Kuien Liu

Effective map-matching on the most simplified road network

The effectiveness of map-matching algorithms highly depends on the accuracy and correctness of underlying road networks. In practice, the storage capacity of certain hardware, e.g. mobile devices and embedded systems, is sometimes insufficient to maintain a large digital map for map-matching. Unfortunately, most existing map-matching approaches consider little about this problem. They only apply to environments with information-rich maps, but turn out to be unacceptable for map-matching on simplified road networks. In this paper, we propose a novel map-matching algorithm called Passby to work on most simplified road networks. The storage size of a digital map in disk or memory can be greatly reduced after the simplification. Even under the most simplified situation, i.e., each road segment only consists of a couple of intersection points and omits any other information of it, the experimental results on real dataset show that our Passby algorithm significantly maintains high matching accuracy. Benefiting from the small size of map, simple index structure and heuristic foresight strategy, Passby improves matching accuracy as well as efficiency.

MOIR/MT: monitoring large-scale road network traffic in real-time

Floating Car Data (FCD) provides an economic complement to infrastructure-based traffic monitoring systems. Based on our previous MOIR platform [5], we use FCD as the data source for large-scale real-time traffic monitoring. This new function brings a challenge of efficiently handling of streaming data from a very large number of moving objects. Server overload problems can occur when a system fails to process data and queries in real-tme, which can lead to critical issues such as unbounded delay accumulation, lost monitoring accuracy or lack of spontaneity. These problems can be addressed by adopting suitable load dropping decisions. In this work, we demonstrate several load shedding techniques, focusing on decision-making based on data attributes. With the end results being quantified and visualized using real data for a large city, this proof-of-concept system provides a convincing way of validating our ideas.

Human Mobility Prediction and Unobstructed Route Planning in Public Transport Networks

With the increasing availability of human-tracking data (e.g., Public transport IC card data, trajectory data, etc.), human mobility prediction is increasingly important. In this paper, we study a novel problem of using human-tracking data to predict human mobility and to detect over-crowded stations in public transport networks, and then finding unobstructed routes to go around these over-crowded stations. We believe that this study can bring significant benefits to users in many popular mobile applications such as route planning and recommendation, urban computing, and location based services in general. This problem is challenged by two difficulties: (1) how to detect crowded stations effectively, and (2) how to find unobstructed routes in public transport networks efficiently. To overcome these difficulties, we propose three human-mobility prediction methods based on uniform distribution, standard normal distribution, and priority ranking, respectively, to predict human mobility and to detect over-crowded stations. Then, we develop an efficient algorithm based on network expansion to find unobstructed routes in public transport networks. The performance of the developed algorithms has been verified by extensive experiments.

User oriented trajectory similarity search

Trajectory similarity search studies the problem of finding a trajectory from the database such the found trajectory most similar to the query trajectory. Past research mainly focused on two aspects: shape similarity search and semantic similarity search, leaving personalized similarity search untouched. In this paper, we propose a new query which takes users preference into consideration to provide personalized searching. We define a new data model for this query and identify the efficiency issue as the key challenge: given a user specified trajectory, how to efficiently retrieve the most similar trajectory from the database. By taking advantage of the spatial localities, we develop a two-phase algorithm to tame this challenge. Two optimized strategies are also developed to speed up the query process. Both the theoretical analysis and the experiments demonstrate the high efficiency of the proposed method.

Compressing large scale urban trajectory data

With the increasing size of trajectory data generated by location-based services and applications which are built from inexpensive GPS-enabled devices in urban environments, the need for compressing large scale trajectories becomes obvious. This paper proposes a scalable urban trajectory compression scheme (SUTC) that can compress a set of trajectories collectively by exploiting common movement behaviors among the urban moving objects such as vehicles and smartphone users. SUTC exploits that urban objects moving in similar behaviors naturally, especially large-scale of human and vehicle which are moving constrained by some geographic context (e.g., road networks or routes). To exploit redundancy across a large set of trajectories, SUTC first transforms trajectory sequences from Euclidean space to network-constrained space and represents each trajectory with a sequence of symbolic positions in textual domain. Then, SUTC performs compression by encoding the symbolic sequences with general-purpose compression methods. The key challenge in this process is how to transform the trajectory data from spatio-temporal domain to textual domain without introducing unbounded error. We develop two strategies (i.e., velocity-based symbolization, and beacon-based symbolization) to enrich the symbol sequences and achieves high compression ratios by sacrificing a little bit the decoding accuracy. Besides, we also optimize the organization of trajectory data in order to adapt it to practical compression algorithms, and increase the efficiency of compressing processes. Our experiments on real large-scale trajectory datasets demonstrate the superiority and feasibility of the our proposed algorithms.

