Portfolio

About Me

Helo, I’m Tanmoy Sarkar Pias
I am a lecturer at University of Asia Pacific. I have completed my B.Sc. in Computer Science and Engineering from BUET.

personal information

Full Name: Tanmoy Sarkar Pias
D.o.b.: 30 Sep 1996
address: New paltan line, Azimpur, Dhaka-1205
e-mail: 1305055.tsp@ugrad.cse.buet.ac.bd
e-mail: tsr@uap-bd.edu
phone: +880 1757222240

Research Interest

Deep Learning & Machine Learning

IOT

Security

work experience

Oct 2018 - PRESENT

Lecturer

Computer Science and Engineering

University of Asia Pacific, Dhaka

Course Conducted

Pattern Recognition (CSE 437) [Fall 18]
Digital System Design (CSE 335) [Fall 18]
Digital System Design Lab (CSE 336) [Fall 18]
Object Oriented Programming II (CSE 309) [Spring 19]
Object Oriented Programming II lab (CSE 310) [Spring 19]
Object Oriented Programming II (CSE 309) [Fall 19]
Object Oriented Programming II lab (CSE 310) [Fall 19]
Software Development lab [Fall 19]

Jan 2018 - PRESENT

Co-Founder

All in one Platform

Online open platform for outsourcing products and services.

Feb 2017 - Mar 2018

Project Manager and Full Stack Developer (Part time)

Move the Chains

Develop client projects
Manage a developer team
Requirement analysis

Educational Background

June 2014 - Oct 2018

Bachelor of Science

Computer Science and Engineering

Bangladesh University of Engineering and Technology

Completed Core Courses

Artificial Intelligence [A+]
Artificial Intelligence Lab[A+]
Machine Learning [A+]
Machine Learning Lab [A+]
Computer Networks [A+]

Research

October 2018 - PRESENT

Working under the supervision of Professor Dr. A.K.M. Ashikur Rahman

Bangladesh University of Engineering and Technology

Gender and Age recognition from facial images (Current)
Emotion Recognition from facial expression

Jan 2018 - PRESENT

Joint research with faculty members

University of Asia Pacific

Human Activity Recognition using smart device sensors
Vehicle recognition using smart device sensors
Desk Activity Recognition using smart device sensors
Indoor localization using Wi-Fi signals

Feb 2017 - Mar 2018

Students

Group 1

Creating Robust Steganography tools

Group 2

License Plate Recognition (for Bangladeshi vehicles)

Publications

Published in ICMLA, 2018:

Ananya Bhattacharjee, Tanmoy Sarkar Pias, Mahathir Ahmad, and Ashikur Rahman, “On the Performance Analysis of APIs Recognizing Emotions from Video Images of Facial Expressions" , IEEE 17th International Conference on Machine Learning and Applications (ICMLA) 2018, USA.

Abstract
This work is meant to provide insights towards state-of-the-art Application Programming Interfaces (APIs) commercially available today for recognizing emotions from video footprint of facial expressions. We analyze and compare performance of four such integrable commercial APIs using standard Extended Cohn-Kanade Dataset (CK+) containing over 10; 000 images with facial emotions and some randomly collected real life images. We also discuss issues to understand their limitations and adaptation as well as enhancement strategies. For performance analysis, we introduce the performance metric moving average to find the primary expression in the displayed emotion of a video sequence. Finally, using the popular valence-arousal dimensions, we show how to (lexicographically) order six basic emotions anger, happiness, sadness, surprise, fear and disgust. By providing neutral performance comparison, we hope to fill the existing notable gap between researchers, solution providers and application developers working on emotion based user modeling.

Some figures

Under Review:

Tanmoy Sarkar Pias, Muhammad Aminul Islam, Md. Al-Amin Khan Riad, Zarif Khan Mojlish, David Eisenberg, “Performance Analysis of Steganography Tools”, 6th International Conference on Networking, Systems and Security, 2019, BUET, Bangladesh.

Abstract
Steganography is the art of hiding secret data in a medium. The medium is an image, video, or an audio file, which is intended to raise no suspicion. Steganography tools typically use generate an identical cover image to conceal secret data that lies in the original medium image. In this paper, we use compare popular steganography tools designed with different embedding algorithms. We will first hypothetically input a set of cover and secret images, and then consider the resulting output images. Implications for future research and software development for the enhancing steganography tools are discussed

Some figures