Federated Learning (FL) has recently attracted considerable attention in internet of things, due to its capability of enabling mobile clients to collaboratively learn a global prediction model without sharing their privacy-sensitive data to the server. Despite its great potential, a main challenge of FL is that the training data are usually non-Independent, Identically Distributed (non-IID) on the clients, which may bring the biases in the model training and cause possible accuracy degradation. To address this issue, this paper aims to propose a novel FL algorithm to alleviate the accuracy degradation caused by non-IID data at clients. Firstly, we observe that the clients with different degrees of non-IID data present heterogeneous weight divergence with the clients owning IID data. Inspired by this, we utilize weight divergence to recognize the non-IID degrees of clients. Then, we propose an efficient FL algorithm, named CSFedAvg, in which the clients with lower degree of non-IID data will be chosen to train the models with higher frequency. Finally, we conduct simulations using publicly-available datasets to train deep neural networks. Simulation results show that the proposed FL algorithm improves the training performance compared with existing FL protocol.

Nowadays, vehicles have been increasingly adopted in mobile crowdsensing applications. Due to their predictable mobility trajectories, vehicles as participants bring new insight in improving the crowdsensing quality. The predictable mobility of vehicles provides not only the current locations of the vehicles, but also their future mobility trajectory. In this context, the existing participant recruitment solutions, which are mainly based on the current locations of the participants, cannot be directly used in vehicle-based mobile crowdsensing. Utilizing the predicted mobility trajectory of vehicles, this paper aims to propose efficient vehicle recruitment algorithms for mobile crowdsensing, so as to minimize the overall recruitment cost. Specifically, we study two mobility trajectory models of the vehicles, named deterministic and probabilistic models. We first prove that the vehicle recruitment problem under both models is NP-hard. Then, for the deterministic trajectory model, an efficient LP-relaxation-based heuristic algorithm is proposed, and an approximation ratio is analyzed. For the probabilistic trajectory model, we propose a greedy algorithm and analyze its performance with a guaranteed approximation ratio. Finally, we evaluate the performance of the proposed schemes through simulations.

Accurately predicting Origin-Destination (OD) passenger flow can help metro service quality and efficiency. Existing works have focused on predicting incoming and outgoing flows for individual stations, while little attention was paid to OD prediction in metro systems. The challenges are that OD flows 1) have high temporal dynamics and complex spatial correlations, 2) are affected by external factors, and 3) have sparse and incomplete data slices. In this paper, we propose an Adaptive Feature Fusion Network (AFFN) to a) adaptively fuse spatial dependencies from multiple knowledge-based graphs and even hidden correlations between stations and b) accurately capture the periodic patterns of passenger flows based on the auto-learned impact from external factors. To deal with the incompleteness and sparsity of OD matrices, we extend AFFN to multi-task AFFN to predict the inflow and outflow of each station as a side-task to further improve OD prediction accuracy. We conducted extensive experiments on two real-world metro trip datasets collected in Nanjing and Xi’an, China. Evaluation results show that our AFFN and multi-task AFFN outperform the state-of-the-art baseline techniques and AFFN variants in various accuracy metrics, demonstrating the effectiveness of AFFN and each of its key components in OD prediction.

Deep learning is a popular direction in computer vision and digital image processing. It is widely utilized in many fields, such as robot navigation, intelligent video surveillance, industrial inspection, and aerospace. With the extensive use of deep learning techniques, classification and object detection algorithms have been rapidly developed. In recent years, with the introduction of the concept of "unmanned retail", object detection and image classification play a central role in unmanned retail applications. However, open source datasets of traditional classification and object detection have not yet been optimized for application scenarios of unmanned retail. Currently, classification and object detection datasets do not exist that focus on unmanned retail solely. Therefore, in order to promote unmanned retail applications by using deep learning-based classification and object detection, we collected more than 30,000 images of unmanned retail containers using a refrigerator affixed with different cameras under both static and dynamic recognition environments. These images were categorized into 10 kinds of beverages. After manual labeling, the dataset images contained 155,153 instances, each of which was annotated with a bounding box. We performed extensive experiments on this dataset using 10 state-of-the-art deep learning-based models. Experimental results indicate great potential of using these deep learning-based models for real-world smart unmanned vending machines (UVMs).

With the increasing complexity of tasks that are crowdsourced, requesters need to form teams of professional workers that can satisfy complex task skill requirements. Team crowdsourcing in social networks (SNs) provides a promising solution for complex task crowdsourcing, where the requester hires a team of professional workers that are also socially connected can work together collaboratively. Previous social team formation approaches have mainly focused on the algorithmic aspect for social welfare maximization; however, within the traditional objective of maximizing social welfare alone, selfish workers can manipulate the crowdsourcing market by behaving untruthfully. This dishonest behavior discourages other workers from participating and is unprofitable for the requester. To address this strategic social team crowdsourcing problem, truthful mechanisms are developed to guarantee that a worker's utility is optimized when he behaves honestly. This problem is proved to NP-hard, and two efficient mechanisms are proposed to optimize social welfare while reducing time complexity for different scale applications. For small-scale applications where the task requires a small number of skills, a binary tree network is first extracted from the social network, and a dynamic programming-based optimal team is formed in the binary tree. For large-scale applications where the task requires a large number of skills, a team is formed greedily based on the workers' social structure, skill and working cost. For both mechanisms, the threshold payment rule, which pays each worker his marginal value for task completion, is proposed to elicit truthfulness. Finally, the experimental results of a real-world dataset show that compared to the benchmark exponential VCG truthful mechanism, the proposed small-scale-oriented mechanism can reduce computation time while producing nearly the same social welfare results. Furthermore, compared to other state-of-the-art polynomial heuristics, the proposed large-scale-oriented mechanism can achieve truthfulness while generating better social welfare outcomes.