Shimul Paul
I am a Software Engineer and a Web developer. At present, I am studying for a Master's degree in High Integrity Systems at Frankfurt University of Applied Sciences, located in Germany. I am interested in research fields that include deep learning, machine learning, natural language processing, computer vision, and image captioning.

I worked on several Projects and participated in various challenges. My works are summarized here. To know me more, have a look at my profile.
Download Resume


Degrees I obtained


My expertise area

Web Development

React JS
Node JS

Programming Languages

Oracle (PL/SQL)

Developer Tools

VS Code
Jupyter Notebook/Colab
Code Blocks
Android Studio


What I achieved

Robo Soccer

CHAMPION in Robo Soccer Competition, Codeware19 (INTRA AUST ROBO SOCCER COMPETITION)

ISSUER: Department of CSE, Ahasanullah University of Science and Technology (AUST)

Programming Contest

CHAMPION in Programming Competition, Codeware19 (INTRA AUST PROGRAMMING CONTEST)

ISSUER: Department of CSE, Ahasanullah University of Science and Technology (AUST)

Hult Prize at AUST

Top 25 at Hult Prize at AUST

ISSUER: HULT Prize Committee

Banglalink Ennovators

Award was given in 2020 for achieving the position at top 100.

ISSUER: Banglalink Digital

Improving Deep Neural Networks

Educational, Specialization in Deep Neural Networks in the year 2020

ISSUER: Coursera

Technical Support Fundamentals

Educational, Specialization in Technical Support year 2020

ISSUER: Coursera

Sequences, Time Series and Prediction

Educational, Specialization in Sequences in the year 2020.

ISSUER: Coursera

Sequence Models

Educational, Specialization in Sequence Models in the year 2020.

ISSUER: Coursera

Complete Web Development

Professional Course on MERN stack.

ISSUER: Programming Hero

Job Experience

Jobs I did

Part-Time Lecturer

Duration: May 2022 - May 2023

A part-time Lecturer at
Ahsanullah University of Science and Technology

Web Developer

Duration: February 2022 - May 2022

A Web Developer at
Pran-Rfl Group

Software Engineer

Duration: November 2021 - February 2022

A Software Engineer at


Software Projects

Software Projects that I completed in University
(Click the image to view code in GitHub)

House, Rose, and Box Models
JavaScript API:WebGL

Here are some problems to make some design using the WebGL API.

Shop Management
Platform: PL/SQL of Oracle

In this project, two sites were made, one used my computer as the server and another was created using VMware. The site_link was run by the VMware site. Different tasks could be performed in these sites.

Information Pool System
Platform: ASP.NET framework of Visual Studio

The Information Pool System is an online-based website that showcase news from various sites in one place. It aims to be the one-stop destination for people seeking information about current events of the world as well as find classfields according to their requirements.
Language: PHP, Database: MySQL

This project '' is aimed at developing a web application that depicts online shopping of clothes and gift items and purchasing through 'Cash on Delivery' method only.This application involves most of the features of online shopping.

ZAS Restaurent Management System
Platform: Java Swing

This project(Restaurant billing management system) made with the help of java,mysql .In the system some specific users can log in and generate the bill only by providing the item's quantity and vat percentage. The bill can be printed as a token. Only the main admin can add or delete users by id from database by logging in. He /She can also add or delete food item from the database.

Bird Shooter ZAS
Platform: Visual Studio 10. Language: C++/Igraphics

This project(Shooting game) made with visual studio 10. the main page has 5 states, the 1st one starts the game. The objective of the 1st level of the game is to shoot the birds and collect points in a certain time and go to next level. In the 2nd level shooter has to shoot the birds and collect a certain points in certain time to win the game.The game will be over if the shooter loses all the lives by missing the targets and collecting life killing gems.In both the levels shooter can collect life increasing gems also.

Hardware Projects

Hardware Projects that I completed in University

A Quadcopter was built with a flight controller, brushless motors, camera and a Raspberry pi for wirelessly transmitting the image from the camera. It is capable of lifting a small amount of weight as well as fly autonomously.
Remote Control Robot
A Remote Control Robot consisting of four dc motors was made to participate in Robo Soccer competitions.

Job Projects

The projects I completed at jobs are shown here

Product, Employee, Delivery Management
Platform: Laravel
Mobile Shop Management Software
Platform: Laravel
OJOFB: A Facebook Page Manager
Platform: Laravel
Electroland: An Electronics Shop Management Software
Platform: Laravel
WhatsOn Plus: Social Media
Platform: Smarty Framework and PHP

Pet Projects

The projects I completed at my own are shown here

Doctor's Portal
Users can take appointments after login and also able to pay through stripe payment gateway cards.Users can see all of his/her appointment by date wise after login to his/her dashboard.Admin can add doctor and make admin to another person.Developed with ReactJS, NodeJs and MongoDB.
Baby Toy Shop
Users are able to checkout by login using Gmail/Email and Password. Users are able to see all of his/her orders in his/her panel.Also, users can cancel orders from his/her end if their status is pending. Admin can manage all products and status of orders. Developed with ReactJS, NodeJs and MongoDB.
Travel Go
Header and footer section is shared for all Any one can login with his/her gmail id and book and see the booking information For booking any service users need to login using Gmail. Admin manages all bookings. Admin can update booking status. Developed with ReactJS, NodeJs and MongoDB.

