Melika Baghi

Projects

Research threads

Hospital capacity for medical tourists and local patients

Amirkabir University of Technology · paper under review at Health Care Management Science

Mean inpatient admission wait, same department and demand Hybrid model channel choice, doctor switching, abandonment, deterioration 14.8 days 42% lower, p < 0.001 Discrete-event only same flow, behaviours removed 25.8 days
With patient behaviour modelled, the mean inpatient admission wait is 14.8 days; the otherwise identical discrete-event-only model shows 25.8 days (30 and 36 replications, Welch t-test).
Problem
A multi-specialty international-patient department serves medical tourists alongside local patients, and how those patients behave (abandoning, switching doctors, choosing a channel) affects the queues.
Approach
A hybrid agent-based and discrete-event simulation in AnyLogic that models channel choice, physician switching, treatment abandonment and deterioration. A 256-run fractional factorial design screened 16 controllable factors across six performance measures, followed by a replicated comparison against an otherwise identical discrete-event-only model.
Result
Bed capacity is the most consistent driver of waiting; priority rules, channel design and appointment timing also matter. Leaving patient behaviour out changes the answer: the discrete-event-only model shows a 25.8-day admission wait against 14.8 days in the hybrid model (42% lower, p < 0.001).
Links
PaperCodeDOI

Healthcare operationsSimulationAnyLogicDesign of experiments

Constrained boosting for reduced-order models

Georgia Institute of Technology

valid unconstrained leaf value outside the valid region projected into both balls so the prediction is always usable enforced at every split, during fit not corrected afterwards
An unconstrained leaf value falls outside the valid region; cXGBoost projects it into the intersection of the balls during fitting.
Problem
Predicting a simulation's reduced basis at unseen parameters means regressing a point on a manifold, valid only inside a bounded region.
Approach
cXGBoost enforces that bound inside every leaf of the boosting ensemble rather than correcting afterwards, so predictions are valid by construction and no general-purpose optimiser is called at any split.
Result
Lower mean reconstruction error than the projected Gaussian process and Grassmann interpolation on four parametric problems (cylinder wake, Kolmogorov flow, the Kuramoto–Sivashinsky equation and a forced beam). Released as an open-source Python package.
Links
PaperCode

Gradient boostingManifold learningSurrogate modeling

Learning from delayed feedback

Georgia Institute of Technology

actions a₁ a₂ a₃ states s₁ s₂ delay d loss at s₁ credited to a₁ and a₂, the actions that reach s₁ price of pooling effective dimension vₜ set by how much actions overlap
Actions lead to states; a loss seen after a delay is credited back only to the actions that could have produced that state.
Problem
When an action's outcome only arrives after a delay, most algorithms wait or discard the signal.
Approach
State-EXP3 charges one delayed outcome to every action that could have produced it, and pays for that pooling with an effective dimension that reads the overlap between actions rather than counting them, so the cost tracks how much the actions actually share.
Result
Regret reduced by up to 79% versus action-level weighting and by 32–68% versus a rate-optimal action-only delayed-bandit baseline, with a lower bound showing the cost of delayed feedback cannot be eliminated by pooling.
Links
PaperCode

Sequential decision makingBanditsOnline learningDelayed feedback

Deciding when partial clinical evidence is enough

Georgia Institute of Technology

observed imaging labs notes genomics enough evidence? yes certify & act no abstain, acquire next coverage holds for every stopping pattern
From the observed modalities, either certify the prediction and act, or abstain and acquire the next modality.
Problem
Clinical models often have to act on incomplete inputs: imaging but no labs, notes but no genomics.
Approach
RouteCert certifies a prediction when the evidence already in hand determines the decision, and otherwise abstains and says which modality to acquire next. Acquisition is separated from calibration, so conformal coverage holds conditional on the terminal modality pattern rather than on average.
Result
Distribution-free coverage guarantees, evaluated on four datasets spanning ECG, speech and wearable sensing (PTB-XL, CMU-MOSEI, MHEALTH, IEMOCAP).
Links
PaperCode

Conformal predictionMultimodal learningMissing dataClinical decision support

Surrogates that keep the data's shape

Georgia Institute of Technology · submitted to the Journal of Computational Physics

simulation field space × space × time one subspace per mode U₁ U₂ U₃ core each mode interpolated on its own manifold cores aligned, then one low-rank surrogate vs flattening the field up to 482× smaller 3.3×–8.5× faster, same accuracy
Simulation output is multiway; instead of flattening it, each mode keeps its own subspace, interpolated separately, with cores aligned before fitting.
Problem
Simulation output is naturally multiway: space by space by time. The usual move is to flatten it into one long vector, which throws that structure away.
Approach
Every mode gets its own low-dimensional subspace, each interpolated on its own manifold, with the cores aligned before a single low-rank surrogate is fitted.
Result
Across five PDE benchmarks in two and three dimensions, including public CFD data, the interpolation size is 13× to 482× smaller and cached queries run 3.3× to 8.5× faster than a single-subspace surrogate built on the flattened field, with mean errors within 0.22 percentage points. In a 3D grid study at 64³ the size ratio reaches 2,260× and the speedup 11.9×.
Links
Paper

Tensor decompositionsSurrogate modelingRiemannian geometryScientific ML

Other projects

Additional projects