Download PDF


Received his B.S. degree in mechatronics engineering from Tishreen University, Lattakia, Syria, in 2008. He received his M.S. degree in health care IT from from Carinthia University of Applied Science, Klagenfurt, Austria, In October 2016 he finished his PhD at Klagenfurt University. He is a university assistant, and a lecturer at the Institute for Smart System Technology (IST), University of Klagenfurt in Austria. His research interests include machine vision, machine learning, applied mathematics, and neurocomputing. He developed a variety of methods in the scope of human-machine interaction and pattern recognition. He has participated in several projects in the field of transportation informatics, and the outcomes were patented


Teaching Experience

Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies



ROTEN KREUZ KÄRNTEN-Red Cross Carinthia:

  • Arabic-English/German Translator


Cloud Computing

Computer Graphics

Project Managment

Public Speaking



Machine Vision


Neural Networks

Machine Learning and Data Mining


Universität Klagenfurt


Phd in Information Technology

Passed with destinction

Fachhochschule Kärnten


Master in Healthcare IT

Tishreen University


Bachelor in Mechatronics

Programming Languages

  • C++
  • C#
  • Matlab
  • Python
  • Java
  • Torch


EU Patent EP2790165


Quality determination in data acquisition

  • Truck Detection (Classification Task)
  • Over Detection (Classification Task)
  • Fault Rate Prediction (Time Series Forecast Task)
  • Java & Matlab

Tools And Platforms Skills


Machine Learning and Datascience

Python C# Matlab Lua
  • TensorFlow
  • Theano
  • Numpy
  • Accord.Net
  •  Statistics and machine learning toolbox
  • Neural network toolbox
  • Torch


Machine Vision

  • OpenCV (C++, Java, Python)
  • EmguCv (C#)
  • Matlab machine vision tools


Integrated development environment IDEs

  • MS Visual Studio
  • Xcode
  • Xamarin
  • Eclipse
  • Spyder
  • Jupyter notebook
  • PyCharm


Cloud Computing

  • Google Cloud Platform
  • Azure



  • MS Office
  • Latex
  • Adobe Indesign
  • Keynote


Game Design

  • Unity3d
  • Unreal
  • Pygame


Computer Graphics

  • Blender
  • Adobe Illustrator
  • SketchUp
  • Autodesk Inventor




Full Professional





AIS Innovationsscheck (FFG)

  • Human Emotion Recognition 
  • Classification 
  • Matlab & Python  & Tensorflow
  • Xamarin (C#)
  • Neural Networks

Local Prediction Integrationsunterst

  • Green traffic light duration prediction
  • Time series forecast
  • Java & Matlab
  • Neural Networks

Lokale Online Simulation

  • Neuro-Computing based traffic management 
  • Time series forecast
  • Matlab

RoSiT- Robust Sensors in Traffic

  • Truck Detection (Classification Task)
  • Over Detection (Classification Task)
  • Fault Rate Prediction (Time Series Forecast Task)
  • C# & Java & Matlab 


Transportation Research Part C


Soft Radial Basis Cellular Neural Network (SRB-CNN) based Robust Low-Cost Truck Detection using a Single Presence Detection Sensors

Status: Published

Abstract: This paper does present a comprehensive concept for a robust and reliable truck detection involving solely one single presence sensor (e.g. an inductive loop, but also any other presence sensor) at a signalized traffic junction. Hereby, two operations modes are distinguished: (a) during green traffic light phases, and (b) a much challenging case, during red traffic light phases. First, it is shown how difficult the underlying classification task is, this mainly due to strongly overlapped classes, which cannot be easily separated by simple hyper-planes. Then, a novel soft radial basis cellular neural/nonlinear network (SRB-CNN) based concept is developed, validated and extensively benchmarked with a selection of the best representatives of the current related state-of-the-art classification concepts (namely the following: support vector machines with radial basis function, artificial neural network, naive Bayes, and decision trees). For benchmarking purposes, all selected competing classifiers do use the same features and the superiority of the novel CNN based classifier is thereby underscored, as it strongly outperforms the other ones. This novel SRB-CNN based concept does satisfactorily fulfill the hard industrial requirements regarding robustness, low-cost, high processing speed, low memory consumption, and the capability to be deployed in low cost embedded systems.