Areas of Research


The approches utilized by my research teammates and I

A Hybridized Deep Learning Method for Bengali Image Captioning

Researchgate: Hybridized Deep Learning Method for Bengali Image Captioning

An omnipresent challenging research topic in computer vision is the generation of captions from an input image. Previously, numerous experiments have been conducted on image captioning in English but the generation of the caption from the image in Bengali is still sparse and in need of more refining. Only a few papers untill now have worked on image captioning in Bengali. Hence, we proffer a standard strategy for Bengali image caption generation on two different sizes of the Flickr8k dataset and BanglaLekha dataset which is the only publicly available Bengali dataset for image captioning. Afterward, the Bengali captions of our model were compared with Bengali captions generated by other researchers using different architectures. Additionally, we employed a hybrid approach based on InceptionResnetV2 or Xception as Convolution Neural Network and Bidirectional Long Short-Term Memory or Bidirectional Gated Recurrent Unit on two Bengali datasets. Furthermore, a different combination of word embedding was also adapted. Lastly, the performance was evaluated using Bilingual Evaluation Understudy and proved that the proposed model indeed performed better for the Bengali dataset consisting of 4000 images and the BanglaLekha dataset.

Bengali Image Captioning with Visual Attention

Researchgate: Image Captioning with Visual Attention

Attention based approaches has been manifested to be an effective method in image captioning. However, attention can be used on text called semantic attention or on image which in known as spatial attention. We chose to implement the latter as the main problem of image captioning is not being able to detect objects in image properly. In this work, we develop an approach which extracts features from images using two different convolutional neural network and combines the features with an attention model in order to generate caption with an RNN. We adapted Xception and InceptionV3 as our CNN and GRU as our RNN. Moreover, we Evaluated our proposed model on Flickr8k dataset translated into Bengali. So that captions can be generated in Bengali using visual attention.

Bornon: Bengali Image Captioning with Transformer-based Deep learning approach

Researchgate: Image Captioning with Visual Attention

Image captioning using Encoder-Decoder based approach where CNN is used as the Encoder and sequence generator like RNN as Decoder has proven to be very effective. However, this method has a drawback that is sequence data must be processed in order. The beginning of the sequence must be processed before the end. To solve this issue we utilized the transformer-based model to caption images in Bengali. Unlike other sequence models, the Transformer uses an attention mechanism that provides context for any position in the input sequence. For instance, if the input data is a natural language sentence, the transformer does not need to process the beginning of the sentence before the end. As a result, we utilized three different Bengali datasets to generate Bengali captions from images using the Transformer model. Additionally, we fine-tuned the number of heads and layers in the transformer of all three Bengali datasets. Finally, we compared the result of the transformer-based model with a visual attention-based approach to caption images in Bengali.

Automated Bengali abusive text classification: Using deep learning techniques

In recent years, the breakdown of most human causes that hampers a large number of people is verbal abuse. The most noticeable fact is that most of the verbal abuse is made online by people behind the screen. While this problem has occurred with growing modern technologies, a modern solution is needed to solve the drawback. The growing rate of abusive comments and hate speech online is rapidly increasing on a large scale, and manual reports and corrections cannot help this critical situation. This proposed model introduces automation of the hate speech filtering process through deep learning. This work uses only Bengali datasets to find the real classification, as many Bengali and English mixed research works are available in this field. Using the intelligent automated classification of text comments in a limited resource-constrained language (example: Bengali) is critical for several reasons. This proposed system classifies 'Personal Offensive Text', 'Geographical Offensive Text', 'Religious Offensive text', 'Crime Offensive Text', 'Entertainment, Sports, Meme Tiktok, and others'. By combining two large datasets for this research and employing Bengali BERT, the best feasible outcome has been achieved. This paper indicates the complete results of the combined two different datasets and classified into nine segments, while the proposed Bengali BERT models achieved the highest accuracy of 0.706 and a weighted f1 score of 0.705 in the identification and classification tasks.

Topic of Interest

Research Topics that interest me

Machine Learning
Deep Learning
Artificial Intelligence
Computer Vision
Natural Language Processing(NLP)
Human Computer Interaction


What I Researched on

Journal Publication

Mayeesha Humaira, Shimul Paul, Md Abidur Rahman Khan Jim, Amit Saha Ami, and Faisal Muhammad Shah, "A hybridized deep learning method for bengali image captioning." International Journal of Advanced Computer Science and Applications, volume 12, pages 698–707.The Science and Information Organization, 2021, doi: 10.14569/IJACSA.2021.0120287.

Faisal Muhammad Shah, Mayeesha Humaira, Md Abidur Rahman Khan Jim, Amit Saha Ami, and Shimul Paul , "Bornon: Bengali Image Captioning with Transformer-based Deep learning approach." SN Computer Science Journal, volume 3, Article number: 90, Springer, 2022, doi:

Faisal Muhammad Shah, Sajib Kumar Saha Joy, Farzad Ahmed, Tonmoy Hossain, Mayeesha Humaira, Amit Saha Ami, Shimul Paul, and Md Abidur Rahman Khan Jim, Sifat Ahmed, "A Comprehensive Survey of COVID-19 Detection Using Medical Images." SN Computer Science Journal, volume 2, number 6, pages 1--22, Springer, 2021, doi:

Conference Publication

Amit Saha Ami, Mayeesha Humaira, Md Abidur Rahman Khan Jim, Shimul Paul, and Faisal Muhammad Shah, "Bengali image captioning with visual attention." In 2020 23rd International Conference on Computer and Information Technology (ICCIT), pages 1–5, 2020, doi: 10.1109/ICCIT51783.2020.9392709.

Showni Rudra Titli, Shimul Paul "Automated Bengali abusive text classification: Using deep learning techniques" presented at International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems (ICAECIS-2023)

Contact Me

Phone: +4915219576061