Infrastructure Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 14
-
ItemUser-Independent Motion State Recognition Using Smartphone Sensors(MDPI, 2015-12)The recognition of locomotion activities (e.g., walking, running, still) is important for a wide range of applications like indoor positioning, navigation, location-based services, and health monitoring. Recently, there has been a growing interest in activity recognition using accelerometer data. However, when utilizing only acceleration-based features, it is difficult to differentiate varying vertical motion states from horizontal motion states especially when conducting user-independent classification. In this paper, we also make use of the newly emerging barometer built in modern smartphones, and propose a novel feature called pressure derivative from the barometer readings for user motion state recognition, which is proven to be effective for distinguishing vertical motion states and does not depend on specific users' data. Seven types of motion states are defined and six commonly-used classifiers are compared. In addition, we utilize the motion state history and the characteristics of people's motion to improve the classification accuracies of those classifiers. Experimental results show that by using the historical information and human's motion characteristics, we can achieve user-independent motion state classification with an accuracy of up to 90.7%. In addition, we analyze the influence of the window size and smartphone pose on the accuracy.
-
ItemAPFiLoc: An Infrastructure-Free Indoor Localization Method Fusing Smartphone Inertial Sensors, Landmarks and Map Information(MDPI, 2015-10)The utility and adoption of indoor localization applications have been limited due to the complex nature of the physical environment combined with an increasing requirement for more robust localization performance. Existing solutions to this problem are either too expensive or too dependent on infrastructure such as Wi-Fi access points. To address this problem, we propose APFiLoc-a low cost, smartphone-based framework for indoor localization. The key idea behind this framework is to obtain landmarks within the environment and to use the augmented particle filter to fuse them with measurements from smartphone sensors and map information. A clustering method based on distance constraints is developed to detect organic landmarks in an unsupervised way, and the least square support vector machine is used to classify seed landmarks. A series of real-world experiments were conducted in complex environments including multiple floors and the results show APFiLoc can achieve 80% accuracy (phone in the hand) and around 70% accuracy (phone in the pocket) of the error less than 2 m error without the assistance of infrastructure like Wi-Fi access points.
-
ItemStochastic modelling of GPS phase observations for improved quality estimation(Informa UK Limited, 2002-01-01)
-
ItemSpatial Data Infrastructure: an integrated architecture for Location Based Services( 2002-12)Trends in wireless communication towards the development of smaller, faster, cheaper devices are contributing to a radical change in the spatial information user base. With the ability to access information using a mobile phone or a Mobile Internet enabled Personal Digital Assistant, combined with the capability to determine the position of mobile devices, a range of applications known as Location Based Services (LBS) are emerging. These services provide relevant information to users based on the position of their mobile device. This information can be both spatially and non-spatially related, but must be presented in a useful way. The broader issues of LBS, that revolve around enabling a range of users to access spatial information, can be considered under the domain of Spatial Data Infrastructures (SDI). Since the SDI components of people, data, access networks, policy and technical standards parallel the issues of LBS, it is proposed that the SDI concept be augmented to support the development and deployment of wireless LBS applications. This paper describes a proposed case study approach for LBS development so as to determine how SDI needs to adapt in order to support these emerging applications.
-
ItemSpatial Data Infrastructure requirements for mobile location based journey planning(Blackwell Publishing Ltd., 2003-12)A growing number of services are now being offered over mobile devices. They typically combine positioning technology, wireless technology and spatial analysis methods applied to detailed geographical, time based data to offer services in support of time critical, spatial, mobile decision making. A collection of research issues need to be addressed in the successful delivery of such services that extend beyond issues of sophisticated network algorithms. Specifically, careful attention needs to be given to: (1) people and user environments; (2) access to networks; (3) policy, privacy and liability; (4) standards and interoperability; and (5) data quality. Spatial Data Infrastructure (SDI) is the collective term for these interconnected issues and has been a traditional area of research associated with geographic information science. In this paper the particular SDI requirements for the successful delivery of Location Based Services (LBS) are explored through the development of a prototype LBS for journey planning. The initial implementation and testing of this prototype has revealed that the SDI context is well suited as a framework within which to examine the related LBS issues. From a more technical perspective, the testing has revealed that data structure and the means by which large data sets are mined (in order to gather information to present to users) is critical to the success of timely information delivery over limited bandwidth media.
