Congestion Graphs for Automated Time Predictions
Authors: Arik Senderovich, J. Christopher Beck, Avigdor Gal, Matthias Weidlich4854-4861
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our approach on two real-world datasets from healthcare systems where scarce resources prevail: an emergency department and an outpatient cancer clinic. Our experimental results show that using automatic generation of congestion features, we get an up to 23% improvement in terms of relative error in time prediction, compared to common baseline methods. |
| Researcher Affiliation | Academia | Arik Senderovich, J. Christopher Beck Mechanical and Industrial Engineering University of Toronto Canada sariks@mie.utoronto.ca jcb@mie.utoronto.ca Avigdor Gal Industrial Engineering and Management Technion-Israel Institute of Technology Israel avigal@technion.ac.il Matthias Weidlich Dept. of Computer Science Humboldt University zu Berlin Germany matthias.weidlich@hu-berlin.de |
| Pseudocode | No | The paper describes procedures and mathematical formulations but does not include a clearly labeled pseudocode or algorithm block. |
| Open Source Code | Yes | All algorithms for congestion graph mining and feature extraction are implemented in Python and are publicly available.1 http://bit.ly/2lcq37s |
| Open Datasets | No | The paper uses two real-world event logs from an Israeli emergency department (ED) and an outpatient cancer clinic (CC), but it does not provide any links, DOIs, repository names, or formal citations for these specific datasets to indicate public availability. |
| Dataset Splits | Yes | We follow the training-validation-test paradigm (Friedman, Hastie, and Tibshirani 2001) to evaluate our approach and randomly partition the two datasets into training data and test data. Specifically, for each dataset we make the following four partitions: Single month training: We use patients that arrived during April 2014 as training data and patients that were admitted during May 2014 as test data. ... Summer months: We use April 2014 June 2014 for training and test the technique on patients that arrived during July 2014. ... Entire year: we use April 2014 October 2014 for training and November 2014 December 2014 for testing. ... Peak hours: We choose the heavily loaded hours for each of the healthcare systems...we use April 2014 October 2014 for training and November 2014 December 2014 for testing. |
| Hardware Specification | Yes | Our experiments were conducted on an 8-core server, Intel Xeon CPU E5-2660 v4 @ 2.00GHz, each core being equipped with 32GB main memory, running on Linux Centos 7.3 OS. |
| Software Dependencies | No | The paper mentions that algorithms are "implemented in Python" and uses "XGBoost (Chen and Guestrin 2016)", but it does not specify any version numbers for Python or XGBoost, nor for any other libraries or dependencies. |
| Experiment Setup | No | The paper states that XGBoost was used and its hyperparameters were validated using cross-validation. However, it does not provide specific values for hyperparameters (e.g., learning rate, batch size, number of epochs) or other detailed training configurations in the main text. |