Zhixian Yan

Semantic trajectories modeling and analysis

Focus on movement data has increased as a consequence of the larger availability of such data due to current GPS, GSM, RFID, and sensors techniques. In parallel, interest in movement has shifted from raw movement data analysis to more application-oriented ways of analyzing segments of movement suitable for the specific purposes of the application. This trend has promoted semantically rich trajectories, rather than raw movement, as the core object of interest in mobility studies. This survey provides the definitions of the basic concepts about mobility data, an analysis of the issues in mobility data management, and a survey of the approaches and techniques for: (i) constructing trajectories from movement tracks, (ii) enriching trajectories with semantic information to enable the desired interpretations of movements, and (iii) using data mining to analyze semantic trajectories and extract knowledge about their characteristics, in particular the behavioral patterns of the moving objects. Last but not least, the article surveys the new privacy issues that arise due to the semantic aspects of trajectories.

Semantic trajectories: Mobility data computation and annotation

With the large-scale adoption of GPS equipped mobile sensing devices, positional data generated by moving objects (e.g., vehicles, people, animals) are being easily collected. Such data are typically modeled as streams of spatio-temporal (x,y,t) points, called trajectories. In recent years trajectory management research has progressed significantly towards efficient storage and indexing techniques, as well as suitable knowledge discovery. These works focused on the geometric aspect of the raw mobility data. We are now witnessing a growing demand in several application sectors (e.g., from shipment tracking to geo-social networks) on understanding the semantic behavior of moving objects. Semantic behavior refers to the use of semantic abstractions of the raw mobility data, including not only geometric patterns but also knowledge extracted jointly from the mobility data and the underlying geographic and application domains information. The core contribution of this article lies in a semantic model and a computation and annotation platform for developing a semantic approach that progressively transforms the raw mobility data into semantic trajectories enriched with segmentations and annotations. We also analyze a number of experiments we did with semantic trajectories in different domains.

A hybrid model and computing platform for spatio-semantic trajectories

Spatio-temporal data management has progressed significantly towards efficient storage and indexing of mobility data. Typically such mobility data analytics is assumed to follow the model of a stream of (x,y,t) points, usually coming from GPS-enabled mobile devices. With large-scale adoption of GPS-driven systems in several application sectors (shipment tracking to geo-social networks), there is a growing demand from applications to understand the spatio-semantic behavior of mobile entities. Spatio-semantic behavior essentially means a semantic (and preferably contextual) abstraction of raw spatio-temporal location feeds. The core contribution of this paper lies in presenting a Hybrid Model and a Computing Platform for developing a semantic overlay - analyzing and transforming raw mobility data (GPS) to meaningful semantic abstractions, starting from raw feeds to semantic trajectories. Secondly, we analyze large-scale GPS data using our computing platform and present results of extracted spatio-semantic trajectories. This impacts a large class of mobile applications requiring such semantic abstractions over streaming location feeds in real systems today.

SeTraStream: semantic-aware trajectory construction over streaming movement data

Location data generated from GPS equipped moving objects are typically collected as streams of spatiotemporal 〈x, y, t〉 points that when put together form corresponding trajectories. Most existing studies focus on building ad-hoc querying, analysis, as well as data mining techniques on formed trajectories. As a prior step, trajectory construction is evidently necessary for mobility data processing and understanding, including tasks like trajectory data cleaning, compression, and segmentation so as to identify semantic trajectory episodes like stops (e.g. while sitting and standing) and moves (while jogging, walking, driving etc). However, semantic trajectory construction methods in the current literature are typically based on offline procedures, which is not sufficient for real life trajectory applications that rely on timely delivery of computed trajectories to serve real-time query answers. Filling this gap, our paper proposes a platform, namely SeTraStream, for online semantic trajectory construction. Our framework is capable of providing real-time trajectory data cleaning, compression, segmentation over streaming movement data.

