arXiv subjects

Khushboo Sharma

Publications and source records attributed to Khushboo Sharma.

3 recordsLinked to original sources

arXiv2026

Constraints on GRB Jet Properties from IceCube Upper Limits: Insights from GRB 221009A and GRB 240825A

The IceCube neutrino telescope has provided upper limits on neutrino emission from gamma ray bursts. These constraints provided by the IceCube detector have been instrumental in investigating the properties of the GRB jet and its emission models. During the prompt phase of gamma ray burst emission, intense radiation components are generated that interact with the shock-accelerated particles within the jet. We study various GRB emission models, such as the internal shock model, the photospheric models, and also include a model-independent case. Based on these models, we calculate the neutrino fluence using the photo-hadronic interaction process. We estimate the bulk Lorentz factor using the well-known correlations between prompt phase observables, which is then used to calculate the emission site for the model-dependent scenarios. For GRB 221009A, we find that a low baryon loading scenario is consistent with the IceCube upper limits; however, for GRB 240825A, a higher value of baryon loading is preferred. Also, the values of the microphysical parameters $ε_e$ and $ε_B$ for GRB 240825A are lower by factors of approximately 10 and 100, respectively, compared to those of GRB 221009A. Further, using neutrino upper limits for these two sources, we estimate the lower limits on the dissipation radius for our models. The current TeV PeV upper limits for GRB 221009A are already useful for constraining parameter space for the BPH and MPH models.

astro-ph.HE↗

arXiv2025

Tree Boosting Methods for Balanced andImbalanced Classification and their Robustness Over Time in Risk Assessment

Most real-world classification problems deal with imbalanced datasets, posing a challenge for Artificial Intelligence (AI), i.e., machine learning algorithms, because the minority class, which is of extreme interest, often proves difficult to be detected. This paper empirically evaluates tree boosting methods' performance given different dataset sizes and class distributions, from perfectly balanced to highly imbalanced. For tabular data, tree-based methods such as XGBoost, stand out in several benchmarks due to detection performance and speed. Therefore, XGBoost and Imbalance-XGBoost are evaluated. After introducing the motivation to address risk assessment with machine learning, the paper reviews evaluation metrics for detection systems or binary classifiers. It proposes a method for data preparation followed by tree boosting methods including hyper-parameter optimization. The method is evaluated on private datasets of 1 thousand (K), 10K and 100K samples on distributions with 50, 45, 25, and 5 percent positive samples. As expected, the developed method increases its recognition performance as more data is given for training and the F1 score decreases as the data distribution becomes more imbalanced, but it is still significantly superior to the baseline of precision-recall determined by the ratio of positives divided by positives and negatives. Sampling to balance the training set does not provide consistent improvement and deteriorates detection. In contrast, classifier hyper-parameter optimization improves recognition, but should be applied carefully depending on data volume and distribution. Finally, the developed method is robust to data variation over time up to some point. Retraining can be used when performance starts deteriorating.

cs.LG↗

arXiv2023

Evaluating XGBoost for Balanced and Imbalanced Data: Application to Fraud Detection

This paper evaluates XGboost's performance given different dataset sizes and class distributions, from perfectly balanced to highly imbalanced. XGBoost has been selected for evaluation, as it stands out in several benchmarks due to its detection performance and speed. After introducing the problem of fraud detection, the paper reviews evaluation metrics for detection systems or binary classifiers, and illustrates with examples how different metrics work for balanced and imbalanced datasets. Then, it examines the principles of XGBoost. It proposes a pipeline for data preparation and compares a Vanilla XGBoost against a random search-tuned XGBoost. Random search fine-tuning provides consistent improvement for large datasets of 100 thousand samples, not so for medium and small datasets of 10 and 1 thousand samples, respectively. Besides, as expected, XGBoost recognition performance improves as more data is available, and deteriorates detection performance as the datasets become more imbalanced. Tests on distributions with 50, 45, 25, and 5 percent positive samples show that the largest drop in detection performance occurs for the distribution with only 5 percent positive samples. Sampling to balance the training set does not provide consistent improvement. Therefore, future work will include a systematic study of different techniques to deal with data imbalance and evaluating other approaches, including graphs, autoencoders, and generative adversarial methods, to deal with the lack of labels.

cs.LG↗