Mobile crowd sensing (MCS) with human participants has been proposed as an efficient way of collecting data for smart cities applications. However, there often exist situations where humans are not able or reluctant to reach the target areas, due to for example traffic jams or bad road conditions. One solution is to complement manual data collection with autonomous data collection using unmanned aerial vehicles (UAVs) equipped with various sensors. In this paper, we focus on the scenarios of UAV-assisted MCS and propose a task allocation method, called “UMA” ( U AV-assisted M ulti-task A llocation method) to optimize the sensing coverage and data quality. The method incentivizes human participants to contribute sensing data from nearby points of interest (PoIs), with a limited budget. Meanwhile, the method jointly considers the optimization of task assignment and trajectory scheduling. It schedules the trajectories of UAVs, considering the locations of human participants, other UAVs and PoIs which are rarely visited by human participants. In detail, UAVs take care of two tasks in our proposal. One is to calibrate the data collected by the human participants whom the UAVs come across along their trajectories. The other is to collect data from the PoIs which are not covered by other UAVs or human participants. We apply deep reinforcement learning to schedule UAVs moving trajectories and sensing activities in order to minimize the overall energy cost. We evaluate the proposed scheme via simulation using two real data sets. The results show that our proposal outperforms the compared methods, in terms of coverage completed ratio, calibrating ratio, energy efficiency, and task fairness.

Providing accurate real-time environmental monitoring services is a meaningful but difficult task. Whereas recent developments in the Internet of Things and the fog computing paradigm have brought new opportunities to improve the service, achieving accurate environmental monitoring faces several challenges. First, data collected by the Internet of Things varies in temporal-spatial distribution, quality, and relevance to objectives. Second, due to the limited communication cost and stability, local real-time monitoring systems can be hardly achieved by adopting centralized cloud paradigm solutions in the real world. Third, the amount of data at a single edge node of fog computing paradigm is usually not sufficient for accurate environmental monitoring. In this paper, we propose a framework for environmental monitoring based on fog computing that uses multi-source heterogeneous data collected from the Internet of Things sensors. At each edge node, we employ local sub-classifiers to analyze the collected data and afterwards, a deep neural network based model to aggregate results from sub-classifiers. For the homologous sub-classifiers at different edge nodes, we design a federated learning mechanism to update sub-classifiers in concert by model transmission. We use multi-source heterogeneous data collected in Beijing to evaluate the proposed fog computing framework. Experimental results show that our federated learning mechanism has almost the same performance compared with centralized data fusion mechanism when training rounds are increased.

Mobile crowd sensing campaigns usually require spatial-temporal sensing coverage. However, there are numerous circumstances where human participants are unable or unwilling to reach the target regions, such as traffic jams or accidents. Furthermore, human participants may not prefer to be interrupted frequently or leak private information too much. All of these are salient challenges that affect task achievement. To solve these problems, we propose in this paper a method that employs human participants and UAVs to sense data together. For human participants, the proposed method takes their sensing and reporting tolerance into consideration, which predicts their trajectories based on the sole clue of their start and destination locations and allocates tasks following the Pareto optimal theory. In the meantime, the UAVs sense data efficiently from areas that are not sensed by human participants or other UAVs. We evaluate the proposed method using simulation and a small-scale practical experiment. Extensive experiments are used to verify the method's efficiency.

Graph-based approaches are successful for histology image classification tasks but still face many challenges, such as: 1) the lack of nuclei-level labels and the significant variations between histology images make it extremely difficult to extract discriminative high-level nuclei features like nuclei type, texture and micro-environment; 2) graph-based approaches cannot handle large-scale cell graph nodes typically contained in histology images; and 3) graph neural networks (GNNs) struggle to learn the long-range dependency of cell graphs. To address the above challenges, we propose a scalable graph-based framework for multi-organ histology image classification. We develop a two-step MNP supervised training approach to extract discriminative high-level nuclei features for histology images without nuclei-level labels. Additionally, we introduce a nuclei sampling strategy to make our graph-based framework scalable for large-scale cell graphs. Furthermore, we propose HierArchical Transformer Graph Neural Network (HAT-Net+) for cell graph classifications. HAT-Net+ adopts Transformer to model the long-range dependency of cell graphs and a parameter-free approach to adaptively fuse different hierarchical graph representations of each layer. We achieved the state-of-the-art results on four public histology image classification datasets: CRC dataset (100%), Extended CRC dataset (98%), UZH dataset (96.9%) and BACH dataset (88%). Unlike other methods, our approach can be used in various histology image classification tasks, even for images without nuclei-level labels, indicating its potential in cancer diagnosis.

In this paper, we leverage unmanned aerial vehicles (UAVs) to enhance mobile crowd sensing (MCS) by addressing two critical challenges: uncontrollable data quality and inevitable unsensed points of interest (PoIs). We introduce a UAV-assisted method to deal with these challenges. To ensure the accuracy of sensing data contributed by human participants, the proposed truth discovery method utilizes UAV-collected sensing data as few-shot samples to train the truth discovery model, which is then employed to calibrate sensing data solely collected by human participants. Additionally, to meet the sensing coverage requirement, we present a method that predicts data values for unsensed PoIs by utilizing their historical sensing data and the sensed neighboring PoIs information. The method employs a graph neural network to capture spatio-temporal relationships of the sensing data, facilitating accurate estimation of unsensed PoIs. Through extensive simulations, our approaches demonstrate superior performance compared to existing methods, showcasing the potential of UAV-assisted MCS for overcoming challenges and enhancing data collection efficiency in various domains.