Hi! This is Fariha. I am a first year Ph.D. student at the University of Wisconsin-Madison in the department of Computer Sciences. Previously, I worked as a faculty at the Department of CSE in United International University. I have completed my Undergrad and Master’s in the Department of CSE, BUET.
[C1] A Privacy-Enhanced and Personalized Safe Route Planner with Crowdsourced Data and Computation
Fariha Tabassum Islam, Tanzima Hashem, Rifat Shahriyar
ICDE 2021 | Link | PDF
[C2] MTUL: A Novel Approach for Multi-Trajectory User Linking
Fariha Tabassum Islam*, Md. Tareq Mahmood*, Mahmuda Naznin
NSysS 2022 | Link
[J1] A Crowd-enabled Solution for Privacy-Preserving and Personalized Safe Route Planning for Fixed or Flexible Destinations
Fariha Tabassum Islam, Tanzima Hashem, Rifat Shahriyar
TKDE 2023 | Link | PDF
[J2] Representative Dissimilar Path Queries: Accomodating Human Movement Dynamics in Road Networks
Tanzima Hashem, Matt Duckham, Mahathir Monjur, Fariha Tabassum Islam
JOSIS 2023 | Link
Thesis: A Privacy-enhanced Approach for Planning Safe Routes with Crowdsourced Data and Computation
Thesis: An Efficient Approach for Real-Time Crowdsourced Package Delivery using Public Transport Networks
We introduce a novel safe route planning problem and develop an efficient solution to ensure the travelers' safety on roads. Our approach finds the safest routes within a user-specified distance threshold based on the personalized travel experience of the knowledgeable crowd without involving any centralized computation. Our algorithms for finding the safest route further enhance user privacy by minimizing the exposure of personalized safety scores with others. Our safe route planner can find the safest routes for individuals and groups by considering both a fixed and a set of flexible destination locations.
The popularity of e-commerce has caused the rise of crowdsourced package delivery. In this research, we introduce an efficient approach to find the package delivery route based on the available journey plans of passengers in public transport networks. Our approach allows package transfers between the public transport passengers and thereby increase the success rate of the crowdsourced package delivery.
This work identifies a user from his/her multiple available trajectories using GRU autoencoder.
This work introduces a representative dissimilar path (RDP) query and provides an efficient algorithm for finding a set of most dissimilar routes from sets of representative routes for different features.
In this project, we utilize smartphone cameras and sensors to screen various diseases for preliminary healthcare, especially considering underserved people.
In this project, we annotates a target genome using a closely related, well-annotated reference genome using ensemble of RATT, Glimmer and BLAST.
In this project, we detects credit card frauds using Siamese network.
