Koushik Roy

I am currently working as a data analyst at NEXT Ventures. I process raw data generated by thousands of users of different products and platforms of NEXT Ventures and try to find critical information to guide business and management decisions. My job responsibility includes creating automation scripts and deploying analytics microservices to the cloud in order to automate reporting dashboards. Additionally, I apply machine learning for classification, regression, and forecasting problems.

I previously worked as a machine learning engineer at NybSys. I have undertaken a few projects in this role and gained valuable experiences from them. Before joining this position, I worked as a data scientist in the same company. Additionally, I am a part-time research engineer in the Visual Information Processing research lab at MIST.

Biography

I have completed my B.Sc. in Electrical, Electronic and Communication Engineering (EECE) from the Military Institute of Science and Technology (MIST), affiliated with Bangladesh University of Professionals (BUP), Dhaka, Bangladesh on January 2021. Download CV

Achievements and Other Credentials

2021   TensorFlow Developer Certificate | Awarded By: TensorFlow.Org(Google) [See Credential]

2019   1st Runner-up of IEEE Conference Project Presentation | Awarded By: ICEEICT

2018   Winner of National Power and Energy Hackathon | Awarded By: Ministry of Power, Energy and Mineral Resources (MPEMR)

2017   Recipient of Dean’s List Scholarship for Outstanding Academic Results | Awarded By: MIST

2017   Rank-52, MIST Undergraduate Admission Test, 2016, among 9,000 students

Email

rkoushikroy2@gmail.com

Address

House 15/16, Road 23
Mirpur Section 6/D
Dhaka North, Dhaka

Phone

+880 1623 994430

Expereience

Professional Experience

Jun 2022 - Present
[Full Time]
Data Analyst
NEXT Ventures
Job Responsibilities
  • Processing, analyzing, visualizing data, and creating dashboards.
  • Modularizing and automating data processing and reporting process.
  • Applying machine learning for classification, regression, and forecasting problems.
  • Tech Stack: R, Python, R Shiny Dashboard, AWS EC2 etc.
Apr 2022 - Jul 2022
[Full Time]
Machine Learning Engineer
NybSys Ltd.
Projects
  • Driver’s attention monitoring and alert system
  • Masked face detection and recognition for facial authentication based security system
  • Hand written digit sequence recognition for optical mark recognition (OMR).
  • Multi camera surveillance and monitoring solution for industrial usage.
  • Tech Stack: Python, PyTorch, TensorFlow, OpenCV, Pandas, NumPy, MediaPipe etc.
Sep 2021 - Mar 2022
[Full Time]
Data Scientist
NybSys Ltd.
Projects
  • Location-based efficient navigation-equipped web app for emergency responders
  • Mixed fidelity synthetic data generation by combining statistical parameters of both low-fi and hi-fi data.
  • Interactive web app for stock price prediction.
  • Tech Stack: Python, R, Shiny, Leaflet, Dplyr, AWS, revgeo, ggmap, osrm, geosphere etc.
Sep 2021 - Present
[Part Time]
Research Engineer
Visual Information Processing(VIP) Lab, MIST
Projects
  • Modelling Lips-State Detection Using CNN for Non-Verbal Communications.
  • A New DNN model for Automatic License Plate Detection and Recognition with Bengali OCR.
  • Cheating detection system for the online exam using time series anomaly detection.
  • Eliminating false positive in Automatic License Plate Detection and Recognition.

Internship

Dec 2019 - Jan 2020
Industrial Trainee
Grameenphone Ltd.
Tasks
  • Exploring the existing technologies of the telecommunication field and having hands-on experience.
  • Learning the necessary skills and background information in the telecommunication field.
  • Final presentation on the overall learning experience.
Jan 2020 - Feb 2020
Industrial Trainee
BDCOM Online Ltd.
Tasks
  • Learning the operations and responsibilities of the different positions within the company.
  • Learning necessary networking terminologies and working methods.
  • Learning how different organizations provide different services in Bangladesh's networking sector.

Organization

Jan 2020 - Dec 2020
Vice President Technical Activities
MIST Robotics Club (MRC)
Responsibilities
  • Mentored robotics enthusiasts on multiple projects’ construction and implementation.
  • Helped organizing the technical aspects of several national level robotics competitions.

