KMA Solaiman
Assistant Teaching Professor
Computer Science & Electrical Engineering
University of Maryland, Baltimore County

Director
H.A.R.M.O.N.I. Lab

Affiliate Faculty
UMBC Center for AI

Posts by Collection

projects

publications

  • Minimal Parameter Clustering of Complex Shaped & Different Sized Dataset with Noise & Outlier Handling (MPCACS) [PDF]
    K. M. A. Solaiman, Ahmed Al Muzaddid
    Bangladesh University of Engineering & Technology (BUET) 2014

  • Multimodal Data Management in Open-world Environment [URL] [PDF]
    KMA Solaiman
    Purdue University 2023

  • AVRA Bangladesh collection, analysis & visualization of road accident data in Bangladesh [URL] [PDF]
    K. M. A. Solaiman, Md. Mustafizur Rahman, Nashid Shahriar
    ICIEV 2013

  • Minimal Parameter Clustering of Complex Shape Dataset with High Dimensional Dataset Compatibility (MPCACS) [URL] [Poster]
    Ahmed Al Muzaddid, KMA Solaiman
    BUET Thesis Poster Presentation 2014

  • Multi-modal Information Retrieval via Joint Embedding [URL] [Poster]
    KMA Solaiman and Bharat Bhargava
    NGC TechFest 2019

  • SKOD: A Framework for Situational Knowledge on Demand [URL] [PDF] [Video] [Presentation]
    Servio Palacios*, KMA Solaiman*, Pelin Angin, Alina Nesen, Bharat Bhargava, Zachary Collins, Aaron Sipser, Michael Stonebraker, and James Macdonald
    POLY@VLDB 2019

  • Surveillance Video Querying With A Human-in-the-Loop [PDF] [Video]
    Michael Stonebraker, Bharat Bhargava, Michael Cafarella, Zachary Collins, Jenna McClellan, Aaron Sipser, Tao Sun, Alina Nesen, KMA Solaiman, Ganapathy Mani, Kevin Kochpatcharin, Pelin Angin, and James MacDonald
    HILDA@SIGMOD 2020

  • Dataset Augmentation with Generated Novelties [URL] [PDF]
    Alina Nesen, K.M.A. Solaiman, and Bharat Bhargava
    TransAI 2021

  • Measurement of Novelty Difficulty in Monopoly [PDF]
    KMA Solaiman and Bharat Bhargava
    AAAI Spring Symposium 2022

  • Open-Learning Framework for Multi-modal Information Retrieval with Weakly Supervised Joint Embedding [PDF]
    KMA Solaiman and Bharat Bhargava
    AAAI Spring Symposium 2022

  • Applying Machine Learning and Data Fusion to the “Missing Person” Problem [URL] [PDF] [Video]
    K.M.A. Solaiman, Tao Sun, Alina Nesen, Bharat Bhargava, Michael Stonebraker
    IEEE Computer 2022

  • Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision [PDF] [Previous Version]
    K.M.A. Solaiman* and Bharat Bhargava
    Submitted to ICDE 2024 ; SIGMOD'23

  • NovASGrid: Novelty-Aware Smart-Grid Resilience
    KMA Solaiman
    Peer-reviewed and accepted at ICDM-ARRL 2025 (subsequently withdrawn prior to publication)

  • BoardVision: Deployment-ready and Robust Motherboard Defect Detection with Ensemble [PDF] [Poster]
    Brandon Hill, KMA Solaiman
    Peer-reviewed at WACV Applications Track 2026 ; Presented at UMBC CSEE Research Day 2025

  • BiasLab: Toward Explainable Political Bias Detection with Dual-Axis Annotations and Rationale Indicators [URL] [PDF] [Poster]
    KMA Solaiman
    Peer reviewed, Accepted and Presented at ICML MoFA 2025

  • TRIAGE-M: Triage from MIMIC — Emergency Triage Benchmark bridging Hospital-Rich and MCI-Like Field Simulation [URL] [PDF] [OpenReview]
    Joshua Sebastian, Karma Tobden, and KMA Solaiman
    Peer-reviewed at NeurIPS GenAI4Health 2025

  • Pre-Deployment Complexity Estimation for Federated Perception Systems [URL] [PDF]
    KMA Solaiman*, Shafkat Islam*, Ruy De Oliveira, Bharat Bhargava
    Under Review at Edge AI 2026

    • research

    talks

    SKOD: A Framework for Situational Knowledge on Demand

    Presented at Poly’19: Towards Polystores that manage multiple Databases, Privacy, Security and/or Policy Issues for Heterogenous Data, Co-located with VLDB 2019 - 45th International Conference on Very Large Data Bases

    Guest Lecture @ Introduction to Database Systems: CS448

    CS 448 Project 3: Relational Operators The goal of this project is to implement Relational Algebra Operators using the Iterator interface inside a working database system. This project is based on Minibase, a small relational DBMS, structured in several layers.