Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
projects
Hi5: 2D Hand Pose Estimation with Zero Human Annotation
We introduce Hi5, a large synthetic dataset and data synthesis pipeline for 2D hand pose estimation that requires no human annotation, enabling diverse and accurate model training with only consumer-grade hardware.
- Developed a data synthesis pipeline using high-fidelity 3D hand models, diverse genders and skin tones, and dynamic environments to generate realistic 2D hand images with automatic keypoint annotation.
- Constructed the Hi5 dataset comprising ~583,000 labeled images, produced in 48 hours on a single consumer computer with full pose annotations.
- Demonstrated that models trained on Hi5 perform competitively on real hand pose benchmarks and show robustness under occlusions and varied conditions.
- Illustrated cost-effective synthetic data generation as a viable alternative to expensive manual annotation, expanding accessibility for pose estimation research.
Longitudinal PD Symptom Monitoring
Building a remote monitoring framework that tracks digital severity trajectories over time and aligns them with clinical scores, medication states, and self-reported symptom burden.
- Monthly multimodal assessments via ROUTE-PD dataset (12-month repeated measurements)
- Predict digital severity trends and correlate with neurologist-rated UPDRS changes
- Model intra-individual progression using ranking, linear-mixed, and temporal regression methods
- Identify digital markers that reflect symptom fluctuations and medication effects between visits
PARK: Remote AI Screening for Parkinson’s Disease
We developed PARK, a multimodal AI-driven remote screening tool that identifies Parkinson’s disease from webcam-based recordings of speech, facial expression, and motor tasks. PARK was evaluated across three independent datasets spanning supervised and unsupervised settings, demonstrating strong classification performance and high usability in diverse populations.
- Leveraged short standardized tasks (speech, facial expression, finger tapping) captured via webcam and extracted clinically relevant features for multimodal analysis.
- Evaluated PARK on 1,865 participants (including 670 with PD) across multiple real-world cohorts, with AUROC between 0.85–0.87 and accuracy ~80–83% on held-out test sets.
- Demonstrated balanced performance across demographic subgroups (age, sex, ethnicity) and agreement with neurologist assessments on external validation subsets.
- Designed uncertainty-aware prediction mechanisms that withhold low-confidence outputs to support safe use in unsupervised, at-home deployment.
- Collected structured usability feedback showing high participant satisfaction and perceived utility in both supervised and home settings.
Video-Based PD Severity Prediction
Developing a model that predicts clinician-rated MDS-UPDRS Part III severity from task-based video recordings, enabling objective, at-home motor assessment.
- Extract multimodal digital biomarkers from finger-tapping, smile/facial movement, and speech tasks
- Predict continuous clinical severity scores using regression and multitask modeling
- Evaluate model reliability across medication states, PD stages, and demographic strata
- Integrate temporal consistency checks to prepare for longitudinal deployment
AI-Enabled Parkinson’s Disease Screening Using Smile Videos
We developed an AI-based screening framework that detects Parkinson’s disease from brief smile videos captured on a smartphone or webcam, demonstrating high accuracy and broad applicability, including in diverse population samples.
- Collected one of the largest annotated smile–video datasets to date, involving participants with and without PD from multiple settings.
- Extracted facial landmarks and motion features indicative of hypomimia (reduced facial expressivity), a hallmark PD motor symptom.
- Trained and validated machine learning models achieving ≈88% accuracy for distinguishing PD from non-PD using only smile videos.
- Demonstrated generalizability in external validation cohorts, including clinical and international datasets.
- Showed the approach is scalable and accessible, enabling remote, low-cost initial screening that could complement traditional clinical evaluations and improve early detection access.
Semi-Supervised Speech Embedding Fusion for Parkinson’s Detection
We developed a novel fusion architecture that combines semi-supervised speech embeddings to detect Parkinson’s Disease (PD) using natural speech recordings collected from over 1,300 participants in both home and clinical environments.
- Leveraged deep speech embeddings (Wav2Vec 2.0, WavLM, ImageBind) to capture rich vocal features indicative of PD, moving beyond traditional handcrafted features.
