Kunqing Xie

Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning

Traffic flow prediction is a fundamental problem in transportation modeling and management. Many existing approaches fail to provide favorable results due to being: 1) shallow in architecture; 2) hand engineered in features; and 3) separate in learning. In this paper we propose a deep architecture that consists of two parts, i.e., a deep belief network (DBN) at the bottom and a multitask regression layer at the top. A DBN is employed here for unsupervised feature learning. It can learn effective features for traffic flow prediction in an unsupervised fashion, which has been examined and found to be effective for many areas such as image and audio classification. To the best of our knowledge, this is the first paper that applies the deep learning approach to transportation research. To incorporate multitask learning (MTL) in our deep architecture, a multitask regression layer is used above the DBN for supervised prediction. We further investigate homogeneous MTL and heterogeneous MTL for traffic flow prediction. To take full advantage of weight sharing in our deep architecture, we propose a grouping method based on the weights in the top layer to make MTL more effective. Experiments on transportation data sets show good performance of our deep architecture. Abundant experiments show that our approach achieved close to 5% improvements over the state of the art. It is also presented that MTL can improve the generalization performance of shared tasks. These positive results demonstrate that deep learning and MTL are promising in transportation research.

An experimental study of large-scale mobile social network

Mobile social network is a typical social network where one or more individuals of similar interests or commonalities, conversing and connecting with one another using the mobile phone. Our works in this paper focus on the experimental study for this kind of social network with the support of large-scale real mobile call data. The main contributions can be summarized as three-fold: firstly, a large-scale real mobile phone call log of one city has been extracted from a mobile phone carrier in China to construct mobile social network; secondly, common features of traditional social networks, such as power law distribution and small diameter etc, have been experimented, with which we confirm that the mobile social network is a typical scale-free network and has small-world phenomenon; lastly, different from traditional analytical methods, important properties of the actors, such as gender and age, have been introduced into our experiments with some interesting findings about human behavior, for example, the middle-age people are more active than the young and old people, and the female is unusual more active than the male while in the old age.

Influence Maximization on Large-Scale Mobile Social Network: A Divide-and-Conquer Method

With the proliferation of mobile devices and wireless technologies, mobile social network systems are increasingly available. A mobile social network plays an essential role as the spread of information and influence in the form of “word-of-mouth”. It is a fundamental issue to find a subset of influential individuals in a mobile social network such that targeting them initially (e.g., to adopt a new product) will maximize the spread of the influence (further adoptions of the new product). The problem of finding the most influential nodes is unfortunately NP-hard. It has been shown that a Greedy algorithm with provable approximation guarantees can give good approximation; However, it is computationally expensive, if not prohibitive, to run the greedy algorithm on a large mobile social network. In this paper, a divide-and-conquer strategy with parallel computing mechanism has been adopted. We first propose an algorithm called Community-based Greedy algorithm for mining top-K influential nodes. It encompasses two components: dividing the large-scale mobile social network into several communities by taking into account information diffusion and selecting communities to find influential nodes by a dynamic programming. Then, to further improve the performance, we parallelize the influence propagation based on communities and consider the influence propagation crossing communities. Also, we give precision analysis to show approximation guarantees of our models. Experiments on real large-scale mobile social networks show that the proposed methods are much faster than previous algorithms, meanwhile, with high accuracy.

An On-Road Wireless Sensor Network Approach for Urban Traffic State Monitoring

Wireless sensor networks are expected to be deployed on urban roadways to monitor the traffic continuously. One of the requirements of traffic monitoring is displaying the traffic states of the front roadways, which can guide the drivers to choose the right way and avoid potential traffic congestions. In this scenario, the information of traffic state changes should be refreshed as early as possible. We propose an adaptive segmentation of the traffic flow based on discrete Fourier transform, which responses timely to traffic state changes without inducing large error. On the other hand, considering the limited power of wireless sensor networks, we propose a novel algorithm for in-network aggregation of the traffic flow time-series, which reduces the communication cost between the sensor nodes and base station significantly. The proposed algorithm scales well with the size of the sensor networks. Our methods are computationally efficient and suitable to be implemented on sensor nodes. The primary experiments on PeMS data demonstrate the effectiveness and energy efficiency of our approach.

