Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

This document provides updates to IEEE Std 802.16's MIB for the MAC, PHY and asso- ciated management procedures in order to accommodate recent extensions to the standard.

IEEE Standard for Local and Metropolitan Area Networks Part 16: Air Interface for Fixed Broadband Wireless Access Systems Draft Amendment: Management Information Base Extensions

The spatial features of emitted wireless signals are the basis of location distinction and determination for wireless indoor localization. Available in mainstream wireless signal measurements, the Received Signal Strength Indicator (RSSI) has been adopted in vast indoor localization systems. However, it suffers from dramatic performance degradation in complex situations due to multipath fading and temporal dynamics. Break-through techniques resort to finer-grained wireless channel measurement than RSSI. Different from RSSI, the PHY layer power feature, channel response, is able to discriminate multipath characteristics, and thus holds the potential for the convergence of accurate and pervasive indoor localization. Channel State Information (CSI, reflecting channel response in 802.11 a/g/n) has attracted many research efforts and some pioneer works have demonstrated submeter or even centimeter-level accuracy. In this article, we survey this new trend of channel response in localization. The differences between CSI and RSSI are highlighted with respect to network layering, time resolution, frequency resolution, stability, and accessibility. Furthermore, we investigate a large body of recent works and classify them overall into three categories according to how to use CSI. For each category, we emphasize the basic principles and address future directions of research in this new and largely open area.

From RSSI to CSI: Indoor Localization via Channel Response, A survey on indoor localization using PHY-layer information

Gaussian process (GP) regression has been widely used in supervised machine learning due to its flexibility and inherent ability to describe uncertainty in function estimation. In the context of control, it is seeing increasing use for modeling of nonlinear dynamical systems from data, as it allows the direct assessment of residual model uncertainty. We present a model predictive control (MPC) approach that integrates a nominal system with an additive nonlinear part of the dynamics modeled as a GP. We describe a principled way of formulating the chance-constrained MPC problem, which takes into account residual uncertainties provided by the GP model to enable cautious control. Using additional approximations for efficient computation, we finally demonstrate the approach in a simulation example, as well as in a hardware implementation for autonomous racing of remote-controlled race cars with fast sampling times of 20 ms, highlighting improvements with regard to both performance and safety over a nominal controller.

/pdf/cautious-model-predictive-control-using-gaussian-process-22h61bh9m4.pdf

Cautious Model Predictive Control Using Gaussian Process Regression

Learning-based methods have been successful in solving complex control tasks without significant prior knowledge about the system. However, these methods typically do not provide any safety guarantees, which prevents their use in safety-critical, real-world applications. In this paper, we present a learning-based model predictive control scheme that can provide provable high-probability safety guarantees. To this end, we exploit regularity assumptions on the dynamics in terms of a Gaussian process prior to construct provably accurate confidence intervals on predicted trajectories. Unlike previous approaches, we do not assume that model uncertainties are independent. Based on these predictions, we guarantee that trajectories satisfy safety constraints. Moreover, we use a terminal set constraint to recursively guarantee the existence of safe control actions at every iteration. In our experiments, we show that the resulting algorithm can be used to safely and efficiently explore and learn about dynamic systems.

Learning-Based Model Predictive Control for Safe Exploration

This paper reports the development of a practical visible light positioning (VLP) system using received signal strength. The indoor localization system is accurate and easy to train and calibrate despite using fingerprinting technique. The VLP system consists of cheap photodiode-based receiver and consumer grade LED luminaires. The impact of distance metrics used to compute the weights of the weighted $K$ -nearest neighbor (WKNN) algorithm on the localization accuracy of the VLP is investigated. Experimental results show that square chord distance is the most robust and accurate metric and significantly outperforms the commonly used Euclidean distance metric. A room-scale implementation shows that a mean error of 2.2 cm and a 90-percentile error of 4.9 cm within a 3.3 $\text {m} \times 2.1$ m 2-D floor space are achievable. However, the high localization accuracy comes at the cost of requiring 187 offline measurements to construct the fingerprint database. A method for estimating an optical propagation model using only a handful of measurements is developed to address this problem. This leads to the creation of a dense and accurate fingerprinting database through fabricated data. The performance of the VLP system does not degrade noticeably when the localization is performed with the fabricated data. A mean error of 2.7 cm and a 90-percentile error of 5.7 cm are achievable with only 12 offline measurements.

An Accurate Visible Light Positioning System Using Regenerated Fingerprint Database Based on Calibrated Propagation Model

The Model Predictive Control (MPC) trajectory tracking problem of an unmanned quadrotor with input and output constraints is addressed. In this article, the dynamic models of the quadrotor are obtained purely from operational data in the form of probabilistic Gaussian Process (GP) models. This is different from conventional models obtained through Newtonian analysis. A hierarchical control scheme is used to handle the trajectory tracking problem with the translational subsystem in the outer loop and the rotational subsystem in the inner loop. Constrained GP based MPC are formulated separately for both subsystems. The resulting MPC problems are typically nonlinear and non-convex. We derived a GP based local dynamical model that allows these optimization problems to be relaxed to convex ones which can be efficiently solved with a simple active-set algorithm. The performance of the proposed approach is compared with an existing unconstrained Nonlinear Model Predictive Control (NMPC) algorithm and an existing constrained nonlinear GP based MPC algorithm. In the first comparison, simulation results show that the two approaches exhibit similar trajectory tracking performance. However, our approach has the advantage of incorporating constraints on the control inputs. In the second comparison, simulation results demonstrate that our approach only requires 20% of the computational time for the existing nonlinear GP based MPC.

