Learned ultra-wideband RADAR sensor model for augmented LIDAR-based traversability mapping in vegetated environments

In vegetated environments, reliable obstacle detection remains a challenge for state-of-the-art methods, which are usually based on geometrical representations of the environment built from LIDAR and/or visual data. In many cases, in practice field robots could safely traverse through vegetation, thereby avoiding costly detours. However, it is often mistakenly interpreted as an obstacle. Classifying vegetation is insufficient since there might be an obstacle hidden behind or within it. Some Ultra-wide band (UWB) radars can penetrate through vegetation to help distinguish actual obstacles from obstacle-free vegetation. However, these sensors provide noisy and low-accuracy data. Therefore, in this work we address the problem of reliable traversability estimation in vegetation by augmenting LIDAR-based traversability mapping with UWB radar data. A sensor model is learned from experimental data using a support vector machine to convert the radar data into occupancy probabilities. These are then fused with LIDAR-based traversability data. The resulting augmented traversability maps capture the fine resolution of LIDAR-based maps but clear safely traversable foliage from being interpreted as obstacle. We validate the approach experimentally using sensors mounted on two different mobile robots, navigating in two different environments.

Lateralization of temporal lobe epilepsy based on resting-state functional magnetic resonance imaging and machine learning

Lateralization of temporal lobe epilepsy (TLE) is critical for successful outcome of surgery to relieve seizures. TLE affects brain regions beyond the temporal lobes and has been associated with aberrant brain networks, based on evidence from functional magnetic resonance imaging. We present here a machine learning-based method for determining the laterality of TLE, using features extracted from resting-state functional connectivity of the brain. A comprehensive feature space was constructed to include network properties within local brain regions, between brain regions, and across the whole network. Feature selection was performed based on random forest and a support vector machine was employed to train a linear model to predict the laterality of TLE on unseen patients. A leave-one-patient-out cross validation was carried out on 12 patients and a prediction accuracy of 83% was achieved. The importance of selected features was analyzed to demonstrate the contribution of resting-state connectivity attributes at voxel, region, and network levels to TLE lateralization.

Fractional diffusion models of cardiac electrical propagation: Role of structural heterogeneity in dispersion of repolarization

Impulse propagation in biological tissues is known to be modulated by structural heterogeneity. In cardiac muscle, improved understanding on how this heterogeneity influences electrical spread is key to advancing our interpretation of dispersion of repolarization. We propose fractional diffusion models as a novel mathematical description of structurally heterogeneous excitable media, as a means of representing the modulation of the total electric field by the secondary electrical sources associated with tissue inhomogeneities. Our results, analysed against in vivo human recordings and experimental data of different animal species, indicate that structural heterogeneity underlies relevant characteristics of cardiac electrical propagation at tissue level. These include conduction effects on action potential (AP) morphology, the shortening of AP duration along the activation pathway and the progressive modulation by premature beats of spatial patterns of dispersion of repolarization. The proposed approach may also have important implications in other research fields involving excitable complex media.

A data mining approach for fault diagnosis: An application of anomaly detection algorithm

Rolling-element bearing failures are the most frequent problems in rotating machinery, which can be catastrophic and cause major downtime. Hence, providing advance failure warning and precise fault detection in such components are pivotal and cost-effective. The vast majority of past research has focused on signal processing and spectral analysis for fault diagnostics in rotating components. In this study, a data mining approach using a machine learning technique called anomaly detection (AD) is presented. This method employs classification techniques to discriminate between defect examples. Two features, kurtosis and Non-Gaussianity Score (NGS), are extracted to develop anomaly detection algorithms. The performance of the developed algorithms was examined through real data from a test to failure bearing. Finally, the application of anomaly detection is compared with one of the popular methods called Support Vector Machine (SVM) to investigate the sensitivity and accuracy of this approach and its ability to detect the anomalies in early stages.

Increasing autonomy transparency through capability communication in multiple heterogeneous UAV management

Interest in the area of collaborative Unmanned Aerial Vehicles (UAVs) in a Multi-Agent System is growing to compliment the strengths and weaknesses of the human-machine relationship. To achieve effective management of multiple heterogeneous UAVs, the status model of the agents must be communicated to each other. This paper presents the effects on operator Cognitive Workload (CW), Situation Awareness (SA), trust and performance by increasing the autonomy capability transparency through text-based communication of the UAVs to the human agents. The results revealed a reduction in CW, increase in SA, increase in the Competence, Predictability and Reliability dimensions of trust, and the operator performance.

