Polynomial regression under arbitrary product distributions

In recent work, Kalai, Klivans, Mansour, and Servedio (2005) studied a variant of the “Low-Degree (Fourier) Algorithm” for learning under the uniform probability distribution on {0,1} ⁿ . They showed that the L ₁ polynomial regression algorithm yields agnostic (tolerant to arbitrary noise) learning algorithms with respect to the class of threshold functions—under certain restricted instance distributions, including uniform on {0,1} ⁿ and Gaussian on ? ⁿ . In this work we show how all learning results based on the Low-Degree Algorithm can be generalized to give almost identical agnostic guarantees under arbitrary product distributions on instance spaces X ₁×???×X _n . We also extend these results to learning under mixtures of product distributions. The main technical innovation is the use of (Hoeffding) orthogonal decomposition and the extension of the “noise sensitivity method” to arbitrary product spaces. In particular, we give a very simple proof that threshold functions over arbitrary product spaces have δ-noise sensitivity $O(\sqrt{\delta})$ , resolving an open problem suggested by Peres (2004).     

Trading Off Cache Capacity for Low-Voltage Operation

Two proposed techniques let microprocessors operate at low voltages despite high memory-cell failure rates. They identify and disable defective portions of the cache at two granularities: individual words or pairs of bits. Both techniques use the entire cache during high-voltage operation while sacrificing cache capacity during low-voltage operation to reduce the minimum voltage below 500 mV.     

Using LiDAR and quickbird data to model plant production and quantify uncertainties associated with wetland detection and land cover generalizations

Spatiotemporal data from satellite remote sensing and surface meteorology networks have made it possible to continuously monitor global plant production, and to identify global trends associated with land cover/use and climate change. Gross primary production (GPP) and net primary production (NPP) are routinely derived from the Moderate Resolution Imaging Spectroradiometer (MODIS) onboard satellites Terra and Aqua, and estimates generally agree with independent measurements at validation sites across the globe. However, the accuracy of GPP and NPP estimates in some regions may be limited by the quality of model input variables and heterogeneity at fine spatial scales. We developed new methods for deriving model inputs (i.e., land cover, leaf area, and photosynthetically active radiation absorbed by plant canopies) from airborne laser altimetry (LiDAR) and Quickbird multispectral data at resolutions ranging from about 30 m to 1 km. In addition, LiDAR-derived biomass was used as a means for computing carbon-use efficiency. Spatial variables were used with temporal data from ground-based monitoring stations to compute a six-year GPP and NPP time series for a 3600 ha study site in the Great Lakes region of North America. Model results compared favorably with independent observations from a 400 m flux tower and a process-based ecosystem model (BIOME-BGC), but only after removing vapor pressure deficit as a constraint on photosynthesis from the MODIS global algorithm. Fine-resolution inputs captured more of the spatial variability, but estimates were similar to coarse-resolution data when integrated across the entire landscape. Failure to account for wetlands had little impact on landscape-scale estimates, because vegetation structure, composition, and conversion efficiencies were similar to upland plant communities. Plant productivity estimates were noticeably improved using LiDAR-derived variables, while uncertainties associated with land cover generalizations and wetlands in this largely forested landscape were considered less important.     

Development of a pit filling algorithm for LiDAR canopy height models

LiDAR canopy height models (CHMs) can exhibit unnatural looking holes or pits, i.e., pixels with a much lower digital number than their immediate neighbors. These artifacts may be caused by a combination of factors, from data acquisition to post-processing, that not only result in a noisy appearance to the CHM but may also limit semi-automated tree-crown delineation and lead to errors in biomass estimates. We present a highly effective semi-automated pit filling algorithm that interactively detects data pits based on a simple user-defined threshold, and then fills them with a value derived from their neighborhood. We briefly describe this algorithm and its graphical user interface, and show its result in a LiDAR CHM populated with data pits. This method can be rapidly applied to any CHM with minimal user interaction. Visualization confirms that our method effectively and quickly removes data pits.     

The MarineGrid project in Ireland with Webcom

The 1999–2007 Irish National Seabed Survey is one of the largest ocean floor mapping projects ever attempted. Its aim is to map the ocean floor of the Irish territorial waters (approximately $525000{\mathrm{km}}^2$). To date, the Geological Survey of Ireland has gathered in excess of 4 TB of multibeam sonar data from the Irish National Seabed, and this data set is expected to exceed 10 TB upon completion. The main challenge that arises from having so much data is how to extract accurate information given the size of the data set. Geological interpretation is carried out by visual inspection of bathymetric patterns. The size of this, and similar, data sets renders the extraction of knowledge by human observers infeasible. Consequently, the focus has turned to using artificial intelligence and computational methods for assistance. The commercial and environmental sensitivity of the data means that secure data processing and transmission are of paramount importance. This has lead to the creation of the MarineGrid project within the Grid-Ireland organisation. New methods have been developed for statistical analysis of bathymetric information specifically for automated geological interpretation of rock types on the sea floor and feature extraction from the sea floor. We present a discussion on how to provide Marine and Geological researchers convenient yet secure access to resources that make use of grid technologies including pre-written algorithms in order to exploit the Irish National Seabed Survey data archive.     

