Privacy-Preserving Federated Mobility Prediction with Compound Data and Model Perturbation Mechanism

Human mobility prediction is important for many applications.However,training an accurate mobility prediction model requires a large scale of human trajectories,where privacy issues become an important problem.The rising federated learning provides us with a promising solution to this problem,which enables mobile devices to collaboratively learn a shared prediction model while keeping all the training data on the device,decoupling the ability to do machine learning from the need to store the data in the cloud.However,existing federated learningbased methods either do not provide privacy guarantees or have vulnerability in terms of privacy leakage.In this paper,we combine the techniques of data perturbation and model perturbation mechanisms and propose a privacy-preserving mobility prediction algorithm,where we add noise to the transmitted model and the raw data collaboratively to protect user privacy and keep the mobility prediction performance.Extensive experimental results show that our proposed method significantly outperforms the existing stateof-the-art mobility prediction method in terms of defensive performance against practical attacks while having comparable mobility prediction performance,demonstrating its effectiveness.

Routing Protocol for Heterogeneous FANETs with Mobility Prediction

In recent years,with the growth in Unmanned Aerial Vehicles(UAVs),UAV-based systems have become popular in both military and civil applications.In these scenarios,the lack of reliable communication infrastructure has motivated UAVs to establish a network as flying nodes,also known as Flying Ad Hoc Networks(FANETs).However,in FANETs,the high mobility degree of flying and terrestrial users may be responsible for constant changes in the network topology,making end-to-end connections in FANETs challenging.Mobility estimation and prediction of UAVs can address the challenge mentioned above since it can provide better routing planning and improve overall FANET performance in terms of continuous service availability.We thus develop a Software Defined Network(SDN)-based heterogeneous architecture for reliable communication in FANETs.In this architecture,we apply an Extended Kalman Filter(EKF)for accurate mobility estimation and prediction of UAVs.In particular,we formulate the routing problem in SDN-based Heterogeneous FANETs as a graph decision problem.As the problem is NP-hard,we further propose a Directional Particle Swarming Optimization(DPSO)approach to solve it.The extensive simulation results demonstrate that the proposed DPSO routing can exhibit superior performance in improving the goodput,packet delivery ratio,and delay.

Participants Recruitment for Coverage Maximization by Mobility Predicting in Mobile Crowd Sensing

Mobile Crowd Sensing(MCS)is an emerging paradigm that leverages sensor-equipped smart devices to collect data.The introduction of MCS also poses some challenges such as providing highquality data for upper layer MCS applications,which requires adequate participants.However,recruiting enough participants to provide the sensing data for free is hard for the MCS platform under a limited budget,which may lead to a low coverage ratio of sensing area.This paper proposes a novel method to choose participants uniformly distributed in a specific sensing area based on the mobility patterns of mobile users.The method consists of two steps:(1)A second-order Markov chain is used to predict the next positions of users,and select users whose next places are in the target sensing area to form a candidate pool.(2)The Average Entropy(DAE)is proposed to measure the distribution of participants.The participant maximizing the DAE value of a specific sensing area with different granular sub-areas is chosen to maximize the coverage ratio of the sensing area.Experimental results show that the proposed method can maximize the coverage ratio of a sensing area under different partition granularities.

Theoretical Prediction of the Photovoltaic Properties of BFBPD-PC61 BM System as a Promising Organic Solar Cell

In this work,the photovoltaic properties of BFBPD-PC61 BM system as a promising high-performance organic solar cell（OSC） were theoretically investigated by means of quantum chemistry and molecular dynamics calculations coupled with the incoherent charge-hopping model.Moreover,the hole carrier mobility of BFBPD thin-film was also estimated with the aid of an amorphous cell including 100 BFBPD molecules.Results revealed that the BFBPD-PC61 BM system possesses a middle-sized open-circuit voltage of 0.70 V,large short-circuit current density of 17.26 mA ·cm^-2,high fill factor of 0.846,and power conversion efficiency of 10%.With the Marcus model,in the BFBPD-PC61 BM interface,the exciton-dissociation rate,kdis,was predicted to be 2.684×10^13 s^-1,which is as 3-5 orders of magnitude large as the decay（radiative and non-radiative） one（10-8-10^10s^-1）,indicating a high exciton-dissociation efficiency of 100% in the BFBPD-PC61 BM interface.Furthermore,by the molecular dynamics simulation,the hole mobility of BFBPD thin-film was predicted to be as high as 1.265 × 10^-2 cm-2·V^-1·s^-1,which can be attributed to its dense packing in solid state.

Adaptive Graph Convolutional Recurrent Neural Networks for System-Level Mobile Traffic Forecasting

Accurate traffic pattern prediction in largescale networks is of great importance for intelligent system management and automatic resource allocation.System-level mobile traffic forecasting has significant challenges due to the tremendous temporal and spatial dynamics introduced by diverse Internet user behaviors and frequent traffic migration.Spatialtemporal graph modeling is an efficient approach for analyzing the spatial relations and temporal trends of mobile traffic in a large system.Previous research may not reflect the optimal dependency by ignoring inter-base station dependency or pre-determining the explicit geological distance as the interrelationship of base stations.To overcome the limitations of graph structure,this study proposes an adaptive graph convolutional network(AGCN)that captures the latent spatial dependency by developing self-adaptive dependency matrices and acquires temporal dependency using recurrent neural networks.Evaluated on two mobile network datasets,the experimental results demonstrate that this method outperforms other baselines and reduces the mean absolute error by 3.7%and 5.6%compared to time-series based approaches.

Mobility assisted spectrum aware routing protocol for cognitive radio ad hoc networks

We propose a mobility assisted spectrum aware routing(MASAR) protocol for cognitive radio ad hoc networks(CRAHNs),providing robustness to primary user activity and node mobility.This protocol allows nodes to collect spectrum information during a spectrum management interval followed by a transmission period.Cognitive users discover next hops based on the collected spectrum and mobility information.Using a beaconless mechanism,nodes obtain the mobility information and spectrum status of their neighbors.A geographical routing scheme is adopted to avoid performance degradation specially due to the mobility of the nodes and the activity of the primary users.Our scheme uses two approaches to fnd either short or stable routes.Since mobility metrics have a signifcant role in the selection of the next hop,both approaches use a reactive mobility update process assisted by mobility prediction to avoid location errors.MASAR protocol performance is investigated through simulations of diferent scenarios and compared with that of the most similar protocol,CAODV.The results indicate that MASAR can achieve signifcant reduction in control overhead as well as improved packet delivery in highly mobile networks.