In Sparse Mobile Crowdsensing, many data inference schemes have been proposed without considering the sensing dataset with different trust levels which contains unrecognizable false data, resulting in high inference error and poor practical utility. To address this challenge, we propose a Transformer based Truthful Data Inference (TTDI) scheme that can tolerate false data interference to enhance data inference quality. Firstly, the trust-weighted loss function (TLF) is proposed to reduce the false interference for data inference model training. The TLF implements a differential model parameter updating strategy for data with different trust levels, which can enhance and weaken the effect of high-trust and low-trust data on the trained data inference model, respectively. Secondly, the transformer based truthful spatiotemporal feature extraction (T-TSFE) algorithm is proposed to mitigate the mutual interference between biased spatiotemporal features. The T-TSFE extracts data features through temporal and spatial multi-head attention respectively, which reduces the propagation of false information across the spatiotemporal dimensions. Finally, we conduct extensive experiments with four real-world air quality datasets to verify the effectiveness of the TTDI in data inference quality.

In sparse mobile crowdsensing, the platform con-structs services based on low-cost data collection through data inference schemes, where the quality of the inferred data directly affects the service quality. Existing data inference schemes assume that workers report trustworthy data, which is not practical in SMCS. It is urgent to establish a high-quality data collection scheme for data inference that can tolerate false data to enhance inferred data quality. To address this challenge, we propose a Truthful Multi-Task Allocation (TMTA) scheme. First, we estimate the spatiotemporal correlation between areas for iden-tifying areas with high importance to the data inference process. Second, a trust-based multi-task allocation algorithm is proposed to ensure that the sensing data from high-importance areas have high trust levels. Third, a multi-armed bandit based trustworthy worker identification strategy is proposed to prioritize Multi-Task allocation for workers who can be effectively identified as trustworthy. Finally, a truthful discrete heuristic algorithm is proposed to optimize the multi-task allocation using the proposed hybrid neighbor-mode strategy, which reduces the difficulty of searching for high-utility multi-task allocations. Extensive exper-iments on two real-world air-quality datasets demonstrate that TMTA consistently outperforms six baseline methods, achieving average reductions of 24.70% in RMSE and 17.79% in sensing cost across five experimental scenarios.

Nowadays, Mobile Crowd Sensing (MCS) has become a popular paradigm for large-scale data collection using ubiquitous mobile sensing devices. However, most existing works do not consider that requester's payments are unknown prior, and assume that workers are honest, which may not be true in practice. To address these problems, we propose a novel Truthful and Dual-direction Combinatorial Multi-Armed Bandit (TD-CMAB) scheme, which maximizes the total profit of the dual-direction platform for both the worker side and the requester side. Specifically, for the worker side, to overcome the problem that the platform is not clear whether sensed data are true, we propose a worker recruitment strategy that identifies and recruits honest workers at low cost through the Upper Confidence Bound (UCB) algorithm based on truth data discovery. For the requester side, where requesters’ payments are unknown prior, we model requester selection as a CMAB problem and solve it by the proposed adaptive UCB algorithm. Furthermore, we theoretically prove the worst regret bound of the TD-CMAB. Finally, we evaluate the effectiveness of the TD-CMAB scheme through extensive experiments using the Beijing taxi dataset.

Sparse mobile crowdsensing (SMCS) is a prospective solution for large-scale data sensing through mobile devices of Internet of Things (IoT) systems where IoT systems cannot obtain the sensing data of the area under extreme environments. The unsensed area data can be obtained by the data inference algorithm trained by the sensed data of recruited workers. However, recruited workers may upload false data in exchange for payment, and the platform is unable to distinguish between true and false data. In this article, our goal is to maximize the SMCS platform’s total profit, where the platform cannot verify the authenticity of the sensed data, and the requester’s payment is based on the sensing task’s data quality. To meet the objective, we propose the area-constrained truthful worker recruitment-based sensing map recovery (ATWR-SMR) scheme, which includes the area constraint, the area-constrained truthful worker recruitment, and the sensing map recovery. 1) The area constraint establishes the importance of areas by history data differences in the sliding window. 2) The truthful worker recruitment identifies trustworthy workers by the truthful upper confidence bound algorithm and recruits low-cost trustworthy workers to sense high-importance areas. 3) The sensing map recovery infers the unsensed data by the deep matrix factorization algorithm trained by the history truthful data set. Finally, we verify the effectiveness of the ATWR-SMR scheme in improving the total profit of the platform through extensive comparison experiments based on the China air quality data set.