In the wireless Federated Learning （FL） architecture， the model parameter data need to be continuously exchanged between the client and the server to update the model， thus causing a large communication overhead and power consumption on the client. At present， there are many methods to reduce communication overhead by data quantization and data sparseness. In order to further reduce the communication overhead， a wireless FL algorithm based on 1?bit compressive sensing was proposed. In the uplink of wireless FL architecture， the data update parameters of its local model， including update amplitude and trend， were firstly recorded on the client. Then， sparsification was performed to the amplitude and trend information， and the threshold required for updating was determined. Finally， 1?bit compressive sensing was performed on the update trend information， thereby compressing the uplink data. On this basis， the data size was further compressed by setting dynamic threshold. Experimental results on MNIST datasets show that the 1?bit compressive sensing process with the introduction of dynamic threshold can achieve the same results as the lossless transmission process， and reduce the amount of model parameter data to be transmitted by the client during the uplink communication of FL applications to 1/25 of the normal FL process without this method； and can reduce the total user upload data size to 2/11 of the original size and reduce the transmission energy consumption to 1/10 of the original size when the global model is trained to the same level.

Most Mobile Crowd Sensing （MCS） task allocation methods are specific to a single task and are difficult to apply to real-world scenarios of real-time concurrent multi-task. And it is often necessary for these methods to obtain user location in real time， which is not conducive to the protection of participant privacy. Concerning the above problems， a distributed multi-task allocation method for user area was proposed， named Crowd-Cluster. Firstly， the global perception task and the user area were clustered by using the greedy heuristic algorithm. Secondly， based on the spatial correlation， the Q-learning algorithm was used to combine the concurrent tasks into the task path. Then， the task path was dynamically priced by constructing user intention model that satisfying the Boltzmann distribution. Finally， based on the historical reputation records， the participants were greedily selected to implement task allocation. Experimental results on the real dataset mobility show that Crowd-Cluster can effectively reduce the total number of participants and the total movement distance of users， and can also reduce the impact of insufficient perception resources on task completion in the low population density scenarios.