- Designed a fusion model that projects and aligns multi-model speech embeddings into a unified feature space, improving classification performance relative to baseline approaches.
- Achieved high classification accuracy (AUROC ≈ 88.9%, accuracy ≈ 85.7%) on internal evaluation and demonstrated generalizability on external clinical datasets.
- Conducted detailed bias and robustness analyses showing equitable performance across sex, ethnicity, and disease stages, supporting broader real-world applicability.
Accessible, At-Home PD Detection via Multi-Task Video Analysis (UFNet)
We developed UFNet, an uncertainty-calibrated multimodal fusion network that detects Parkinson’s disease from at-home webcam tasks (finger tapping, smiling, and speech), using only a computer with a camera, microphone, and internet connection. The work introduces the first large-scale, multi-task PD video dataset and shows that fusing task-specific models with uncertainty-aware attention improves both performance and safety for remote screening.
- Collected a multi-task video dataset of 845 participants (272 with PD) performing three standardized tasks (finger-tapping, smile, and pangram speech), yielding 1,102 complete multi-task sessions and 3,306 total videos for model development and evaluation.
- Built task-specific shallow neural networks with Monte Carlo (MC) dropout for each modality, extracting clinically motivated features (finger-tapping kinematics, facial action/motion features, and WavLM speech embeddings) and estimating prediction uncertainty.
- Proposed UFNet, which projects task-specific features into a shared space and uses uncertainty-calibrated self-attention to down-weight noisier or less reliable tasks while leveraging complementary information across modalities.
- Demonstrated that UFNet outperforms single-task models and standard multimodal fusion baselines, achieving around 87–88% accuracy and ~93% AUROC on a subject-separated test set, with further gains when withholding low-confidence predictions.
- Incorporated confidence-aware decision policies (MC dropout, conformal prediction, and calibration techniques) to selectively abstain on uncertain cases, improving calibration and reducing harmful mispredictions in a screening context.
- Showed no significant performance bias across sex and race, and best performance for individuals aged 50–80, while also validating the approach on the external YouTubePD dataset to test robustness across different video sources.
User-Centered Framework for Empowering People with Parkinson’s Disease
We developed and evaluated a user-centered teleneurology platform designed to empower individuals with Parkinson’s Disease (PD) by offering remote access to screening tasks, educational resources, and responsive interfaces.
- Designed a web-accessible PD support system integrating speech, motor, and facial mimicry tasks for remote interaction and self-exploration.
- Incorporated interactive components such as a GPT-driven chatbot, local neurologist finder, and actionable PD prevention/management resources.
- Conducted a user validation study with 91 participants (including people with and without PD) to assess usability and experience.
- Achieved above-average usability outcomes and positive feedback, informing iterative improvements and future remote PD care research.
Personalized LLM Assistant for PD Management
Designing a preference-aligned LLM assistant that contextualizes digital severity trends, medication states, and lifestyle factors to support continuous, individualized PD care.
- Generates structured clinical summaries grounded in digital biomarkers and user context
- Tracks severity in relation to medication timing, therapy engagement, and daily variability
- Employs prompt engineering, personalization via RLHF, and safety-aligned response routing
- Conducts simulated and real user studies to evaluate trust, clarity, grounding, and safety
TallnWide: Fast, Scalable and Geo-Distributed PCA for Big Data Analytics
We introduce TallnWide, a novel algorithm for performing Principal Component Analysis (PCA) on extremely large, high-dimensional datasets that are distributed across geographic locations, addressing both scalability and communication overhead in big data analytics.
- PCA is widely used for dimensionality reduction but faces scalability issues when both rows and columns grow large; existing methods can suffer from memory overflow and high communication cost in distributed environments.
- TallnWide leverages a zero-noise-limit Probabilistic PCA model with a block-division strategy to manage tall and wide data efficiently, suppressing intermediate data explosion.
- The algorithm introduces communication-efficient coordination among geographically distributed datacenters by transmitting only necessary parameters and minimizing idle computation time.
- Empirical evaluation on real large-scale datasets shows TallnWide handles significantly higher dimensions (10× larger) and achieves up to 2.9× faster runtime compared to conventional approaches in geo-distributed settings.
