arXiv subjects

Yash Travadi

Publications and source records attributed to Yash Travadi.

5 recordsLinked to original sources

arXiv2026

A Systematic Evaluation of Imbalance Handling Methods in Biomedical Binary Classification

Objective: The primary goal of this study was to systematically examine the impact of commonly used imbalance handling methods (IHMs) on predictive performance in biomedical binary classification, considering the interplay between model complexity and diverse data modalities. Material and Methods: We evaluated five representative IHMs: random undersampling (RUS), random oversampling (ROS), SMOTE, re-weighting (RW), and direct F1-score optimization (DMO), against a raw training (RAW) baseline. The evaluation encompassed three public biomedical datasets: MIMIC-III (tabular), ADE-Corpus-V2 (text), and MURA (image), spanning three common biomedical data modalities. To assess varying model complexity, we employed a range of architectures, from classical logistic regression and random forest to deep neural networks, including multilayer perceptron (MLP), BiLSTM, BERT, DenseNet, and DINOv2. Results: For simpler models such as logistic regression on tabular data, IHMs yielded no significant advantage over the RAW baseline, aligning with prior findings. However, clear benefits were observed for more complex models and unstructured data: (a) ROS and RW consistently enhanced the performance of powerful models; (b) direct F1-score optimization demonstrated utility primarily for unstructured text and image data; and (c) RUS and SMOTE consistently degraded performance and are therefore not recommended. Conclusion: The effectiveness of IHMs depends on both model complexity and data modality. Performance gains are most pronounced when leveraging appropriate IHMs, such as ROS, RW, and DMO, on high-complexity models.

cs.LG↗

arXiv2025

Exact Reformulation and Optimization for Direct Metric Optimization in Binary Imbalanced Classification

For classification with imbalanced class frequencies, i.e., imbalanced classification (IC), standard accuracy is known to be misleading as a performance measure. While most existing methods for IC resort to optimizing balanced accuracy (i.e., the average of class-wise recalls), they fall short in scenarios where the significance of classes varies or certain metrics should reach prescribed levels. In this paper, we study two key classification metrics, precision and recall, under three practical binary IC settings: fix precision optimize recall (FPOR), fix recall optimize precision (FROP), and optimize $F_1$-score (OFOS). Unlike existing methods that rely on smooth approximations to deal with the indicator function involved, we introduce, for the first time, exact constrained reformulations for these direct metric optimization (DMO) problems, which can be effectively solved by exact penalty methods. Experiment results on multiple benchmark datasets demonstrate the practical superiority of our approach over the state-of-the-art methods for the three DMO problems. We also expect our exact reformulation and optimization (ERO) framework to be applicable to a wide range of DMO problems for binary IC and beyond. Our code is available at https://github.com/sun-umn/DMO.

cs.LG↗

arXiv2025

Circulating tumor cell detection in cancer patients using in-flow deep learning holography

Circulating tumor cells (CTCs) are cancer cells found in the bloodstream that serve as biomarkers for early cancer detection, prognostication, and disease monitoring. However, CTC detection remains challenging due to low cell abundance and heterogeneity. Digital holographic microscopy (DHM) offers a promising, label-free method for high-throughput CTC identification by capturing superior morphological information compared to traditional imaging methods, while remaining compatible with in-flow data acquisition. We present a streamlined DHM-based system that integrates microfluidic enrichment with deep learning-driven image analysis, supplemented by immunofluorescent profiling, to improve the sensitivity and specificity of CTC enumeration. Specifically, our platform combines inertial microfluidic preprocessing with dual-modality imaging, integrating holography with fluorescence sensing of up to two markers. A deep learning model, trained on a diverse set of healthy blood samples and cancer cell lines, and executed in real-time, provides a morphological confidence on a cell-by-cell basis that may then be combined with immunofluorescence criteria for enumeration. In a pilot study, we demonstrate significantly higher CTC counts in patients with late-stage prostate cancer (n=13) compared to healthy controls (n=8), with a patient-level false positive rate of 1 cell/mL. Notably, nearly two-thirds of identified CTCs were EpCAM-negative but PSMA positive (a prostate specific epithelial marker), suggesting that traditional use of EpCAM as an epithelial marker for CTCs may lead to false negatives. These findings highlight the potential of DHM for applications including but not limited to screening, diagnostics, and precision oncology.

physics.optics↗

arXiv2023

Welfare and Fairness Dynamics in Federated Learning: A Client Selection Perspective

Federated learning (FL) is a privacy-preserving learning technique that enables distributed computing devices to train shared learning models across data silos collaboratively. Existing FL works mostly focus on designing advanced FL algorithms to improve the model performance. However, the economic considerations of the clients, such as fairness and incentive, are yet to be fully explored. Without such considerations, self-motivated clients may lose interest and leave the federation. To address this problem, we designed a novel incentive mechanism that involves a client selection process to remove low-quality clients and a money transfer process to ensure a fair reward distribution. Our experimental results strongly demonstrate that the proposed incentive mechanism can effectively improve the duration and fairness of the federation.

cs.LG↗

arXiv2022

Imbalanced Classification in Medical Imaging via Regrouping

We propose performing imbalanced classification by regrouping majority classes into small classes so that we turn the problem into balanced multiclass classification. This new idea is dramatically different from popular loss reweighting and class resampling methods. Our preliminary result on imbalanced medical image classification shows that this natural idea can substantially boost the classification performance as measured by average precision (approximately area-under-the-precision-recall-curve, or AUPRC), which is more appropriate for evaluating imbalanced classification than other metrics such as balanced accuracy.

cs.CV↗