Coordinating Measurements in Uncertain Participatory Sensing Settings
Authors: Alexandros Zenonos, Sebastian Stein, Nicholas R. Jennings
JAIR 2018 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically evaluate our algorithm on a real-world human mobility and air quality dataset and show that it outperforms the current state of the art by up to 24% in terms of utility gained. |
| Researcher Affiliation | Academia | Alexandros Zenonos EMAIL Sebastian Stein EMAIL Electronics and Computer Science, University of Southampton, Southampton, UK Nicholas R. Jennings EMAIL Department of Computing, Department of Electrical and Electronic Engineering, Imperial College London, London, UK |
| Pseudocode | Yes | Algorithm 1 Adaptive Best-Match (a BM) Algorithm Algorithm 2 Simulations for Scalable Searching (Si Sca S) Algorithm Algorithm 3 Stochastic Local Greedy Search (SLGS) Algorithm 4 Adapt Algorithm 5 Matching algorithm |
| Open Source Code | No | The paper does not provide explicit statements about releasing code, a link to a source-code repository, or mentions code in supplementary materials for the methodology described. |
| Open Datasets | Yes | We use an air quality dataset (Zheng, Liu, & Hsieh, 2013), which contains one year’s (2013-2014) fine grained air quality data from static air quality monitoring stations in Beijing. In this work, however, we use data from the Geolife trajectories dataset (Zheng, Zhang, Xie, & Ma, 2009; Zheng, Li, Chen, Xie, & Ma, 2008; Zheng, Xie, & Ma, 2010), which contains sequences of time-stamped locations of 182 people in Beijing over a period of 5 years (2007-2012), as reported by portable GPS devices. |
| Dataset Splits | No | The paper describes preprocessing steps and how the data is used (e.g., to train the GP model), but it does not specify any training, validation, or test dataset splits or percentages required to reproduce the experiments. |
| Hardware Specification | Yes | Our experimental platform is the IRIDIS High Performance Computing Facility with 2.6 GHz Intel Sandybridge processors and 64GB RAM per node. |
| Software Dependencies | No | The paper mentions various techniques and algorithms (e.g., DBSCAN, K-means, Gaussian Processes) and cites their original publications, but it does not specify any software names with version numbers used for its implementation. |
| Experiment Setup | Yes | In our work, we assume that people have an average budget of two measurements per day... We create the probability distribution of the locations such that 80% of the time the true location of the people will be allocated a higher probability than the alternative locations. At the same time, 20% of the time the correct location is assigned less probability than a random location from the user’s mobility patterns... The dynamism in this experiment is fixed at 1... We vary the average reliability of the users between zero and one. |