- For reproducibility and future extension, TallnWide’s implementation is available as open-source, enabling further research in scalable dimension reduction on distributed data.
UACD: User Attributed Core Decomposition for Influential Spreaders
We propose User Attributed Core Decomposition (UACD), a novel graph analytic method that identifies the most influential spreaders in large social networks by combining network topology with rich user-specific information (followers, friends, tweet counts, verified status) in a distributed setting. UACD significantly improves accuracy and scalability over existing local and global centrality measures by incorporating both structural and user attributes.
- Introduced UACN (User Attributed Core Number), a measure that augments traditional k-core decomposition with user features to better capture real influence potential.
- Designed UACD to use only local neighborhood information, avoiding the prohibitive memory/runtime costs of global centrality measures on massive graphs.
- Provided a distributed implementation of the algorithm on AWS EC2, demonstrating scalability to networks with tens of millions of nodes.
- Empirically evaluated UACD against state-of-the-art spreader identification methods using standard metrics (e.g., Kendall τ, Spearman ρ, modified Jaccard similarity), showing ~12.5% higher accuracy on average.
- Achieved up to 175× faster runtime than global centrality approaches while maintaining high ranking quality across real Twitter datasets.
publications
Fast, Scalable and Geo-Distributed PCA for Big Data Analytics
Published in Information Systems, 2021
We propose TallnWide, a fast, scalable geo-distributed principal component analysis (PCA) algorithm that efficiently computes PCA on extremely high-dimensional data without intermediate memory overflow by dividing blocks of data and minimizing communication overhead. The method handles $\mathbf{10\times}$ higher dimensionality with $\mathbf{2.9\times}$ less time compared to baselines, enabling practical deployment in distributed big data settings.
Recommended citation: Adnan TMT, Tanjim MM, Adnan MA. Fast, Scalable and Geo-Distributed PCA for Big Data Analytics. Information Systems. 2021;98:101710.
Download Paper
UACD: A Local Approach for Identifying the Most Influential Spreaders in Twitter in a Distributed Environment
Published in Social Network Analysis and Mining, 2022
We propose UACD, a novel method for identifying the most influential spreaders in large social networks by combining user-specific attributes with topological structure. Unlike traditional global centrality methods, UACD uses only local node information and offers scalability to large graphs while maintaining superior ranking performance. A distributed implementation on Amazon EC2 shows that UACD is on average $\mathbf{12.5\%}$ more accurate and $\mathbf{175\times}$ faster than state-of-the-art alternatives for influence ranking on large Twitter datasets.
Recommended citation: Adnan, T.T., Islam, M.S., Papon, T.I., Nath, S. and Adnan, M.A., 2022. Uacd: a local approach for identifying the most influential spreaders in twitter in a distributed environment. Social Network Analysis and Mining, 12(1), p.37.
Download Paper
A user-centered framework to empower people with parkinson’s disease
Published in IMWUT, 2024
This study evaluated user reactions to AI-driven PD screening results and communication strategies in unsupervised home settings. The findings highlight design considerations that enhance user autonomy and trust, informing future deployments of remote PD screening tools.
Recommended citation: Rahman, W., Abdelkader, A., Lee, S., Yang, P., Islam, M.S., Adnan, T., Hasan, M., Wagner, E., Park, S., Dorsey, E.R. and Schwartz, C., 2024. A user-centered framework to empower people with parkinson's disease. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 7(4), pp.1-29.
Download Paper
Hi5: 2D Hand Pose Estimation with Zero Human Annotation
Published in ACII, 2025
We introduce Hi5, a synthetic hand pose estimation dataset of $\mathbf{583,000}$ images generated without human annotation, leveraging high-fidelity 3D hand models with diverse genders and skin tones, dynamic environments, and consumer-grade rendering. The data synthesis pipeline precisely controls pose diversity and representation, enabling robust model training. Models trained on Hi5 outperform real-data baselines on occluded and perturbed real benchmarks, demonstrating synthetic data’s potential for scalable hand pose estimation.