Implementation of a Gaussian process-based machine learning grasp predictor

With the goal of advancing the state of automatic robotic grasping, we present a novel approach that combines machine learning techniques and physical validation on a robotic platform to develop a comprehensive grasp predictor. After collecting a large grasp sample set (522 grasps), we first conduct a statistical analysis of the predictive ability of grasp quality metrics that are commonly used in the robotics literature. We then apply principal component analysis and Gaussian process (GP) algorithms on the grasp metrics that are discriminative to build a classifier, validate its performance, and compare the results to existing grasp planners. The key findings are as follows: (i) several of the existing grasp metrics are weak predictors of grasp quality when implemented on a robotic platform; (ii) the GP-based classifier significantly improves grasp prediction by combining multiple grasp metrics to increase true positive classification at low false positive rates; (iii) The GP classifier can be used generate new grasps to improve bad grasp samples by performing a local search to find neighboring grasps which have improved contact points and higher success rate.     

Whole-body hierarchical motion and force control for humanoid robots

Robots acting in human environments usually need to perform multiple motion and force tasks while respecting a set of constraints. When a physical contact with the environment is established, the newly activated force task or contact constraint may interfere with other tasks. The objective of this paper is to provide a control framework that can achieve real-time control of humanoid robots performing both strict and non strict prioritized motion and force tasks. It is a torque-based quasi-static control framework, which handles a dynamically changing task hierarchy with simultaneous priority transitions as well as activation or deactivation of tasks. A quadratic programming problem is solved to maintain desired task hierarchies, subject to constraints. A generalized projector is used to quantitatively regulate how much a task can influence or be influenced by other tasks through the modulation of a priority matrix. By the smooth variations of the priority matrix, sudden hierarchy rearrangements can be avoided to reduce the risk of instability. The effectiveness of this approach is demonstrated on both a simulated and a real humanoid robot.     

Opportunistic sampling-based active visual SLAM for underwater inspection

This paper reports on an active SLAM framework for performing large-scale inspections with an underwater robot. We propose a path planning algorithm integrated with visual SLAM that plans loop-closure paths in order to decrease navigation uncertainty. While loop-closing revisit actions bound the robot’s uncertainty, they also lead to redundant area coverage and increased path length. Our proposed opportunistic framework leverages sampling-based techniques and information filtering to plan revisit paths that are coverage efficient. We employ Gaussian process regression for modeling the prediction of camera registrations and use a two-step optimization procedure for selecting revisit actions. We show that the proposed method offers many benefits over existing solutions and good performance for bounding navigation uncertainty in long-term autonomous operations with hybrid simulation experiments and real-world field trials performed by an underwater inspection robot.     

The personal lift-assist device and lifting technique: a principal component analysis

The personal lift-assist device (PLAD) is a non-motorised, on-body device that acts as an external force generator using the concept of stored elastic energy. In this study, the effect of the PLAD on the lifting kinematics of male and female lifters was investigated using principal component analysis. Joint kinematic data of 15 males and 15 females were collected using an opto-electronic system during a freestyle, symmetrical-lifting protocol with and without wearing the PLAD. Of the 31 Principal Components (PCs) retained in the models, eight scores were significantly different between the PLAD and no-PLAD conditions. There were no main effects for gender and no significant interactions. Results indicated that the PLAD similarly affected the lifting kinematics of males and females; demonstrating significantly less lumbar and thoracic flexion and significantly greater hip and ankle flexion when wearing the PLAD. These findings add to the body of work that suggest the PLAD may be a safe and effective ergonomic aid. STATEMENT OF RELEVANCE: The PLAD is an ergonomic aid that has been shown to be effective at reducing low back demands during manual materials handling tasks. This body of work establishes that the PLAD encourages safe lifting practices without adversely affecting lifting technique.     

Test-retest reliability of Purdue Pegboard performance in thermoneutral and cold ambient conditions

In the cold, Purdue Pegboard (PP) performance declines. The purpose of this study was to determine if this cold-induced impairment is consistent across days (i.e. test-retest reliability) in 5°C. In thermoneutral air (25°C), 14 men were familiarised to the dominant hand (PPa) and bimanual (PPb) PP tasks. They then experienced two 90-min cold exposures (Day 1, Day 2) while wearing ～1 clo. Bare hands were maintained throughout. Performance on both tasks showed high reliability from day to day (intraclass correlations >0.700) in both thermoneutral and cold conditions. However for both tasks, room temperature performance did not predict performance in the cold (intraclass correlations <0.450). When screening applicants for manual labour in the cold, one must consider that room temperature dexterity does not correlate with dexterity in the cold. It is recommended that a 60-min period of cold exposure be employed to assess manual dexterity in these workers. STATEMENT OF RELEVANCE: This study shows that PP performance in room temperature does not predict performance in the cold but performance in the cold is consistent from day to day. When screening applicants for manual labour in the cold, it is recommended that dexterity tests be conducted in the same ambient conditions.