: This thesis applies neural network feature selection techniques to multivariate time series data to improve prediction of a target time series. Two approaches to feature selection are used. First, a subset enumeration method is used to determine which financial indicators are most useful for aiding in prediction of the S&P 500 futures daily price. The candidate indicators evaluated include RSI, Stochastics and several moving averages. Results indicate that the Stochastics and RSI indicators result in better prediction results than the moving averages. The second approach to feature selection is calculation of individual saliency metrics. A new decision boundary-based individual saliency metric, and a classifier independent saliency metric are developed and tested. Ruck's saliency metric, the decision boundary based saliency metric, and the classifier independent saliency metric are compared for a data set consisting of the RSI and Stochastics indicators as well as delayed closing price values. The decision based metric and the Ruck metric results are similar, but the classifier independent metric agrees with neither of the other metrics. The nine most salient features, determined by the decision boundary based metric, are used to train a neural network and the results are presented and compared to other published results. (AN)

/pdf/nonlinear-time-series-analysis-1j3a35n4y3.pdf

Nonlinear Time Series Analysis.

The availability of location information has become a key factor in today's communications systems allowing location based services. In outdoor scenarios, the mobile terminal position is obtained with high accuracy thanks to the global positioning system (GPS) or to the standalone cellular systems. However, the main problem of GPS and cellular systems resides in the indoor environment and in scenarios with deep shadowing effects where the satellite or cellular signals are broken. In this paper, we survey different technologies and methodologies for indoor and outdoor localization with an emphasis on indoor methodologies and concepts. Additionally, we discuss in this review different localization-based applications, where the location information is critical to estimate. Finally, a comprehensive discussion of the challenges in terms of accuracy, cost, complexity, security, scalability, etc. is given. The aim of this survey is to provide a comprehensive overview of existing efforts as well as auspicious and anticipated dimensions for future work in indoor localization techniques and applications.

Recent Advances in Indoor Localization: A Survey on Theoretical Approaches and Applications

Location information is an important source of context for ubiquitous computing systems. This paper looks at how a foot-mounted inertial unit, a detailed building model, and a particle filter can be combined to provide absolute positioning, despite the presence of drift in the inertial unit and without knowledge of the user's initial location. We show how to handle multiple floors and stairways, how to handle symmetry in the environment, and how to initialise the localisation algorithm using WiFi signal strength to reduce initial complexity.We evaluate the entire system experimentally, using an independent tracking system for ground truth. Our results show that we can track a user throughout a 8725 m2 building spanning three floors to within 0.5m 75% of the time, and to within 0.73 m 95% of the time.

/pdf/pedestrian-localisation-for-indoor-environments-29fhcn12xt.pdf

Pedestrian localisation for indoor environments

.............................................................................................................................................................. 6 1 Introduction ............................................................................................................................................. 7 1.1 Motivation .......................................................................................................................................................... 7 1.2 Previous Surveys ............................................................................................................................................. 8 1.3 Overview of Technologies ........................................................................................................................... 9 1.4 Indoor Positioning Applications ............................................................................................................ 11 1.5 Structure of this Work ............................................................................................................................... 14 2 User Requirements ............................................................................................................................. 15 2.1 Requirements Parameters Overview .................................................................................................. 15 2.2 Positioning Requirements Parameters Definition ......................................................................... 17 2.3 Man Machine Interface Requirements ................................................................................................ 19 2.4 Security and Privacy Requirements ..................................................................................................... 20 2.5 Costs .................................................................................................................................................................. 20 2.6 Generic Derivation of User Requirements......................................................................................... 20 2.7 Requirements for Selected Indoor Applications ............................................................................. 21 3 Definition of Terms ............................................................................................................................. 25 3.1 Disambiguation of Terms for Positioning .......................................................................................... 25 3.2 Definition of Technical Terms ................................................................................................................ 27 3.3 The Basic Measuring Principles ............................................................................................................. 29 3.4 Positioning Methods ................................................................................................................................... 31 4 Cameras .................................................................................................................................................. 34 4.1 Reference from 3D Building Models .................................................................................................... 35 4.2 Reference from Images .............................................................................................................................. 36 4.3 Reference from Deployed Coded Targets .......................................................................................... 37 4.4 Reference from Projected Targets ........................................................................................................ 38 4.5 Systems without Reference ..................................................................................................................... 39 4.6 Reference from Other Sensors ............................................................................................................... 40 4.7 Summary on Camera Based Indoor Positioning Systems ........................................................... 40 5 Infrared ................................................................................................................................................... 42 5.1 Active Beacons .............................................................................................................................................. 42 5.2 Imaging of Natural Infrared Radiation ............................................................................................... 43 5.3 Imaging of Artificial Infrared Light ....................................................................................................... 43 5.4 Summary on Infrared Indoor Positioning Systems ....................................................................... 44