-
ItemAssessing Spatial Data Infrastructure Architecture for Integration withWireless Location Services( 2001)Spatial Data Infrastructures (SDIs) have been identified as a mechanism through which complete and consistent spatial data sets can be accessed and retrieved. Whilst SDIs have been developing, wireless communication technologies have been undergoing a rapid evolution. The convergence of wireless communications, positioning technology and SDIs are providing new facilities, new applications and as a result, new challenges for spatial data providers and users. To capitalise on the opportunities presented through the merger of these key areas, the design of SDIs may require modification. Naturally, different applications will have different spatial data requirements, however it is envisaged that there will be common infrastructure requirements (such as data sets, query and delivery mechanisms) that will be applicable for a range of wireless applications. One of the most important issues in relation to delivering information to wireless users is that of data currency. It is imperative that a mobile user be provided with accurate, up to date data. Whilst this is also an important issue for non-mobile users, it is particularly important for users 'on the move'. Thus rather than individual organisations duplicating and maintaining data sets, providing access through a standard SDI would be most beneficial. Infrastructure requirements for Australian wireless applications that utilise spatial information will be determined through the development of a personal navigation system for the visually impaired. The accuracy and reliability requirements of a navigation solution for a visually impaired person are much greater than for a sighted person, thus the rigour of the data content and delivery methods is of paramount importance. This paper overviews the components and issues that need to be considered when building wireless applications that utilise location information. The prototype development will also be discussed to highlight the infrastructure requirements necessary for the proposed technology combination.
-
ItemLocation based services-the underlying technology( 2001)For centuries, people have been concerned with their spatial location and surroundings onEarth. The methods of describing routes and areas of space by one person to another havealways been a function of the available resources. Today these resources include mobilephones, personal digital assistants and palmtop computers, providing people with detailedspatial information whilst 'on the move'.To the Geomatics industry, the potential created by the convergence of wirelesscommunication, positioning technology and Spatial Data Infrastructures (SDIs) is tremendous.It is now possible to deliver relevant information where it is needed most. Time critical andlocation dependent information services have been identified as potentially successfulapplication areas in this domain. Not only will field workers be empowered by such services,but the general citizen will also benefit. There are many examples in Europe and more recentlyin Australia where such benefits are being realised. Most of these examples are termedLocation Based Services (LBS). The underlying technologies of LBS along with their synergywith wireless communication, positioning technology and SDI will be examined.
-
ItemStochastic modelling of GPS phase observations for improved quality estimation( 2002)Data quality information has been recognised as essential in assessing the fitness for use of any spatial dataset, and fundamental to enabling efficient and effective data integration through spatial data infrastructure (SDI). Missing or inaccurate data quality information can result in inappropriate use of the data with associated consequences of poor decision making, reduced utility and decreased market value. The increasing use of the Global Positioning System (GPS) as a primary data acquisition source for spatial databases highlights the significance of this problem. At present the measures of quality for GPS derived coordinates given by commercial software packages tend to be unrealistic and are more often than not optimistic. This is because not all of the systematic and random errors present in the observations are fully modelled through the standard functional or stochastic models used. This paper presents some of the current problems in identifying the quality of GPS data as derived from commercial processing software. Common GPS processing strategies are reviewed in the context of error modelling and data quality. Finally, current research activities into strategies for maximizing GPS data quality are presented.
-
ItemQuality Control and Integrity Monitoring of the Victorian GPS Reference Station Network(International Federation of Surveyors, 2002)
-
ItemSpatial Data Infrastructure concepts for location based services-a case study in public transportation( 2002)The introduction of wireless devices that facilitate communication 'anywhere, anytime' has been readilyembraced by society. Whilst offering alternative communication means with enhanced freedom and security thanthe fixed line telephone network, mobile phones are still limited by factors such as network coverage andhandset functionality (Cox 1996; Singleton 1983; Solymar 1999). Recent technological trends are resulting inthe functionality of organisation and assistant devices (such as Personal Digital Assistants) being combined withwireless communication methods (both voice and data based) one device can be used to record events, ring oremail colleagues and surf the Internet. Whilst network computing and the Internet in particular have evolved toremove the geographical emphasis of users, this new "nomadic computing and communications paradigm"(Leiner et al. 2000 WWW site) is reversing the situation, with user location now playing a critical role in theaccess and dissemination of information. The inherent link between wireless communication and location has thepotential to provide users with a range of services from personal safety (e.g. roadside assistance) through toconvenience or information services (e.g. guiding users from their current location to a restaurant of choice).Such services can be classified as Location Based Services (LBS).Location Based Services can rely on many diverse data sets, from relatively static road network information todynamic, real-time traffic flow information. Currently LBS developers must organise agreements betweenindividual data custodians, integrate these data sets and develop the application essentially establishing theirown infrastructure. To achieve a data sharing environment some form of framework is critical; this frameworkmust provide guidance on issues such as ownership, reuse, access, quality and cost. Spatial Data Infrastructures(SDI) are emerging as this framework and as a result, becoming useful to