Education

Undergraduate Education

Duration:   4 Years (Jan 2017 - Jan 2021)
Degree:   Bachelor of Science (B.Sc.)
Major:   Communication
CGPA:   3.64/4.00
Department:   Electrical, Electronic and Communication Engineering (EECE)
Faculty:   Electrical and Computer Engineering (ECE)
Institute:   Military Institute of Scienc and Technology (MIST)
University:   Bangladesh University of Professionals (BUP)

Skills

  • Programming Language: Python, R, SQL, Matlab, C, LaTeX
  • Deep Learning & Computer-vision Packages: Keras, TensorFlow, PyTorch, Scikit-Learn, Open-CV, Mediapipe, Dlib
  • Data Processing, Visualization & Deployment: Numpy, Pandas, Matplotlib, Seaborn, R Shiny, Leaflet, dplyr
  • Machine Learning: Regression, Classification, Convolutional Neural Network, Transfer Learning, Time Series
  • Robotics: Arduino, Raspberry Pi, PCB Designing, Sensors & Micro-controllers
  • Selected Certifications: TensorFlow Developer Certificate, Convolutional Neural Networks in TensorFlow, Crash Course on Python, Intro to Deep Learning
  • Other Skills: Web Scraping, Django, Flutter, Git, Web Development, Notion, MS Office

Research

Research Interests

My research interests and experiences are mostly in the machine learning and deep learning domain along with computer vision applications. I have done projects and have a keen interest in problems involving computer vision and human-computer interaction applications in robotics, object detection and tracking, time-series data analysis, and modeling, optical character recognition, and similar areas.

Current projects

  • Cheating detection system for the online exam using time series anomaly detection
  • Webcam based real-time American Sign Language(ASL) detection using deep learning
  • Face sentiment analysis using deep neural network
  • License plate detection and recognition for Bangladeshi LP dataset
  • Synthetic time series data generation
  • Driver's drowsyness detection and alert system

Past projects

  • A Robust Webcam-based Eye Gaze Estimation System for Human-Computer Interaction
  • Modelling Lips-State Detection Using CNN for Non-Verbal Communications
  • A Comprehensive Study on Different Machine Learning Techniques for Rainfall Forecasting
  • Real Time Hand Gesture Based User Friendly Human Computer Interaction System
  • Demand Forecasting in Smart Grid Using Long Short-Term Memory RNN
  • Mixed fidelity data generation by translation the characteristics of high fidelity data into low fidelity data
  • Recognition of spoken digits using statistical modeling
  • Admission test result calculation and processing automation dashboard
  • Interactive energrncy call management dashboard for law inforcement
  • Geographical data visualization web app with interative filtering with density map

Publications

Selected Publications

  • Chanda, D. & Roy, K. A Novel Approach on Facial Emotion Recognition using Landmark Distance Based Deep Neural Network in International Conference on Innovations in Science, Engineering and Technology (ICISET) [Under Review] (2022).
  • Onim, M. S. H., Nyeem, H. & Roy, K. BLPnet: A New DNN model for Automatic License Plate Detection with Bengali OCR in Journal: Array 15, 100244 (2022).
  • Roy, K. & Akif, M. A. H. Real Time Hand Gesture Based User Friendly Human Computer Interaction System in International Conference on Innovations in Science, Engineering and Technology (ICISET) 260–265 (2022). pdf
  • Roy, K. & Chanda, D. A Robust Webcam-based Eye Gaze Estimation System for Human-Computer Interaction in International Conference on Innovations in Science, Engineering and Technology (ICISET) 146–151 (2022). pdf
  • Ishmam, A., Hasan, M., Onim, M. S. H. & Roy, K. Modelling Lips-State Detection Using CNN for Non-Verbal Communications in The International Conference on 4th Industrial Revolution and Beyond (IC4IR) [Accepted] (2021). pdf
  • Roy, K., Ishmam, A. & Taher, K. A. Demand Forecasting in Smart Grid Using Long Short-Term Memory in 2021 International Conference on Automation, Control and Mechatronics for Industry 4.0 (ACMI) (2021), 1–5. pdf
  • Biswas, A. K., Roy, K. & Chakraborty, U. Investigation of a Four-element Textile Multiple Input Multiple Output Antenna for Ku-Band Applications in 2020 IEEE Region 10 Symposium (TENSYMP) (2020), 382–385. pdf

Contact