Gaussian Process Model Predictive Control of an Unmanned Quadrotor

Air pollution poses significant risk to environment and health. Air quality monitoring stations are often confined to a small number of locations due to the high cost of the monitoring equipment. They provide a low fidelity picture of the air quality in the city; local variations are overlooked. However, recent developments in low-cost sensor technology and wireless communication systems like Internet of Things (IoT) provide an opportunity to use arrayed sensor networks to measure air pollution, in real time, at a large number of locations. This article reports the development of a novel low-cost sensor node that utilizes cost-effective electrochemical sensors to measure carbon monoxide (CO) and nitrogen dioxide (NO2) concentrations and an infrared sensor to measure particulate matter (PM) levels. The node can be powered by either solar-recharged battery or mains supply. It is capable of long-range, low power communication over public or private long-range wide area network (LoRaWAN) IoT network and short-range high data rate communication over Wi-Fi. The developed sensor nodes were co-located with an accurate reference CO sensor for field calibration. The low-cost sensors’ data, with offset and gain calibration, show good correlation with the data collected from the reference sensor. Multiple linear regression (MLR)-based temperature and humidity correction results in mean absolute percentage error (MAPE) of 48.71% and $R^{2}$ of 0.607 relative to the reference sensor’s data. Artificial neural network (ANN)-based calibration shows the potential for significant further improvement with MAPE of 38.89% and $R^{2}$ of 0.78 for leave-one-out cross-validation.

Low Cost Sensor With IoT LoRaWAN Connectivity and Machine Learning-Based Calibration for Air Pollution Monitoring

Accurate, reliable indoor localization or positioning is the key enabler for location-based services. Indoor localization can be broadly classified into two distinct categories. Active localization entails tracking a tag attached to or carried by the target. Passive localization, on the other hand, involves positioning a device-free or untagged target. While passive or device-free localization is comparatively more difficult to achieve, it is the preferred option for many applications. Vision-based techniques can accurately localize an untagged target. However, privacy is a significant concern and thus have limited usability for many applications, especially in noncommercial and residential settings. Passive localization using radio frequency (RF) or wireless sensing is an unobtrusive option and has seen extensive research efforts in recent years leading to a saturated research field but no consensus solution. Researchers have been investigating alternative solutions that can facilitate robust passive localization. The rapid proliferation of Internet of Things (IoT) is bringing ubiquitous networked devices and ambient sensors into modern buildings. The consequential pervasive ambient intelligence and signals of opportunity can enable unobtrusive device-free positioning. This article presents a comprehensive review of non-RF solutions covering visible light-, infrared-, physical excitation-and electric field sensing-based techniques. Limitations of the state-of-the-art and potential future research directions are also outlined.

Device-Free Localization: A Review of Non-RF Techniques for Unobtrusive Indoor Positioning

This article reports a novel visible light positioning (VLP) system and the associated experimental results. The developed VLP system is completely passive as it does not require a tracked object to carry any active device or tag. At the same time, it does not require any modification to the existing lighting infrastructure. The positioning system, termed Watchers on the Wall (WoW), localizes a target based on measuring the change it creates in the received signal strength (RSS) of the ambient light recorded at an array of light-sensors embedded in the wall. A prototype system has been implemented and tested to investigate the performance of the proposed approach with regard to localization and tracking. The experimental results show that the median and 90-percentile localization errors of 7 and 21 cm, respectively, can be achieved for a 2 m $\times3.6$ m testbed. The effect of various parameters like the height of placement and the number of light-sensors, as well as the size of the fingerprint database, has also been studied. The impact of various distance metrics on the localization performance of the weighted $K$ -nearest neighbor (WKNN) classifier has been investigated. It has been found that two distance metrics outperform the commonly employed Euclidean metric. The experimental results also demonstrated that the developed system could track a mobile target along multiple routes with a median error of 12 cm.

Fakhrul Alam

Papers

An Accurate Visible Light Positioning System Using Regenerated Fingerprint Database Based on Calibrated Propagation Model

Gaussian Process Model Predictive Control of an Unmanned Quadrotor

Low Cost Sensor With IoT LoRaWAN Connectivity and Machine Learning-Based Calibration for Air Pollution Monitoring

Device-Free Localization: A Review of Non-RF Techniques for Unobtrusive Indoor Positioning

Watchers on the Wall: Passive Visible Light-Based Positioning and Tracking With Embedded Light-Sensors on the Wall