Maneesha Rani Saha
- PhD Fall'25 Aspirant || Fresh Graduate @ Dept. of CSE, BUET.
- Research Interest: ML System Security, Human Centered Security, Trustworthy AI and Cloud Computing .
- Recipient of Dean's List Scholarship for academic excellence.
About Me
đź‘‹ I'm Maneesha, a fresh graduate from Dept. of CSE, BUET. I'm interested to work in the fields of ML System Security, Human Centered Security, Trustworthy AI and Fog and Cloud Computing. My current career goal is to pursue a Ph.D. in my field of interest.
đź“ś I've co-authored 2 research papers on Emotion and Social Biases in LLM Responses for Bangla Language. Among these, one paper titled "An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Models" has been accepted in the 5th Workshop on Gender Bias in Natural Language Processing at ACL 2024!
đź“š My undergraduate thesis was on "Dependency and Priority Based Task Scheduling in Heterogeneous Computing Systems" under the supervision of Dr. Rezwana Reaz. In this work, we proposed a task scheduling algorithm that considers the dependencies and priorities of delay-sensitive IoT tasks to minimize the makespan of the system. We are currently working on submitting this work to a reputed conference or publish it in a journal.
🏆 In my undergraduate life at buet, I've regularly participated and won multiple competitions including BWCSE Project Showcasing 2023 and BUET CSE FEST Hackathon (API and Cloud Category) 2022. I have also been involved in various leadership roles in IEEE Computer Society BUET Student Branch Chapter and BUET Security Club. My responsibilities included organizing events, managing teams, and coordinating with other clubs and organizations of other universities.
🎡 In my leisure time, I enjoy reading thriller novels, listening to music and watching tv-series and movies.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "
News and Updates My Resume
Work Experience
-
MySoft Limited
Virtual InternMay 2023 - June 2023- Learned Data pre-processing, Multidimensional data modeling, Online Analytical Processing (OLAP), Aggregation, correlation, association, clustering, prediction on data and Data visualization by solving real-life problems using anonymous data.
Data pre-processing
Multidimensional data modeling
Online Analytical Processing (OLAP)
Data prediction
Data visualization
All Work Experience
Research & Publications
An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Models
Jayanta Sadhu (BUET), Maneesha Rani Saha, Dr. Rifat Shahriyar (Professor, BUET)
Abstract: The influence of Large Language Models (LLMs) is rapidly growing, automating more jobs over time. Assessing the fairness of LLMs is crucial due to their expanding impact. Studies reveal the reflection of societal norms and biases in LLMs, which creates a risk of propagating societal stereotypes in downstream tasks. Many studies on bias in LLMs focus on gender bias in various NLP applications. However, there's a gap in research on bias in emotional attributes, despite the close societal link between emotion and gender. This gap is even larger for low-resource languages like Bangla. Historically, women are associated with emotions like empathy, fear, and guilt, while men are linked to anger, bravado, and authority. This pattern reflects societal norms in Bangla-speaking regions. We offer the first thorough investigation of gendered emotion attribution in Bangla for both closed and open source LLMs in this work. Our aim is to elucidate the intricate societal relationship between gender and emotion specifically within the context of Bangla. We have been successful in showing the existence of gender bias in the context of emotions in Bangla through analytical methods and also show how emotion attribution changes on the basis of gendered role selection in LLMs. All of our resources including code and data are made publicly available to support future research on Bangla NLP.
Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias
Jayanta Sadhu (BUET), Maneesha Rani Saha, Dr. Rifat Shahriyar (Professor, BUET)
Abstract: The rapid growth of Large Language Models (LLMs) has put forward the study of biases as a crucial field. It is important to assess the influence of different types of biases embedded in LLMs to ensure fair use in sensitive fields. Although there have been extensive works on bias assessment in English, such efforts are rare and scarce for a major language like Bangla. In this work, we examine two types of social biases in LLM generated outputs for Bangla language. Our main contributions in this work are: (1) bias studies on two different social biases for Bangla (2) a curated dataset for bias measurement benchmarking (3) two different probing techniques for bias detection in the context of Bangla. This is the first work of such kind involving bias assessment of LLMs for Bangla to the best of our knowledge. All our code and resources are publicly available for the progress of bias related research in Bangla NLP.
Dependency, Deadline and Priority Based Multi‑Queue IoT Task Scheduling in Heterogeneous Systems
Muhammad Ehsanul Kader (BUET)*, Maneesha Rani Saha*, Dr. Rezwana Reaz (Asistant Professor, BUET) (* equal contribution)
Abstract: Internet of Things (IoT) has emerged as a transformative paradigm and revolutionized our way of engaging with technology in everyday life. The limited computing resources and storage capacity of IoT devices have necessitated the integration of heterogeneous fog resources in IoT task execution. Moreover, some IoT applications such as healthcare services are highly delay-sensitive; hence need immediate processing and response. On the other hand, the best utilization of heterogeneous storage and processing capacity of fog resources plays a pivotal role in improving the response time of IoT applications. Thus, an adaptive task scheduling algorithm for executing IoT tasks in fog environment is required which will consider the heterogeneity of available resources and various response time requirements of different IoT application. In this paper, we propose a non-preemptive batch task scheduling algorithm with dynamic resource allocation. The proposed method addresses the challenges of scheduling tasks with varying priority levels, deadline constraints, and dependencies utilizing the concepts of Directed Acyclic Graphs (DAGs), priority queues, and dynamic queue switching. We introduce a novel numerical scoring mechanism that prioritizes the executions of the tasks with higher urgency and critical dependencies. The major goals of the proposed technique are to reduce the overall average response time, makespan, and average deadline violation time; and increase the throughput. We have implemented our algorithm in a java based proprietary simulator. Our simulation results demonstrate that the proposed algorithm significantly improves the average response time, makespan, throughput, and deadline violation time compared to the existing priority based non-preemptive batch scheduling algorithms.
IoT
Task Scheduling
Fog Computing
Heterogeneous Systems
All Publications
Education
-
B.Sc. in Computer Science and Engineering
Bangladesh University of Engineering and TechnologyApril 2019 - July 2024CGPA: 3.78/4.00 -
H.S.C. in Science
Udayan Uchcha Madhyamik BidyalayaJune 2016 - July 2018GPA: 5.00/5.00
Technical Skills
-
Programming Languages
C C++ Java Python HTML/CSS JavaScript SQL -
Frameworks
Spring Boot NodeJS Bootstrap JQuery ReactJS -
DBMS
Oracle PostgreSQL MySql -
Security Tools
Autopsy Wireshark NMap Gophish -
Graphic Designing
Adobe Illustrator Adobe XD Figma Canva -
Miscellaneous
LATEX Firebase Git -
Soft Skills
Team management Problem‑solving Public Speaking Creative Writing