Xinxin Feng

Short-term traffic flow prediction with Conv-LSTM

The accurate short-term traffic flow prediction can provide timely and accurate traffic condition information which can help one to make travel decision and mitigate the traffic jam. Deep learning (DL) provides a new paradigm for the analysis of big data generated by the urban daily traffic. In this paper, we propose a novel end-to-end deep learning architecture which consists of two modules. We combine convolution and LSTM to form a Conv-LSTM module which can extract the spatial-temporal information of the traffic flow information. Furthermore, a Bi-directional LSTM module is also adopted to analyze historical traffic flow data of the prediction point to get the traffic flow periodicity feature. The experimental results on the real dataset show that the proposed approach can achieve a better prediction accuracy compared with the existing approaches.

Short-term traffic flow prediction with optimized Multi-kernel Support Vector Machine

Accurate prediction of the traffic state can help to solve the problem of urban traffic congestion, providing guiding advices for peoples travel and traffic regulation. In this paper, we propose a novel short-term traffic flow prediction algorithm, which is based on Multi-kernel Support Vector Machine (MSVM) and Adaptive Particle Swarm Optimization (APSO). Firstly, we explore both the nonlinear and randomness characteristic of traffic flow, and hybridize Gaussian kernel and polynomial kernel to constitute the MSVM. Secondly, we optimize the parameters of MSVM with a novel APSO algorithm by considering both the historical and real-time traffic data. We evaluate our algorithm by doing thorough experiment on a large real dataset. The results show that our algorithm can do a timely and adaptive prediction even in the rush hour when the traffic conditions change rapidly. At the same time, the prediction results are more accurate compared to four baseline methods.

Distributed cell selection in heterogeneous wireless networks

Abstract A critical issue in many wireless networks is how to establish the best possible quality connections between users to base stations. This is in particular challenging when users are randomly located over a geographical region, and each covered by a number of heterogeneous base stations. To this end, we design a smart and efficient cell selection mechanism to improve the user-base station connection in heterogeneous wireless networks. We formulate the cell selection problem as an asymmetric congestion game with consideration of users’ heterogeneity in their locations and their data rates to various cells. We show the existence of pure Nash equilibria (PNE) and propose a concurrent distributed learning algorithm to converge to them. In the algorithm, we allow users to perform random error-tolerant updates synchronously, and guarantee them to reach one or multiple PNE with the largest utilities. In addition, we do a systematical investigation on the implementation of the algorithm in practical networks. Simulation results show that the algorithm can achieve satisfactory performance with acceptable convergence rate.

A design of distributed storage and processing system for Internet of Vehicles

With the explosion of vehicles, the concept of Internet of Vehicles (IoV) has drawn increasing concern among academics. The IoV refers to extracting and processing information from massive data which are gathering from vehicles and their surrounds. And an integrated IoV system which is reliable on data storage and efficient on data processing is indispensable. In this paper, we design a distributed storage and processing system depending on Hadoop, HBase and Spark to store and process IoV data. The system can overcome the single point of failure problem, guarantee the reliable data storage and meet the real-time computing requirements. We do thorough tests to evaluate the system performance based on practical IoV data of Fuzhou city. The results indicate that the system can satisfy the requirements of stable data storage and efficient data processing.

Traffic estimation in road networks via compressive sensing

The recent advances of compressive sensing (CS) have witnessed a great potential of traffic condition estimation in road networks. In this paper, we propose a traffic estimation approach that applies compressive sensing technique to achieve a city-scale traffic estimation with only a small number of vehicle probes. In particular, we construct a new type of random matrix for CS which can significantly reduce the number of vehicle probes for traffic estimation. Furthermore, we also propose a novel representation matrix to better exploit the correlations of road network to improve the accuracy of traffic estimation. We analyze the incoherence between random measurement matrix and sparsity representation basis. Finally, we validate the effectiveness of the proposed approach through extensive simulations by real-world dataset.

A compressive and adaptive sampling approach in crowdsensing networks

High data quality and low sensing cost are two primary goals in large-scale mobile crowdsensing applications. The oversampling and the undersampling are common problems which always result in a high cost or low data quality that can not satisfy the system requirement. To address this problem, taking into account low-rank latent structure, we propose a compressive and adaptive data sampling scheme (CAS) which exploits adaptivity to identify locations which are highly informative for learning the low-dimensional space of the data matrix. In contrast to existing random sampling methods, it involves a three-pass sampling procedure that firstly assigns a fraction of samples to estimate general information, then samples those more informative locations for exact recovery and finally estimates the values of the unsensing locations. Evaluations on synthetic datasets and real datasets for air quality monitoring show the effectiveness of CAS. The experimental results demonstrate that the proposed scheme is able to not only significantly improve the sensing data quality but also reduce the computation complexity comparing with the state-of-the-art matrix completion methods.

Image-based clustering analysis of massive vehicle networking data

In order to make full use of the massive vehicle networking data and dig out the characteristics of the vehicle driving behaviors, the analysis of the massive vehicle networking data is indispensable. And clustering analysis is an effective way to extract the information which can guide and supervise the vehicles. In this paper, we propose a novel initial clustering center selection algorithm based on the image recognition. In addition, in order to shorter the time of the clustering algorithm, we improve the ε-Link based on the massive vehicle networking data. We refer to image-based clustering algorithm applied on matching map of the vehicle networking data and ultimately obtain the traffic hot spot map of the urban roads by the clustering analysis. We evaluate our algorithm by doing thorough simulation on the massive data of vehicles in Fuzhou city. The result shows that when compared to the traditional clustering algorithms with great randomness in selection, the image-based clustering algorithm consumes less time in the case of massive vehicle networking data. And through the analysis of the trajectory data, the traffic hot spot map can be formed and practically reflects the practical traffic flow of Fuzhou city.

A novel design of Direct Sequence Spread Spectrum receiver based on software radio

The synchronous carrier is difficult to extract in low SNR power line communication environment by traditional spread-spectrum demodulation method. To solve this problem, a novel design of DSSS (Direct Sequence Spread Spectrum) receiver, based on Software radio structure and band-pass sampling theorem is proposed in this paper. The designed receiver consists of A/D converter and digital low-pass filter, which can demodulate information without carrier synchronization. Moreover, spread-spectrum demodulation can be realized in base band. Both theoretical analysis and simulation results prove that the novel receiver structure has low system spending and high anti-noise performance and it can be applied in rough communication environment.