Urban Water Quality Prediction Based on Multi-Task Multi-View Learning
Authors: Ye Liu, Yu Zheng, Yuxuan Liang, Shuming Liu, David S. Rosenblum
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on real-world datasets demonstrate the effectiveness of our approach. |
| Researcher Affiliation | Collaboration | 1 School of Computing, National University of Singapore, Singapore 2 Microsoft Research, Beijing, China 3 School of Computer Science and Technology, Xidian University, China 4 Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences 5 Division of Drinking Water Safety, School of Environment, Tsinghua University, China |
| Pseudocode | No | The paper describes the optimization process verbally and mathematically but does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks, nor structured steps resembling pseudocode. |
| Open Source Code | Yes | The code has been released at: http://research.microsoft.com/apps/pubs/?id=264770. |
| Open Datasets | No | The paper states: 'We evaluate our method with six datasets collected from August 2011 to August 2014 in Shenzhen City, China'. It details the types of data (Water quality, Hydraulic, Road networks, Pipe attributes, Meteorology, POIs) and their collection methods but does not provide specific links, DOIs, or citations to publicly accessible repositories for these datasets. |
| Dataset Splits | No | The paper mentions evaluating predictive performance based on 'historical data' and 'later readings' as 'ground truth' for next 1, 2, 3, 4 hours. However, it does not specify explicit training, validation, or test dataset splits (e.g., 80/10/10 percentages or specific sample counts for each split). |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments, such as CPU or GPU models, memory, or specific computational infrastructure. |
| Software Dependencies | No | The paper mentions using FISTA (Fast Iterative Shrinkage Thresholding Algorithm) and Accelerated Gradient Descent for optimization, but these are algorithms, not specific software packages with version numbers. It does not list any other software dependencies with version information (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | No | The paper mentions some aspects of feature construction, such as using 'the latest 12 hours temporal data' and 'only use the top 3 coefficients' for frequency features, and that 'λ, γ, α are regularization parameters'. However, it does not provide specific values for these regularization parameters or other key training hyperparameters like learning rate, batch size, or optimizer settings, which are crucial for reproducing the experimental setup. |