Hi, I'm Zeeshan Haider, an AI Researcher from Prince Sultan University. 

You Can Find More About Me At Link  

Data Augmentation and Optimizer Tuning for Polyp Segmentation

This work is done as an outcome of seed project at ASSCL Lab Prince Sultan University, Riyadh, Saudi Arabia.

Automatic segmentation of polyps is a very challenging problem in the scope of medical imaging. This challenge is often faced due to a lack of quality datasets. In this research, we explore the effect on the accuracy of colorectal cancer polyp segmentation due to augmentation and various optimizers while training the segmentation model. The effect of augmentation and optimizers on the polyp segmentation is studied separately. The augmentation effect is observed by changing the percentage of augmentation in each experiment whereas the optimizer effect is studied by changing the optimizer for each experiment. The experiments are performed with 8 optimizers and 10 different augmentation strategies.

Paper is accepted in ICCAD 2024 conference Paris France

Exploring Reinforcement Learning Techniques in the Realm of Mobile Robotics

This work is done as an outcome of a research project at ASSCL Lab Prince Sultan University, Riyadh, Saudi Arabia.

Mobile robots are intelligent machines that can move and perform tasks in different environments. They have gained massive popularity across a variety of applications, including healthcare, agriculture, hospitality, exploration, surveillance, transportation, entertainment, and even military deployments. The key factor enabling the autonomy of mobile robots lies in the reliability, safety, and robustness of their navigation systems, without the need for human intervention. Achieving such a high level of autonomy has required extensive research and development efforts, encompassing both classical approaches and the latest advancements in artificial intelligence (AI) techniques. This review paper specifically focuses on the deep reinforcement learning (DRL) techniques employed for mobile robots. It provides a comprehensive look into the most significant DRL-based navigation and control algorithms for mobile robots. Sub-components of mobile robot navigation perception, mapping, localization, and motion planning are well delineated under the lens of DRL and conventional methods. Furthermore, a detailed analysis of the challenges and limitations of DRL algorithms is brought under discussion. This review paper emphasizes the growing importance of DRL methods in the realm of mobile robots and the significance of autonomy in their operations. It also acknowledges the need for further research to address the challenges and limitations associated with deploying mobile robots in real-world applications.

A journal paper is accepted in IJAAC Inderscience journal 

Recruiter Assistant Tool using AI

• While working at QLU I built a LinkedIn recruiter assistant prospect/candidates recommender using NLP..

• Trained NLP models using millions of job descriptions and LinkedIn profiles.

• Assigned specific scores to each profile so that we can sort found candidates based on these scores and only choose the candidates with the best scores.

• These scores are:

Skills score, Education score, Title score, Experience score, Speciality score

Project Link 

Text Based Conversation Analytics System

• While working at Listenforce build a system to extract useful information and indicators from conversations between sales representatives/customer care agents and customers.

• The purpose of this project was to automate the process of extraction of useful information from calls like email, phone number, address, etc.

• The second objective of this project was to identify useful indicators from calls like sales agent is polite, asks info properly, etc. to assess the performance of sales agents and customer care personnel.

Project Link 

AI based defects detection on sawn timber

• This project is done with the Swedish firm Rosenvision as a freelancing contract.

• The main purpose of this project is to spot defective wood logs using an image of wood so that this defective wood is automatically separated from the conveyor belt.

Project Link 

Tabular data extraction from financial documents

• While working at Auditxprt, I worked on a project to automatically extract tabular data from financial documents so that this tabular data is properly stored in Excel sheets for further processing.

Project Link