IEEE Transactions on Instrumentation and Measurement


A Driver State Detection System-Combining a Capacitive Hand Detection Sensor with Physiological Sensors

Status: Accepted

Abstract: A driver state detection system based on Cellular Neural Networks to monitor the stress level of a driver is presented to evaluate a capacitive based wireless hands on/off and position detection sensor for a steering wheel. The ink-jet printed sensor mats are attached underneath the surface of the steering wheel's rim. The driver state detection system incoporates the inputs of driver inherent and driving behavoir domain. A driving simulator platorm providing a realistic virtual traffic environement is utilized to conduct a study for the evaluation of the proposed concept. Each participant is driving in two different scenarios representing one of the two no-stress/stress driver states. A '3-fold' cross validation is applied to evaluate our concept. The division between training and testing data is done in a way that considers carefully the subject-dependency. Furthermore, the Cellular Neural Network approach is compared to other state of the art learning tequnices. The results show a significant improvement combining sensor inputs from both driver inherent and driving bahavoir domain, giving a total related detection accuracy of 92%. Furthermore, the study shows that in case of including the capacitive sensor hands on/off and position detection sensor, the accuracy increases by 10%. These findings indicate that adding a subject-independent sensor, like the proposed capacitive hands on/off and position detection sensor, improves the detection performance significantly.

Journal of Real-Time Image Processing


Real-Time Raindrop Detection based on Cellular Neural Networks for ADAS

Status: Published

Abstract: A core aspect of advanced driver assistance systems (ADAS) is to support the driver with information about the current environmental situation of the vehicle. Bad weather conditions such as rain might occlude regions of the windshield or a camera lens and therefore affect the visual perception. Hence, the automated detection of raindrops has a significant importance for video-based ADAS. The detection of raindrops is highly time critical since video pre-processing stages are required to improve the image quality and to provide their results in real-time. This paper presents an approach for real-time raindrops detection which is based on cellular neural networks (CNN) and support vector machines (SVM). The major idea is to prove the possibility of transforming the support vectors into CNN templates. The advantage of CNN is its ultra fast precessing on embedded platforms such as FPGAs and GPUs. The proposed approach is capable to detect raindrops that might negatively affect the vision of the driver. Different classification features were extracted to evaluate and compare the performance between the proposed approach and other approaches.

DOI: 10.1007/s11554-016-0569-z

IEEE Transactions on Neural Networks and Learning Systems


Online Self-Adaptive Cellular Neural Network Architecture for Robust Time-Series Forecast

Status: Under Review since 5 months

Abstract: This paper presents a novel online adaptive neuro- computing framework for a robust time-series forecast. The proposed framework does mimic the human minds biological two-thinking model. Our mind makes decisions/calculations using a two-connected system. A first system, System 1, the so-called the intuitive system, makes decisions based on our experience. A second system, System 2, the controller system, does control the decisions of System 1 by either modifying or trusting them. Similarly to the human mind’s two-systems model, this paper proposes an artificial framework consisting of two cellular neural network (CNN) systems. The first CNN processor does represent the intuitive system and we call it Intuitive-CNN. The Second CNN processor does represent the controller system, which is called Controller-CNN. Both are connected within a general framework that we name OSA-CNN. The proposed framework is extensively tested, validated and benchmarked with the best state-of-the-art related methods, while involving real field time- series data. Multiple scenarios are considered: traffic flow data extracted from the PeMs traffic database and the 111 time- series collected from the so-called NN3 competitions. The novel OSA-CNN concept does remarkably highly outperform the state- of-the-art competing methods regarding both performance and universality

ID: TNNLS-2016-P-6504


 Springer Verlag


CNN Based Subject-Independent Driver Emotion Recognition System Involving Physiological Signals for ADAS

Autonomous Systems: Developments and Trends

Springer Verlag


A Novel Real-Time Emotion Detection System for Advanced Driver Assistance Systems

Advanced Microsystems for Automotive Applications 2016

Conference Papers

Autonomous Systems


A Review of Object Classification for Video Surveillance Systems

Volume 835, Pages 197 - 208

Autonomous Systems


A Computerized Method to Diagnose Strabismus

Volume 835, Pages 209 - 220

Proceedings of the INDS


A Novel Real-Time EEG-Based Emotion Recognition System for Advanced Driver Assistance Systems (ADAS)

Pages 9 - 13

Autonomous Systems


Neurocomputing-based Matrix Inversion Involving Cellular Neural Networks: Black-box Training Concept

Volume 842, Pages 119 - 132

IFAC Proceedings Volumes


Origin Destination Estimator Based on Hidden Markov Models for Adaptive Traffic Control,

Volume 45, Issue 4, 2012, Pages 92-96

Nonlinear Dynamics and Synchronization (INDS)


A novel real-time emotion detection system from audio streams based on bayesian quadratic discriminate classifier for ADAS