mehrdad-moradi Goto Github PK

followers: 14.0 following: 102.0 repos: 209.0 gists: 1.0

Name: Mehrdad Moradi

Type: User

Company: University of Antwerp

Bio: PhD on dependability analysis, robustness checking, validation, and verification technique for CPSs using model-based fault injection and ML.

Location: Antwerp, Belgium

Blog: https://www.linkedin.com/in/mehrdad-moradi/

Welcome to my page👋

I received my PhD from the University of Antwerp, Belgium. My research is concerned with dependability analysis, robustness checking, validation, and verification technique for Cyber-Physical Systems (CPS) using model-based fault-injection. My main focus is on the optimization of model-based fault-injection using a combination of machine learning and model-based techniques.

I am currently working on an Reinforcement Learning (RL)-based method to optimize fault-injcention. I am currently learning different machine learning approches that can be applied on black-box (FMI standard based model) and white-box (Simulink-based model) CPSs for dependability analysis.

Research interest

Dependability Analysis:
- Safety Assessment
- Fault-Injection
- Hazard Analysis
- Validation and Verification
Model-Based System Engineering
Machine Learning
Embedded System Design and Analysis
Electronic Design Automation (ASIC/FPGA)
Image Processing

Mehrdad Moradi's Projects

machine-learning-systems-design

A booklet on machine learning systems design with exercises

manim

Animation engine for explanatory math videos

matlab-carla-interface

matlab.jl

Calling MATLAB in Julia through MATLAB Engine

mbeddr.formal

FASTEN: FormAl SpecificaTion ENvironment - a set of DSLs to experiment with rigorous systems and safety engineering.

mdp-dp-rl

Markov Decision Processes, Dynamic Programming and Reinforcement Learning

mehrdad-moradi

meta-adversarial-training

Tensorflow implementation of Meta Adversarial Training for Adversarial Patch Attacks on Tiny ImageNet.

ml-design-patterns

Source code accompanying O'Reilly book: Machine Learning Design Patterns

ml-interviews-book

https://huyenchip.com/ml-interviews-book/

ml_cheatsheet

A 5-pages only Machine Learning cheatsheet focusing on the most popular algorithms under the hood

mobstr-dataset

The MobSTr dataset provides artifacts that demonstrate Model-based Safety Assurance and Traceability for a safety-critical automotive system.

modelicagym

Modelica models integration with Open AI Gym

modelicastandardlibrary

Free (standard conforming) library from the Modelica Association to model mechanical (1D/3D), electrical (analog, digital, machines), magnetic, thermal, fluid, control systems and hierarchical state machines. Also numerical functions and functions for strings, files and streams are included.