Recommended citation: Hasan, M., Ozel, C., Long, N., Martin, A., Potter, S., Adnan, T., Lee, S., Zadeh, A. and Hoque, E., 2024. Hi5: 2D Hand Pose Estimation with Zero Human Annotation. arXiv preprint arXiv:2406.03599.
Download Paper
Accessible, at-home detection of Parkinson’s disease via multi-task video analysis
Published in AAAI, 2025
We introduce a large-scale multi-task video dataset ($\mathbf{3,306}$ videos from $\mathbf{845}$ participants) and a novel fusion model, UFNet, for multimodal PD screening using webcam video. UFNet significantly outperformed single-task models in diagnostic accuracy (AUROC $\mathbf{\sim93\%}$), demonstrating scalable at-home detection.
Recommended citation: Islam, M.S., Adnan, T., Freyberg, J., Lee, S., Abdelkader, A., Pawlik, M., Schwartz, C., Jaffe, K., Schneider, R.B., Dorsey, R. and Hoque, E., 2025, April. Accessible, at-home detection of Parkinson’s disease via multi-task video analysis. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 27, pp. 28125-28133).
Download Paper
A novel fusion architecture for detecting Parkinson’s Disease using semi-supervised speech embeddings
Published in npj Parkinson’s Disease, 2025
This work introduces a speech-based Parkinson’s disease screening framework using English pangram utterances from $\mathbf{1,306}$ participants. By fusing semi-supervised Wav2Vec2 and ImageBind speech embeddings into a multimodal classifier, the model achieved $\mathbf{\sim89\%}$ AUROC and $\mathbf{\sim86\%}$ accuracy, with strong external robustness.
Recommended citation: Adnan, T., Abdelkader, A., Liu, Z., Hossain, E., Park, S., Islam, M.S. and Hoque, E., 2025. A novel fusion architecture for detecting Parkinson’s Disease using semi-supervised speech embeddings. npj Parkinson's Disease, 11(1), p.176.
Download Paper
AI-Enabled Parkinson’s Disease Screening Using Smile Videos
Published in NEJM AI, 2025
We developed a facial micro-expression analysis framework to distinguish Parkinson’s disease (PD) using short smile videos, achieving strong classification accuracy and generalizability across international cohorts. The model attained $\mathbf{\sim88\%}$ accuracy using only consumer-grade cameras, demonstrating the potential for remote and accessible PD screening.
Recommended citation: Adnan, T., Islam, M.S., Lee, S., Wasifur Rahman Chowdhury, E.M., Tithi, S.D., Noshin, K., Islam, M.R., Sarker, I., Rahman, M.S., Schneider, R.B. and Adams, J.L., 2025. AI-Enabled Parkinson’s Disease Screening Using Smile Videos. NEJM AI, 2(7), p.AIoa2400950.
Download Paper
Remote AI Screening for Parkinson’s Disease: A Multimodal, Cross-Setting Validation Study
Published in Preprint (PMC / AI Screening), 2025
PARK is a web-based artificial intelligence (AI) tool for remote screening of Parkinson’s disease (PD) using video and audio recordings collected via webcam, including speech, facial expressions, and motor tasks. The system was evaluated on $\mathbf{1,865}$ participants across diverse demographic groups and settings, including supervised clinical environments and unsupervised home use. PARK achieved consistent performance with accuracy ranging from $\mathbf{80.2\%–80.6\%}$ and AUROC between $\mathbf{0.85–0.87}$ on multiple independent test sets, and demonstrated high agreement with movement disorder specialists on held-out assessments. The model generalized well across age, sex, and ethnic subgroups, included uncertainty-aware predictions to support safe use in unsupervised environments, and showed favorable usability and participant satisfaction, highlighting its potential as an accessible, scalable tool for remote PD screening.
Recommended citation: Islam, M.S., Adnan, T., Abdelkader, A., Liu, Z., Ma, E., Park, S., Azad, A., Liu, P., Pawlik, M., Hartman, E. and Shelton, E., 2025. Remote AI Screening for Parkinson’s Disease: A Multimodal, Cross-Setting Validation Study. Research Square, pp.rs-3.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.