DeepSensing: A Novel Mobile Crowdsensing Framework With Double Deep <i>Q</i>-Network and Prioritized Experience Replay
Bibliographic record
Abstract
Mobile crowdsensing (MCS) is a new and promising paradigm of data collection due to the growing number of mobile smart devices. It can be utilized in applications of large-scale sensing by employing a group of mobile users with their smart devices. Since a large number of mobile users are recruited, the allocation of sensing tasks to mobile users has a critical influence on the performance of MCS applications. To efficiently assign sensing tasks to mobile users, we propose a novel MCS framework named DeepSensing. This framework consists of six executive phases, i.e., registration of sensing tasks, the announcement of reward rule, collection of users' information, task allocation, execution of sensing activities, and distribution of data and rewards. Here, the phase of task allocation is a key component, which directly determines the performance of DeepSensing, e.g., the platform's profit. DeepSensing aims to maximize the platform's profit by taking into account the various constraints of sensing tasks and mobile users. Therefore, we propose a deep reinforcement learning (DRL) method to optimally assign sensing tasks to mobile users. Specifically, we employ a double deep Q-network with prioritized experience replay (DDQN-PER) to address the task allocation problem, which is also formulated as a path planning problem with time windows. To evaluate our proposed DDQN-PER solution, three baseline solutions are provided, i.e., the ant colony system (ACS), E-greedy, and random solutions. Finally, the results of numerical simulations show that our proposed DDQN-PER solution outperforms the baseline solutions in terms of the platform's profit and it plans better organized traveling paths for mobile users.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".