NewEvery arXiv paper, its researchers & institutions — mapped.
the archive

#benchmarking

6 results
cs.CR2019

Carl-Hauser -- Open Source Image Matching Algorithms Benchmarking Framework

Vincent Falconieri

The paper presents an open‑source framework for benchmarking image‑matching algorithms, providing evaluation tools and publicly available datasets of phishing and onion‑site screen…

#image matching#benchmarking#open-source tools#phishing detection
stat.ML2019

Multitask learning and benchmarking with clinical time series data

Hrayr Harutyunyan, Hrant Khachatrian, David C. Kale +2

The paper introduces four benchmark prediction tasks derived from the MIMIC-III intensive care database—mortality risk, length of stay, physiologic decline detection, and phenotype…

#clinical prediction#benchmarking#multitask learning#time series
cs.NE2019

Benchmarking Surrogate-Assisted Genetic Recommender Systems

Thomas Gabor, Philipp Altmann

The paper introduces a recommender system that uses a surrogate model within an interactive genetic algorithm to suggest items, updating the model based on user feedback and showin…

#recommender systems#genetic algorithms#surrogate modeling#interactive evolution
cs.PF2019

Edge AIBench: Towards Comprehensive End-to-end Edge Computing Benchmarking

Tianshu Hao, Yunyou Huang, Xu Wen +8

The paper introduces Edge AIBench, an end-to-end benchmark suite for edge AI that models data distribution and workload collaboration across client devices, edge nodes, and cloud s…

#edge computing#benchmarking#ai workloads#federated learning
cs.CV2019

An Evaluation of Action Recognition Models on EPIC-Kitchens

Will Price, Dima Damen

The paper benchmarks several modern action recognition models (TSN, TRN, TSM) on the egocentric EPIC-Kitchens dataset and releases pretrained versions, analyzing performance on cha…

#action recognition#egocentric video#benchmarking#EPIC-Kitchens
econ.EM2019

Predicting credit default probabilities using machine learning techniques in the face of unequal class distributions

Anna Stelzer

The paper benchmarks 23 statistical and machine learning models for credit default prediction across four datasets, evaluating various sampling strategies to address class imbalanc…

#credit scoring#class imbalance#ensemble methods#benchmarking