Indoor Positioning Technologies

We present a new method to accurately locate persons indoors by fusing inertial navigation system (INS) techniques with active RFID technology. A foot-mounted inertial measuring units (IMUs)-based position estimation method, is aided by the received signal strengths (RSSs) obtained from several active RFID tags placed at known locations in a building. In contrast to other authors that integrate IMUs and RSS with a loose Kalman filter (KF)-based coupling (by using the residuals of inertial- and RSS-calculated positions), we present a tight KF-based INS/RFID integration, using the residuals between the INS-predicted reader-to-tag ranges and the ranges derived from a generic RSS path-loss model. Our approach also includes other drift reduction methods such as zero velocity updates (ZUPTs) at foot stance detections, zero angular-rate updates (ZARUs) when the user is motionless, and heading corrections using magnetometers. A complementary extended Kalman filter (EKF), throughout its 15-element error state vector, compensates the position, velocity and attitude errors of the INS solution, as well as IMU biases. This methodology is valid for any kind of motion (forward, lateral or backward walk, at different speeds), and does not require an offline calibration for the user gait. The integrated INS+RFID methodology eliminates the typical drift of IMU-alone solutions (approximately 1% of the total traveled distance), resulting in typical positioning errors along the walking path (no matter its length) of approximately 1.5 m.

/pdf/accurate-pedestrian-indoor-navigation-by-tightly-coupling-1bj85o1lov.pdf

Accurate Pedestrian Indoor Navigation by Tightly Coupling Foot-Mounted IMU and RFID Measurements

Indoor positioning systems based on wireless LAN (WLAN) are being widely investigated in academia and industry. Meanwhile, the emerging low-cost MEMS sensors can also be used as another independent positioning source. In this paper, we propose a pedestrian tracking framework based on particle filters, which extends the typical WLAN-based indoor positioning systems by integrating low-cost MEMS accelerometer and map information. Our simulation and real world experiments indicate a remarkable performance improvement by using this fusion framework.

/pdf/wlan-based-pedestrian-tracking-using-particle-filters-and-3atf7d0i45.pdf

WLAN-Based Pedestrian Tracking Using Particle Filters and Low-Cost MEMS Sensors

Common approaches for indoor positioning based on cellular communication systems use as measurements the received signal strength (RSS). In order to work properly, such a system often requires many calibration points before its start. This paper presents a two-fold approach achieving high indoor localization accuracies without requiring too many calibration points. The basic idea is to use an initial propagation model with few parameters, which can be adapted by a few measurements, e.g. mutual measurements of access points. Then the model is refined by incorporating additional parameters and using online learning. Investigations on the requirements and potentials of different approaches and results for DECT and WLAN setups are given. The first approach uses predefined paths that should be passed through by a service technician with measurement equipment. The second approach uses a Kohonen-like learning algorithm to adapt the model on-the-fly. For both approaches linear propagation models and more involved dominant path models incorporating map information are applied for the initialization.

Initialization and Online-Learning of RSS Maps for Indoor / Campus Localization

Location estimation in indoor/campus environments has attracted much interest for its broad applications. Many applications (e.g. personnel security) require not only the 2-D coordinate but also the floor index where the mobile users are situated. However, most of the current location systems cannot provide the floor information accurately and robustly. In this paper, we propose a 3-D localization scheme which fuses the barometric sensor with Wireless LAN (WLAN) signals and building information. Our experiments show that this fusion scheme can both identify the floor index without errors and improve the horizontal localization accuracy. Moreover, since the barometric sensor is quite simple and cheap, it would bring almost no increase in system costs.

/pdf/fusion-of-barometric-sensors-wlan-signals-and-building-4wh2mologz.pdf

Fusion of Barometric Sensors, WLAN Signals and Building Information for 3--D Indoor/Campus Localization

Location-aware systems are receiving more and more interest in both academia and industry due to their promising prospective in a broad category of so-called Location-Based-Services (LBS). The map interface plays a crucial role in the location-aware systems, especially for indoor scenarios. This paper addresses the usage of map information in a Wireless LAN (WLAN)-based indoor navigation system. We describe the benefit of using map information in multiple algorithms of the system, including radio-map generation, tracking, semantic positioning and navigation. Then we discuss how to represent or model the indoor map to fulfill the requirements of intelligent algorithms. We believe that a vector-based multi-layer representation is the best choice for indoor location-aware system.

/pdf/enhancing-the-map-usage-for-indoor-location-aware-systems-3tscz8s2f6.pdf

Enhancing the map usage for indoor location-aware systems

Indoor WLAN positioning should be modeled as a nonlinear and non-Gaussian dynamic system due to the complex indoor environment, radio propagation and motion behaviour. The aim of this paper is to analyze different filtering strategies for real life indoor WLAN positioning systems. The performance criteria for the comparison are the mean of localization errors and computational complexity. Three nonlinear filters are analyzed: Fourier density approximation (FF), particle filter (PF) and grid-based filter (GF), which are representatives for deterministic and random density approximation approaches. Our experimental results help to choose the appropriate filtering techniques under different resource limitations.

/pdf/performance-comparison-of-nonlinear-filters-for-indoor-wlan-1atnp9xwgn.pdf

Hui Wang

Papers

WLAN-Based Pedestrian Tracking Using Particle Filters and Low-Cost MEMS Sensors

Initialization and Online-Learning of RSS Maps for Indoor / Campus Localization

Fusion of Barometric Sensors, WLAN Signals and Building Information for 3--D Indoor/Campus Localization

Enhancing the map usage for indoor location-aware systems

Performance comparison of nonlinear filters for indoor WLAN positioning