Estimating residual variance in random forest regression

Random forest, a data-mining technique which uses multiple classification or regression trees, is a popular algorithm used for prediction. Inference and goodness-of-fit assessment, however, may require an estimator of variability; in many applications the residual variance is of primary interest. This paper proposes two estimators of residual variance for random forest regression that take advantage of byproducts of the algorithm. The first estimator is based on the residual sum of squares from a random forest fit and uses a bootstrap bias correction. The second estimator is a difference-based estimator that uses proximity measures as weights. The estimators are evaluated through Monte Carlo simulations. Applications of the methods to the problem of assessing the relative variability of males and females on cognitive and achievement tests are discussed, and the methods are applied to estimate the residual variance in test scores for male and female students on the mathematics portion of the 2007 Arizona Instrument to Measure Standards.     

An Active Disturbance Rejection Approach to Leader‐Follower Controlled Formation

This article describes the design of a linearizing, observer‐based, robust dynamic feedback control scheme for output reference trajectory tracking tasks in a leader‐follower non‐holonomic car formation problem. The approach is based on the cars' kinematic models. A radical simplification in the form of a global ultra‐model is proposed on the follower's exact open loop position tracking error dynamics obtained via flatness considerations. This results in a system described by an additively disturbed set of two, second order integrators with non‐linear velocity dependent control input gain matrix. The unknown additive disturbances are modeled as absolutely uniformly bounded time signals which may be locally approximated by arbitrary elements of a sufficiently high degree family of Taylor polynomials. Linear high‐gain Luenberger observers of the generalized proportional integral (GPI) type may be readily designed. These observers include the self updating internal model of the unknown disturbance input vector components in the form of generic, instantaneous, time‐polynomial models. The proposed (GPI) observers, which are the dual counterpart of GPI controllers [17], achieve a simultaneous disturbance estimation and tracking error phase variables estimation. This on‐line gathered information is used to advantage on the follower's feedback controller thus allowing for a simple, yet efficient, disturbance and control input gain cancelation effort. The results are applied to have the follower track a time‐delayed version of the actual leader's trajectory. Experimental results are presented which illustrate the robustness and viability of the proposed approach.     

Robust control with uncertainty estimation for feedback linearizable systems: application to control of distillation columns

The goal of this paper is to describe a linearizing feedback adaptive control structure which leads to a high quality regulation of the output error in the presence of uncertainties and external disturbances. The controller consists of three elements: a nominal input–output linearizing compensator, a state observer and an uncertainty estimator, which provides the adaptive part of the control structure. In this way, the feedback controller, based on the disturbance observer, compensates for external disturbances and plant uncertainties. The effectiveness of the controller is demonstrated on a distillation column via numerical simulations. ©     

Correction to: EKLT: Asynchronous Photometric Feature Tracking Using Events and Frames

International Journal of Computer Vision - The original version of this article was unfortunately omitted to publish the footnote “The best result per row is highlighted in bold” in...     

Evaluation of messaging middleware for high-performance cloud computing

Cloud computing is posing several challenges, such as security, fault tolerance, access interface singularity, and network constraints, both in terms of latency and bandwidth. In this scenario, the performance of communications depends both on the network fabric and its efficient support in virtualized environments, which ultimately determines the overall system performance. To solve the current network constraints in cloud services, their providers are deploying high-speed networks, such as 10 Gigabit Ethernet. This paper presents an evaluation of high-performance computing message-passing middleware on a cloud computing infrastructure, Amazon EC2 cluster compute instances, equipped with 10 Gigabit Ethernet. The analysis of the experimental results, confronted with a similar testbed, has shown the significant impact that virtualized environments still have on communication performance, which demands more efficient communication middleware support to get over the current cloud network limitations.     

Planetary exploration by robotic aerovehicles

Planetary aerobots are a new type of telerobotic science platform that can fly and navigate in a dynamic 3-dimensional atmospheric environment, thus enabling the global in situ exploration of planetary atmospheres and surfaces. Aerobots are enabled by a new concept in planetary balloon altitude control, developed at JPL, which employs reversible-fluid changes to permit repeated excursions in altitude. The essential physics and thermodynamics ofreversible-fluid altitude control have been demonstrated in a series of altitude-control experiments conducted in the Earth's atmosphere, which are described. Aerobot altitude-control technology will be important in the exploration of seven planets and satellites in our solar system. Three of these objects—Venus, Mars, and the Saturnian satellite Titan—have accessible solid surfaces and atmospheres dominated by the dense gases nitrogen or carbon dioxide. They will be explored with aerobots using helium or hydrogen as their primary means of buoyancy. The other four planets—Jupiter, Saturn, Uranus, and Neptune—have deep atmospheres that are predominantly hydrogen. It may be possible to explore these atmospheres with aerobots inflated with atmospheric gas that is then radiatively heated from the hotter gaseous depths below. To fulfill their potential, aerobots to explore the planets will need autonomous state estimators to guide their observations and provide information to the altitude-control systems. The techniques of acquiring these data remotely are outlined. Aerobots will also use on board altitude control and navigation systems to execute complex flight paths including descent to the surface and exploiting differential wind velocities to access different latitude belts. Approaches to control of these systems are examined. The application of aerobots to Venus exploration is explored in some detail: The most ambitious mission described, the Venus Flyer Robot (VFR), would have the capability to make repeated short excursions to the high-temperature surface environment of Venus to acquire data and then return to the Earth-like upper atmosphere to communicate and recool its electronic systems. Finally a Planetary Aerobot Testbed is discussed which will conduct Earth atmospheric flights to validate autonomous-state-estimator techniques and flight-path-control techniques needed for future planetary missions.     

Automatic mapping of parallel applications on multicore architectures using the Servet benchmark suite

Servet is a suite of benchmarks focused on detecting a set of parameters with high influence on the overall performance of multicore systems. These parameters can be used for autotuning codes to increase their performance on multicore clusters. Although Servet has been proved to detect accurately cache hierarchies, bandwidths and bottlenecks in memory accesses, as well as the communication overhead among cores, up to now the impact of the use of this information on application performance optimization has not been assessed. This paper presents a novel algorithm that automatically uses Servet for mapping parallel applications on multicore systems and analyzes its impact on three testbeds using three different parallel programming models: message-passing, shared memory and partitioned global address space (PGAS). Our results show that a suitable mapping policy based on the data provided by this tool can significantly improve the performance of parallel applications without source code modification.     

First experiences of teaching quantum computing

The Journal of Supercomputing - Quantum computing is a reality that presents challenges to computer engineering students and practitioners. It has been claimed that it is possible to effectively...     

New Results for Prediction of Chaotic Systems Using Deep Recurrent Neural Networks

Neural Processing Letters - Prediction of nonlinear and dynamic systems is a challenging task, however with the aid of machine learning techniques, particularly neural networks, is now possible to...