A Nonparametric Online Model for Air Quality Prediction
Authors: Vitor Guizilini, Fabio Ramos
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Tests were conducted using a real-time feed from a sensor network in an area of roughly 50 80 km, alongside comparisons with other techniques for air pollution prediction. |
| Researcher Affiliation | Collaboration | Vitor Guizilini1 and Fabio Ramos1,2 1National ICT Australia (NICTA), 2School of Information Technologies, The University of Sydney, Australia. |
| Pseudocode | No | The paper does not include any clearly labeled pseudocode blocks or algorithm figures. |
| Open Source Code | No | The paper does not provide any links to open-source code for the methodology described, nor does it state that the code is available in supplementary materials or upon request. |
| Open Datasets | No | The paper describes the data collection from a sensor network: 'Tests were conducted using a sensor network composed of 14 sensors, covering an area of roughly 50 80 km. All sensors provide hourly measurements of PM10, temperature (TP), humidity (HM) and wind (WD), and three of these sensors also provide hourly PM2.5 measurements.' However, it does not state that this collected dataset is publicly available, nor does it provide a link, DOI, or formal citation to an existing public dataset. |
| Dataset Splits | No | The paper states: 'In all experiments, a time interval of 3 months was used for training (2 for the starting model and 1 for evaluation)'. While 'evaluation' data is mentioned, the paper does not provide specific percentages or sample counts for a traditional train/validation/test split for reproducibility. It also describes 'Structural Cross-Validation' as a methodology, but this does not equate to providing a reproducible validation split for a specific dataset. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments, such as CPU models, GPU models, or memory specifications. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers (e.g., 'Python 3.x', 'PyTorch 1.x'). |
| Experiment Setup | Yes | In all experiments, a time interval of 3 months was used for training (2 for the starting model and 1 for evaluation), with initial periods of 24, 48, 168 and 672 hours. |