AST3DRNet: Attention-Based Spatio-Temporal 3D Residual Neural Networks for Traffic Congestion Prediction.

Traffic congestion prediction has become an indispensable component of an intelligent transport system. However, one limitation of the existing methods is that they treat the effects of spatio-temporal correlations on traffic prediction as invariable during modeling spatio-temporal features, which results in inadequate modeling. In this paper, we propose an attention-based spatio-temporal 3D residual neural network, named AST3DRNet, to directly forecast the congestion levels of road networks in a city. AST3DRNet combines a 3D residual network and a self-attention mechanism together to efficiently model the spatial and temporal information of traffic congestion data. Specifically, by stacking 3D residual units and 3D convolution, we proposed a 3D convolution module that can simultaneously capture various spatio-temporal correlations. Furthermore, a novel spatio-temporal attention module is proposed to explicitly model the different contributions of spatio-temporal correlations in both spatial and temporal dimensions through the self-attention mechanism. Extensive experiments are conducted on a real-world traffic congestion dataset in Kunming, and the results demonstrate that AST3DRNet outperforms the baselines in short-term (5/10/15 min) traffic congestion predictions with an average accuracy improvement of 59.05%, 64.69%, and 48.22%, respectively.

A game theory-based COVID-19 close contact detecting method with edge computing collaboration.

People all throughout the world have suffered from the COVID-19 pandemic. People can be infected after brief contact, so how to assess the risk of infection for everyone effectively is a tricky challenge. In view of this challenge, the combination of wireless networks with edge computing provides new possibilities for solving the COVID-19 prevention problem. With this observation, this paper proposed a game theory-based COVID-19 close contact detecting method with edge computing collaboration, named GCDM. The GCDM method is an efficient method for detecting COVID-19 close contact infection with users' location information. With the help of edge computing's feature, the GCDM can deal with the detecting requirements of computing and storage and relieve the user privacy problem. Technically, as the game reaches equilibrium, the GCDM method can maximize close contact detection completion rate while minimizing the latency and cost of the evaluation process in a decentralized manner. The GCDM is described in detail and the performance of GCDM is analyzed theoretically. Extensive experiments were conducted and experimental results demonstrate the superior performance of GCDM over other three representative methods through comprehensive analysis.

Locally private frequency estimation of physical symptoms for infectious disease analysis in Internet of Medical Things.

Frequency estimation of physical symptoms for peoples is the most direct way to analyze and predict infectious diseases. In Internet of medical Things (IoMT), it is efficient and convenient for users to report their physical symptoms to hospitals or disease prevention departments by various mobile devices. Unfortunately, it usually brings leakage risk of these symptoms since data receivers may be untrusted. As a strong metric for health privacy, local differential privacy (LDP) requires that users should perturb their symptoms to prevent the risk. However, the widely-used data structure called sketch for frequency estimation does not satisfy the specified requirement. In this paper, we firstly define the problem of frequency estimation of physical symptoms under LDP. Then, we propose four different protocols, i.e., CMS-LDP, FCS-LDP, CS-LDP and FAS-LDP to solve the above problem. Next, we demonstrate that the designed protocols satisfy LDP and unbiased estimation. We also present two approaches to implement the key component (i.e., universal hash functions) of protocols. Finally, we conduct experiments to evaluate four protocols on two real-world datasets, representing two different distributions of physical symptoms. The results show that CMS-LDP and CS-LDP have relatively optimal utility for frequency estimation of physical symptoms in IoMT.

An Exception Handling Approach for Privacy-Preserving Service Recommendation Failure in a Cloud Environment.

Service recommendation has become an effective way to quickly extract insightful information from massive data. However, in the cloud environment, the quality of service (QoS) data used to make recommendation decisions are often monitored by distributed sensors and stored in different cloud platforms. In this situation, integrating these distributed data (monitored by remote sensors) across different platforms while guaranteeing user privacy is an important but challenging task, for the successful service recommendation in the cloud environment. Locality-Sensitive Hashing (LSH) is a promising way to achieve the abovementioned data integration and privacy-preservation goals, while current LSH-based recommendation studies seldom consider the possible recommendation failures and hence reduce the robustness of recommender systems significantly. In view of this challenge, we develop a new LSH variant, named converse LSH, and then suggest an exception handling approach for recommendation failures based on the converse LSH technique. Finally, we conduct several simulated experiments based on the well-known dataset, i.e., Movielens to prove the effectiveness and efficiency of our approach.