Efficient discovery of multilevel spatial association rules using partitions

Spatial data mining has been identified as an important task for understanding and use of spatial data- and knowledge-bases. In this paper, we present a new approach to discover strong multilevel spatial association rules in spatial databases based on partitioning the set of rows with respect to the spatial relations denoted as relation table R. Meanwhile, the introduction of the equivalence partition tree makes the discovery of multilevel spatial association rules easy and efficient. Experiments show that the new algorithm is efficient.

A Kalman Filter Based Approach for Outlier Detection in Sensor Networks

Outliers are common in data collection applications with wireless sensor networks, which consist of a large number of sensor nodes, embedded in physical space. The limited power supplies and noisy sensor data put challenges for outlier detection and cleaning in sensor networks. In this paper, we propose utilizing spatial and temporal dependencies that exist sensory readings. Our approach is based on Kalman filter and we design the state transition module and measuring module of the Kalman filter to exploit the temporal and spatial dependencies of sensor data respectively. The experimental results illustrate the effectiveness of our approach.

Causal relation of queries from temporal logs

In this paper, we study a new problem of mining causal relation of queries in search engine query logs. Causal relation between two queries means event on one query is the causation of some event on the other. We first detect events in query logs by efficient statistical frequency threshold. Then the causal relation of queries is mined by the geometric features of the events. Finally the Granger Causality Test (GCT) is utilized to further re-rank the causal relation of queries according to their GCT coefficients. In addition, we develop a 2-dimensional visualization tool to display the detected relationship of events in a more intuitive way. The experimental results on the MSN search engine query logs demonstrate that our approach can accurately detect the events in temporal query logs and the causal relation of queries is detected effectively.

Deep Architecture for Traffic Flow Prediction

Traffic flow prediction is a fundamental problem in transportation modeling and management. Many existing approaches fail at providing favorable results duo to 1shallow in architecture;2hand engineered in features. In this paper, we propose a deep architecture consists of two parts: a Deep Belief Network in the bottom and a regression layer on the top. The Deep Belief Network employed here is for unsupervised feature learning. It could learn effective features for traffic flow prediction in an unsupervised fashion which has been examined effective for many areas such as image and audio classification. To the best of our knowledge, this is the first work of applying deep learning approach to transportation research. Experiments on two types of transportation datasets show good performance of our deep architecture. Abundant experiments show that our approach could achieve results over state-of-the-art with near 3% improvements. Good results demonstrate that deep learning is promising in transportation research.

Anchor points seeking of large urban crowd based on the mobile billing data

In everyday life, people spend most of their time in some routine places such as the living places(origin) and working places(destination). We define these locations as anchor points. The anchor point information is important to the city planning, transportation management and optimization. Traditional methods of anchor points seeking mainly based on the data obtained from the sample survey or link volumes. The defects of these methods such as low sample rate and high cost make it difficult for us to study on the large crowd in the city.In recent years, with the rapid development of wireless communication, mobile phones have becoming more and more popular. In this paper, we proposed a novel approach to obtain the anchor points of the large urban crowd based on the mobile billing data. In addition, we took advantage of the spatial and temporal patterns of peoples behavior in the anchor points to improve the simple algorithm.

Overlapping decomposition for causal graphical modeling

Causal graphical models are developed to detect the dependence relationships between random variables and provide intuitive explanations for the relationships in complex systems. Most of existing work focuses on learning a single graphical model for all the variables. However, a single graphical model cannot accurately characterize the complicated causal relationships for a relatively large graph. In this paper, we propose the problem of estimating an overlapping decomposition for Gaussian graphical models of a large scale to generate overlapping sub-graphical models. Specifically, we formulate an objective function for the overlapping decomposition problem and propose an approximate algorithm for it. A key theory of the algorithm is that the problem of solving a κ+1 node graphical model can be reduced to the problem of solving a one-step regularization based on a solved κ node graphical model. Based on this theory, a greedy expansion algorithm is proposed to generate the overlapping subgraphs. We evaluate the effectiveness of our model on both synthetic datasets and real traffic dataset, and the experimental results show the superiority of our method.