On Efficient Map-Matching According to Intersections You Pass By

Map-matching is a hot research topic as it is essential for Moving Object Database and Intelligent Transport Systems. However, existing map-matching techniques cannot satisfy the increasing requirement of applications with massive trajectory data, e.g., traffic flow analysis and route planning. To handle this problem, we propose an efficient map-matching algorithm called Passby. Instead of matching every single GPS point, we concentrate on those close to intersections and avoid the computation of map-matching on intermediate GPS points. Meanwhile, this efficient method also increases the uncertainty for determining the real route of the moving object due to less availability of trajectory information. To provide accurate matching results in ambiguous situations, e.g., road intersections and parallel paths, we further propose Passby*. It is based on the multi-hypothesis technique and manages to maintain a small but complete set of possible solutions and eventually choose the one with the highest probability. The results of experiments performed on real datasets demonstrate that Passby* is efficient while maintaining the high accuracy.

Discovering hot topics from geo-tagged video

As video data generated by users boom continuously, making sense of large scale data archives is considered as a critical challenge for data management. Most existing learning techniques that extract signal-level contents from video data struggle to scale due to efficiency limits. With the development of pervasive positioning techniques, discovering hot topics from multimedia data by their geographical tags has become practical: videos taken by advanced cameras are associated with GPS locations, and geo-tagged videos from YouTube can be identified by their associated GPS locations on Google Maps. It enables us to know the cultures, scenes, and human behaviors from videos based on their spatio-temporal distributions. However, meaningful topic discovery requires an efficient clustering approach, through which coherent topics can be detected according to particular geographical regions without out-of-focus effects. To handle this problem, this paper presents a filter-refinement framework to discover hot topics corresponding to geographical dense regions, and then introduces two novel metrics to refine unbounded hot regions, together with a heuristic method for setting rational thresholds on these metrics. The results of extensive experiments prove that hot topics can be efficiently discovered by our framework, and more compact topics can be achieved after using the novel metrics.

SharkDB: an in-memory column-oriented storage for trajectory analysis

The last decade has witnessed the prevalence of sensor and GPS technologies that produce a high volume of trajectory data representing the motion history of moving objects. However some characteristics of trajectories such as variable lengths and asynchronous sampling rates make it difficult to fit into traditional database systems that are disk-based and tuple-oriented. Motivated by the success of column store and recent development of in-memory databases, we try to explore the potential opportunities of boosting the performance of trajectory data processing by designing a novel trajectory storage within main memory. In contrast to most existing trajectory indexing methods that keep consecutive samples of the same trajectory in the same disk page, we partition the database into frames in which the positions of all moving objects at the same time instant are stored together and aligned in main memory. We found this column-wise storage to be surprisingly well suited for in-memory computing since most frames can be stored in highly compressed form, which is pivotal for increasing the memory throughput and reducing CPU-cache miss. The independence between frames also makes them natural working units when parallelizing data processing on a multi-core environment. Lastly we run a variety of common trajectory queries on both real and synthetic datasets in order to demonstrate advantages and study the limitations of our proposed storage.

Hippo: An enhancement of pipeline-aware in-memory caching for HDFS

In the age of big data, distributed computing frameworks tend to coexist and collaborate in pipeline using one scheduler. While a variety of techniques for reducing I/O latency have been proposed, these are rarely specific for the whole pipeline performance. This paper proposes memory management logic called “Hippo” which targets distributed systems and in particular “pipelined” applications that might span differing big data frameworks. Though individual frameworks may have internal memory management primitives, Hippo proposes to make a generic framework that works agnostic of these highlevel operations. To increase the hit ratio of in-memory cache, this paper discusses the granularity of caching and how Hippo leverages the job dependency graph to make memory retention and pre-fetching decisions. Our evaluations demonstrate that job dependency is essential to improve the cache performance and a global cache policy maker, in most cases, significantly outperforms explicit caching by users.

Benchmarking big data for trip recommendation

The availability of massive trajectory data collected from GPS devices has received significant attentions in recent years. A hot topic is trip recommendation, which focuses on searching trajectories that connect (or are close to) a set of query locations, e.g., several sightseeing places specified by a traveller, from a collection of historic trajectories made by other travellers. However, if we know little about the sample coverage of trajectory data when developing an application of trip recommendation, it is difficult for us to answer many practical questions, such as 1) how many (future) queries can be supported with a given set of raw trajectories? 2) how many trajectories are required to achieve a good-enough result? 3) how frequent the update operations need to be performed on trajectory data to keep it long-term effective? In this paper, we focus on studying the overall quality of trajectory data from both spatial and temporal domains and evaluate proposed methods with a real big trajectory dataset. Our results should be useful for both the development of trip recommendation systems and the improvement of trajectory-searching algorithms.