Nitrogen-doped graphene films from chemical vapor deposition of pyridine: Influence of process parameters on the electrical and optical properties

Graphene films were produced by chemical vapor deposition (CVD) of pyridine on copper substrates. Pyridine-CVD is expected to lead to doped graphene by the insertion of nitrogen atoms in the growing sp2 carbon lattice, possibly improving the properties of graphene as a transparent conductive film. We here report on the influence that the CVD parameters (i.e., temperature and gas flow) have on the morphology, transmittance, and electrical conductivity of the graphene films grown with pyridine. A temperature range between 930 and 1070 °C was explored and the results were compared to those of pristine graphene grown by ethanol-CVD under the same process conditions. The films were characterized by atomic force microscopy, Raman and X-ray photoemission spectroscopy. The optical transmittance and electrical conductivity of the films were measured to evaluate their performance as transparent conductive electrodes. Graphene films grown by pyridine reached an electrical conductivity of 14.3 × 105 S/m. Such a high conductivity seems to be associated with the electronic doping induced by substitutional nitrogen atoms. In particular, at 930 °C the nitrogen/carbon ratio of pyridine-grown graphene reaches 3%, and its electrical conductivity is 40% higher than that of pristine graphene grown from ethanol-CVD.

Turning gaming EEG peripherals into trainable brain computer interfaces

Companies such as NeuroSky and Emotiv Systems are selling non-medical EEG devices for human computer interaction. These devices are significantly more affordable than their medical counterparts, and are mainly used to measure levels of engagement, focus, relaxation and stress. This information is sought after for marketing research and games. However, these EEG devices have the potential to enable users to interact with their surrounding environment using thoughts only, without activating any muscles. In this paper, we present preliminary results that demonstrate that despite reduced voltage and time sensitivity compared to medical-grade EEG systems, the quality of the signals of the Emotiv EPOC neuroheadset is sufficiently good in allowing discrimina tion between imaging events. We collected streams of EEG raw data and trained different types of classifiers to discriminate between three states (rest and two imaging events). We achieved a generalisation error of less than 2% for two types of non-linear classifiers.

Automating marine mammal detection in aerial images captured during wildlife surveys: A deep learning approach

Aerial surveys conducted using manned or unmanned aircraft with customized camera payloads can generate a large number of images. Manual review of these images to extract data is prohibitive in terms of time and financial resources, thus providing strong incentive to automate this process using computer vision systems. There are potential applications for these automated systems in areas such as surveillance and monitoring, precision agriculture, law enforcement, asset inspection, and wildlife assessment. In this paper, we present an efficient machine learning system for automating the detection of marine species in aerial imagery. The effectiveness of our approach can be credited to the combination of a well-suited region proposal method and the use of Deep Convolutional Neural Networks (DCNNs). In comparison to previous algorithms designed for the same purpose, we have been able to dramatically improve recall to more than 80% and improve precision to 27% by using DCNNs as the core approach.

An Evaluation of Inventory Management and Performance in Indian Machine Tool SMEs: An Exploratory Study

Inventory Management (IM) plays a decisive role in the enhancement of efficiency and competitiveness of manufacturing enterprises. Therefore, major manufacturing enterprises are following IM practices as a strategy to improve efficiency and achieve competitiveness. However, the spread of IM culture among Small and Medium Enterprises (SMEs) is limited due to lack of initiation, expertise and financial limitations in developed countries, leave alone developing countries. With this backdrop, this paper makes an attempt to ascertain the role and importance of IM practices and performance of SMEs in the machine tools industry of Bangalore, India. The relationship between inventory management practices and inventory cost are probed based on primary data gathered from 91 SMEs. The paper brings out that formal IM practices have a positive impact on the inventory performance of SMEs.

Low-temperature electrical conductivity of LaNi1-xFexO3

We report the electrical conductivity between 2 and 300 K for LaNi1-xFexO3 across the composition-controlled metal-insulator (m-i) transition. Using a method first suggested by Mobius, we identify the critical concentration x(c) to be 0.3 for the m-i transition. The negative temperature coefficient of resistivity observed at low temperatures in the metallic phase follows a temperature dependence characteristic of disorder effects. The semiconducting compositions (x greater than or equal to 0.3) do not show a simple activation energy but exhibit variable-range hopping at high temperatures confirming that the m-i transition in this system is driven by increasing disorder effects.

