Optimized Trust Prediction and Multi-Criteria Framework for Task and Data Collector Selection Using Deep Learning in Ubiquitous Environments
In crowdsourcing and ubiquitous computing environments, efficient task assignment and data collector selection are vital for system performance and profitability. This paper presents a novel framework integrating deep learning models to predict trustworthiness for tasks and data collectors. Natural...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11080383/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In crowdsourcing and ubiquitous computing environments, efficient task assignment and data collector selection are vital for system performance and profitability. This paper presents a novel framework integrating deep learning models to predict trustworthiness for tasks and data collectors. Natural optimization algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Simulating Annulling (SA), and Cuckoo Search are employed to fine-tune hyperparameters of the predictive models. Tasks and data collectors are classified as trusted or non-trusted, and fuzzy multi-criteria decision-making techniques—Fuzzy Analytical Hierarchy Process (FAHP) and Fuzzy Technique for Order Preference by Similarity to Ideal Solution (FTOPSIS)—are used to rank and select tasks and data collectors. Extensive experiments validate the proposed strategy’s efficacy, demonstrating superior performance in terms of total Profit, total Reward, trusted score, overall success probability, and total Selected data collectors compared to existing approaches. |
|---|---|
| ISSN: | 2169-3536 |