SAMMPLE: Detecting Semantic Indoor Activities in Practical Settings Using Locomotive Signatures

We analyze the ability of mobile phone-generated accelerometer data to detect high-level (i.e., at the semantic level) indoor lifestyle activities, such as cooking at home and working at the workplace, in practical settings. We design a 2-Tier activity extraction framework (called SAMMPLE) for our purpose. Using this, we evaluate discriminatory power of activity structures along the dimension of statistical features and after a transformation to a sequence of individual locomotive micro-activities (e.g. sitting or standing). Our findings from 152 days of real-life behavioral traces reveal that locomotive signatures achieve an average accuracy of 77.14%, an improvement of 16.37% over directly using statistical features.

Mining complex activities in the wild via a single smartphone accelerometer

Complex activities are activities that are a combination of many simple ones. Typically, activities of daily living (ADLs) fall in this category. Complex activity recognition is an active area of interest amongst sensing and knowledge mining community today. A majority of investigations along this vein has happened in controlled experimental settings, with multiple wearable and object-interaction sensors. This provides rich observation data for mining. Recently, a new and challenging problem is to investigate recognition accuracy of complex activities in the wild using the smartphone. In this paper, we study the strength of the energy-friendly, cheap, and ubiquitous accelerometer sensor, towards recognizing complex activities in a complete real-life setting. In particular, along the lines of hierarchical feature construction, we investigate multiple higher-order features from the raw sensor stream (x, y, z, t). Further, we propose and evaluate two SVM-based fusion mechanisms (early fusion vs. late fusion) using the higher-order features. Our results show promising performance improvements in recognizing complex activities, w. r.t. prior results in such settings.

Automatic construction and multi-level visualization of semantic trajectories

With the prevalence of GPS-embedded mobile devices, enormous amounts of mobility data are being collected in the form of trajectory - a stream of (x,y,t) points. Such trajectories are of heterogeneous entities - vehicles, people, animals, parcels etc. Most applications primarily analyze raw trajectory data and extract geometric patterns. Real-life applications however, need a far more comprehensive, semantic representation of trajectories. This paper demonstrates the automatic construction and visualization capabilities of SeMiTri - a system we built that exploits 3rd party information sources containing geographic information, to semantically enrich trajectories. The construction stack encapsulates several spatio-temporal data integration and mining techniques to automatically compute and annotate all meaningful parts of heterogeneous trajectories. The visualization interface exhibits different levels of data abstraction, from low-level raw trajectories (i.e. the initial GPS trace) to high-level semantic trajectories (i.e. the sequence of interesting places where moving objects have passed and/or stayed).

Traj-ARIMA: a spatial-time series model for network-constrained trajectory

Trajectory data play an important role in analyzing real world applications that involve movement features, e.g. natural and social phenomena such as bird migration, transportation management, urban planning and tourism analysis. Such trajectory data are a speical kind of time series with another focus on the spatial dimension besides the temporal one. Traditional time series models, especially the ARIMA (Auto-Regression Integrated Moving Average) model, have provided sound theoretical backgrounds and promoted many successful applications for managing and forecasting time-relevant sequential data. This paper aims at extending the ARIMA model with spatial dimension, and further applying it for the network-constrained trajectory data. We implement and evaluate the model for trajectory database, in the context of traffic application scenario about vehicle movement constrained under a given network infrastructure. The proposed Traj-ARIMA model has many application perspectives, such as trajectory data regression and compression, outliers detection, traffic flow and vehicle speed prediction. In this paper, the major focus is on vehicle speed forecasting.

Memo-it: don't write your diary, sense it

The profusion of sensors embedded in modern mobile devices collect an increasing amount of information about the activities performed by a user. Leveraging the episodic memory model defined by neuroscientists, Memo-it exploits this information to create a multi-scale structured representation of the users activities in a semi-automated fashion, while preserving the privacy of the users data. In addition to building a digital diary of the user, the semantic approach taken by Memo-it is able to answer multi-dimensional queries, and to enable the inter-operability of memories between users.