Md. Tareq Mahmood

Researcher | Grad Student | Educator

Email: tareq [at] cs [dot] wisc [dot] edu

About Me

Hi, Tareq here. I am a second year PhD student in the Computer Sciences Department at the University of Wisconsin-Madison. My research interests lie in the intersection of ML and systems. My current research focuses on building efficient distributed ML systems for large-scale GPU clusters.

Previously, I was a faculty member in the Computer Science and Engineering Department at the Bangladesh University of Engineering and Technology.

Research Papers

Md. Tareq Mahmood, Mohammed Eunus Ali, Muhammad Aamir Cheema, Syed Md. Mukit Rashid, and Timos Sellis

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2022) - CORE Rank A - Acceptance Rate 26%

Paper Link

PathOracle - A Deep Learning Based Trip Planner for Daily Commuters


learn-popular-trip

⮞ Details

In this paper, we propose a novel data-driven approach for a trip planner, that finds the most popular multi-modal trip using public transport from historical trips, given a source, a destination, and user-defined constraints such as time, minimum switches, or preferred modes of transport. To solve the most popular trip and its variants, we propose a multi-stage deep learning architecture, PathOracle, that consists of two major components: KSNet to generate key stops, and MPTNet to generate popular path trips from a source to a destination passing through the key stops. We also introduce a unique representation of stops using Stop2Vec that considers both the neighborhood and trip popularity between stops to facilitate accurate path planning. We present an extensive experimental study with a large real-world public transport based commuting Myki dataset of Melbourne city, and demonstrate the effectiveness of our proposed approaches.

Md. Tareq Mahmood and Mohammed Eunus Ali

Paper Link

Learning Indoor Layouts from Simple Point-Clouds


pointcloud-to-room

⮞ Details

Reconstructing a layout of indoor spaces has been a crucial part of growing indoor location based services. One of the key challenges in the proliferation of indoor location based services is the unavailability of indoor spatial maps due to the complex nature of capturing an indoor space model (e.g., floor plan) of an existing building. In this paper, we propose a system to automatically generate floor plans that can recognize rooms from the point-clouds obtained through smartphones like Google's Tango. In particular, we propose two approaches - a Recurrent Neural Network based approach using Pointer Network and a Convolutional Neural Network based approach using Mask-RCNN to identify rooms (and thereby floor plans) from point-clouds. Experimental results on different datasets demonstrate approximately 0.80-0.90 Intersection-over-Union scores, which show that our models can effectively identify the rooms and regenerate the shapes of the rooms in heterogeneous environment.

Fariha Tabassum Islam, Md. Tareq Mahmood and Mahmuda Naznin

International Conference on Networking, Systems and Security (NSysS 2022)

Paper Link

MTUL: A Novel Approach for Multi-Trajectory User Linking


MTUL

⮞ Details

Trajectory User Linking (TUL) is the problem of identifying the user (i.e., his identity) from the trajectories generated by him. Existing works on TUL leverage a single trajectory for identifying a user. We propose a novel problem called Multi-Trajectory User Linking (MTUL), which leverages all available trajectories generated by a particular user to identify him. Thus, MTUL is essentially the generalized TUL problem. This problem has significant applications in Location-Based Services (LBSs) such as personalized route planning and point-of-interests (POI) recommendation, movement anomaly detection, etc. We provide an end-to-end solution to the MTUL problem using sequence embedding and GRU and achieve reasonable accuracy by taking into account the POI type and region information. We consider this work to be an important addition to the TUL research.

Md. Mahmudul Hasan, Md. Rafid UI Islam, and Md. Tareq Mahmood

International Conference on Bangla Speech and Language Processing (ICBSLP 2018)

Paper Link

Recognition of Bengali Handwritten Digits Using Convolutional Neural Network Architectures


bangla-digit-recognition

⮞ Details

Handwritten digit recognition has been the “hello world” of deep learning. Yet, there are no significant work on Bengali handwritten digits due to a lack of benchmark dataset. NumtaDB is the largest dataset on Bengali handwritten digits and currently we have the best accuracy of 99.3359% on it. We used popular CNN architectures namely, ResNet34 and Resnet50. We preprocessed the data, used data augmentation, and trained our models with augmented data. We tested our models on both the raw test data and cleaned test data. We found that slightly underfitted models work better on the test data. And finally ensembled our six best models to get our final predictions. In this paper we describe some methods and techniques that performs well in NumtaDB dataset.

Experience

Faculty Member

October 2019 - August 2023 [On-leave]

Department of Computer Science and Engineering

Bangladesh University of Engineering and Technology

Research Assistant

November 2018 - September 2019

Data Science and Engineering Laboratory (DataLab@BUET)

http://datalab.buet.io

Education

Master of Science

December 2018 - October 2022

Computer Science and Engineering

Bangladesh University of Engineering and Technology

CGPA: 4.00 out of 4.00

Thesis: Deep Learning-based Approaches for Intelligent Trip Planning Using Public Transport

Bachelor of Science

July 2014 - October 2018

Computer Science and Engineering

Bangladesh University of Engineering and Technology

CGPA: 3.99 out of 4.00

Thesis: Learning Indoor Layouts from Simple Point-Clouds

Grants and Fellowships

  • Selected for High Profile ICT Scholar Fellowship 2018-19
  • Received ICT Innovation Fund 2018-19 (with Kazi Antor Hasan)

Awards and Honors

  • Runner Up Student Poster Award - NSysS, 2018
  • Best Student Paper Award - ICBSLP, 2018
  • Champion Team (BUET Backpropers), NumtaDB Computer Vision Challenge - Bengali.Ai, 2018
  • Best Kernel, NumtaDB Computer Vision Challenge - Bengali.Ai, 2018
  • Honourable Mentioned Team (BUET Backpropers), Machine Learning Challenge - National Robotic Festival, 2017
  • Champion Team (BUET Resonance) - Battle of Speed, LFR Challenge, 2015
  • 2nd Placed Team (BUET Novices) - Intra-BUET Programming Contest, 2015

News

  • [Aug 2023] Started as a Grad student at UW-Madison.
  • [Oct 2022] Defended my Master’s thesis. Thanks to my supervisors.
  • [Sep 2022] Attended ECML-PKDD 2022 in Grenoble, France. Met Yann LeCun!.
  • [Jun 2022] PathOracle accepted in ECML-PKDD 2022.

A Little More About Me

In my spare time, I like to try new frameworks, languages and linux distros. I love to build small apps/software/scripts for my own use.

My Erdős number is 4. Paul Erdős - Ronald L. Graham - Jeffrey D. Ullman - Timos K. Sellis - Me.