Hybrid
Key accomplishments
- Developed advanced AI algorithms for crowd count and location popularity insights using wireless signals, achieving 95% accuracy in traffic flow measurement models.
- Implemented backend systems with Django and REST API, resulting in a 50% decrease in deployment time and a 30% reduction in operational costs.
- Managed and restructured PostgreSQL databases, leading to a 20% improvement in database efficiency and enhanced scalability.
- Developed comprehensive Grafana dashboards, resulting in a 60% increase in overall user satisfaction and system performance.
- Trained and deployed ML models for emotional classification based on brain signals, achieving 90% accuracy.
- Applied left- and right-hand posture recognition modules using TensorFlow and scikit-learn.
- Published research papers on smart glove and hand gesture-based control interfaces for multi-rotor aerial vehicles in prestigious IEEE journals and conferences.
Role 1
Data scientist
Role 2
Ai data analyst
B2b software and services
Any
Senior
Canada
Any
NA
Education
-
January 1 2018 - December 16 2020
Concordia University, Canada
Masters of Electrical and Electronics Engineering
Activities and societies: AI algorithm developing,researchingActivities and societies: AI algorithm developing,researching Smart Glove and Hand Gesture-based Control Interface for Multi-Rotor Aerial Vehicles in a Multi-Subject Environment: Designing an adaptable closed-loop control system to recognize and classify right and left-hand postures concurrently with self- and human validation. Also, improving the classifier performance by placing hand recognition and background removal methods before posture classification. Identifying the main user among the others in a crowded environment with just one photo of his/her face and detecting the right/left-hand of the main user and then classifying its postures.
Experience
- May 6 2021 - December 22 2023
-
May 8 2019 - July 31 2019
Atek Monitoring & Control Solutions
Python AI Developer
-
August 16 2018 - November 12 2020
Saintrino Technologies inc
Python AI Developer
Portfolio
Languages
English,
Persian
Honors & awards
-
2020
Smart Glove and Hand Gesture-based Control Interface for Multi-Rotor Aerial Vehicles in a Multi-Subject Environment
This paper introduces an adaptable, human-computer interaction method for control of multi-rotor aerial vehicles in unsupervised, multi-subject environments. A region-based convolutional neural network (R-CNN) first detects subjects in a frame and their faces\' regions of interest (RoIs), which are then fed to a facial recognition module to search for the main user within the frame. The R-CNN model supplies the right-hand RoI of the main user to a convolutional neural network (CNN) that classifies the right-hand gesture. A motion processing unit (MPU) and four flex sensors are embedded in the smart glove of the left hand to produce both discrete and continuous signals. These discrete and continuous signals are generated based on the bending of left-hand fingers and the roll angle of the left hand and then fed to a support vector machine (SVM) to classify the left-hand gesture. Three validation layers have been implemented, including a human-based validation, classification validation, and system validation. The comprehensive experimental results validate the proposed algorithm.
-
2019
Got the 2nd place in a competition
Got the 2nd place for Designing the Best Machine Learning-Based Model for ABB hackaton competition.
-
2019
Smart Glove and Hand Gesture-based Control Interface For Multi-rotor Aerial Vehicles
This paper introduces an adaptable human-robot interface that uses two types of human-computer interactions: an image processing technique for a right-hand gesture recognition and a smart glove for left-hand commands. A fixed number of gestures is used for specific commands to the vehicle (takeoff, land, hover, etc.), while the smart glove is used for the vehicle motors control. A single shot multi-box detector (SSD) model is used for a hand detection. After removing the cluttered background, the region of interest (RoI) is fed to a convolutional neural network (CNN) for right-hand gesture recognition. We propose three concurrent validation layers including a human-based validation. The validation layers allow the system to adapt to various users including different skin colors and hand shapes. Four flex sensors and a motion processing unit (MPU) are used in the smart glove to measure the bending ratio of each finger and the roll angle of the left hand. These signals are used for a left-hand gesture recognition as well as generation of continuous control signals such as throttle and angle commands of the vehicle. Extensive experimental results are presented that validate the proposed control methods.