuracy for GAR problems. For the given set of activities, using locally extracted features for global, group activity recognition is advantageous as energy consumption was reduced by 10 % without experiencing any significant loss in re
  • t
    Energy-Efficient Activity Recognition Using Prediction
    th International Symposium on Wearable Computers IEEE
    Jan 2012
    Energy storage is quickly becoming the limiting factor in mobile pervasive technology. For intelligent wearable applications to be practical, methods for low power activity recognition must be embedded in mobile devices. We present a novel method for activity recognition which leverages the predictability of human behavior to conserve energy. The novel algorithm accomplishes this by quantifying activity-sensor dependencies, and using prediction methods to identify likely future activities. Sensors are then identified which can be temporarily turned off at little or no recognition cost. The approach is implemented and simulated using an activity recognition data set, revealing that large savings in energy are possible at very low cost (e.g.
  • N
    WoR-MAC: Combining Wake-on-Radio with Quality-of-Service for intelligent environments
    Ninth International Conference on Networked Sensing INSS IEEE
    Jan 2012
  • J
    Recognizing Group Activities using Wearable Sensors
    Journal of Mobile and Ubiquitous Systems Computing Networking and Services
    Jan 2011
    Pervasive computing envisions implicit interaction between people and their intelligent environments instead of between individuals and their devices, inevitably leading to groups of individuals interacting with the same intelligent environment. These environments must be aware of user contexts and activities, as well as the contexts and activities of groups of users. Here an application for in-network group activity recognition using only mobile devices and their sensors is presented. Different data abstraction levels for recognition were investigated in terms of recognition rates, power consumption and wireless communication volumes for the devices involved. The results indicate that using locally extracted features for global, multi-user
  • I
    ActiServ: Activity Recognition Service for mobile phones
    International Symposium on Wearable Computers ISWC IEEE
    Jan 2010
    Smart phones have become a powerful platform for wearable context recognition. We present a service-based recognition architecture which creates an evolving classification system using feedback from the user community. The approach utilizes classifiers based on fuzzy inference systems which use live annotation to personalize the classifier instance on the device. Our recognition system is designed for everyday use: it allows flexible placement of the device (no assumed or fixed position), requires only minimal personalization effort from the user (1-3 minutes per activity) and is capable of detecting a high number of activities. The components of the service are shown in an evaluation scenario, in which recognition rates up to 97% can be ac
  • I
    A novel micro-vibration sensor for activity recognition: Potential and limitations
    International Symposium on Wearable Computers ISWC IEEE
    Jan 2010
    This paper researches the potential of a novel ball switch as a wearable vibration sensor for activity recognition. The ball switch is available as a commercial, off-the-shelf sensor and is unique among such sensors due to its miniaturized design and the low mass of the ball. We present a detailed analysis of the physical properties of the sensor as well as a recommendation for circuit design, sampling method and a feature generation algorithm for activity recognition. The analysis reveals that it is sensitive to vibrations between 1.5 kHz and 8 kHz, where the acceleration sensor is responsive below 1.6 kHz. Furthermore, the ball switch is substantially cheaper (3x), smaller (2x) and uses less power (50x) than an accelerometer based system,
This is a community-created genome.