Electrical Conductivity and Magneto-Resistance Studies on Polyaniline-Pmma Blends at Very Low Temperature

D.C. electrical conductivity of polyaniline (33%,40%) blended with PMMA was measured from 5K to 300mK. The conductivity behaviour is consistent with fluctuation induced tunneling. Magneto-resistance (MR) was measured between 300K and 2K. From 20K to 2K, a large positive MR was observed. At 2K, for low magnetic fields (<1 Tesla), a deviation from the normal H-2 behaviour was observed.

Effect of antimony addition on the thermal and electrical-switching behavior of bulk Se-Te glasses

The thermal properties and electrical-switching behavior of semiconducting chalcogenide SbxSe55-xTe45 (2 <= x <= 9) glasses have been investigated by alternating differential scanning calorimetry and electrical-switching experiments, respectively. The addition of Sb is found to enhance the glass forming tendency and stability as revealed by the decrease in non-reversing enthalpy Delta H-nr. and an increase in the glass-transition width Delta T-g. Further, the glass-transition temperature of SbxSe55-xTe45 glasses, which is a measure of network connectivity, exhibits a subtle increase, suggesting a meager network growth with the addition of Sb. The crystallization temperature is also observed to increase with Sb content. The SbxSe55-xTe45 glasses (2 <= x <= 9) are found to exhibit memory type of electrical switching, which can be attributed to the polymeric nature of network and high devitrifying ability. The metallicity factor has been found to dominate over the network connectivity and rigidity in the compositional dependence of switching voltage. which shows a profound decrease with the addition of Sb.

Phase conversions in calcium manganites with changing Ca/Mn ratios and their influence on the electrical transport properties

The phase-interconversions between the spinel-, brownmillerite-, defect rocksalt and perovskite-type structures have been investigated by way of (i) introducing deficiency in A-sites in CaxMn2-xO3 (0.05 <= x <= 1) i.e., by varying Ca/Mn ratio from 0.025 to 1 and (ii) nonstoichiometric CaMnO3-delta (CMO) with 0.02 <= delta <= 1. The temperature dependence of resistivity (rho-T) have been investigated on nonstoichiometric CaMnO3-delta (undoped) as well as the CMO substituted with donor impurities such as La3+, Y3+, Bi3+ or acceptor such as Na1+ ion at the Ca-site. The rho-T characteristics of nonstoichiometric CaMnO3-delta is strongly influenced by oxygen deficiency, which controls the concentration of Mn3+ ions and, in turn, affects the resistivity, rho. The results indicated that the substitution of aliovalent impurities at Ca-site in CaMnO3 has similar effects as of CaMnO3-delta ( undoped) annealed in atmospheres of varying partial pressures whereby electron or hole concentration can be altered, yet the doped samples can be processed in air or atmospheres of higher P-O2. The charge transport mechanisms of nonstoichiometric CaMnO3-delta as against the donor or acceptor doped CaMnO3 (sintered in air, P-O2 similar to 0.2 atm) have been predicted. The rho (T) curves of both donor doped CaMnO3 as well as non-stoichiometric CaMnO3-delta, is predictable by the small polaron hopping (SPH) model, which changes to the variable range hopping (VRH) at low temperatures whereas the acceptor doped CaMnO3 exhibited an activated semiconducting hopping ( ASH) throughout the measured range of temperature (10-500 K).

Structural, optical and electrical properties of sulfur-incorporated amorphous carbon films

Amorphous carbon-sulfur (a-C:S) composite films were prepared by vapor phase pyrolysis technique. The structural changes in the a-C:S films were investigated by electron microscopy. A powder X-ray diffraction (XRD) study depicts the two-phase nature of a sulfur-incorporated a-C system. The optical bandgap energy shows a decreasing trend with an increase in the sulfur content and preparation temperature. This infers a sulfur incorporation and pyrolysis temperature induced reduction in structural disorder or increase in sp (2) or pi-sites. The presence of sulfur (S 2p) in the a-C:S sample is analyzed by the X-ray photoelectron spectroscopy (XPS). The sp (3)/sp (2) hybridization ratio is determined by using the XPS C 1s peak fitting, and the results confirm an increase in sp (2) hybrids with sulfur addition to a-C. The electrical resistivity variation in the films depends on both the sulfur concentration and the pyrolysis temperature.

Role of predictors in downscaling surface temperature to river basin in India for IPCC SRES scenarios using support vector machine

In this paper, downscaling models are developed using a support vector machine (SVM) for obtaining projections of monthly mean maximum and minimum temperatures (T-max and T-min) to river-basin scale. The effectiveness of the model is demonstrated through application to downscale the predictands for the catchment of the Malaprabha reservoir in India, which is considered to be a climatically sensitive region. The probable predictor variables are extracted from (1) the National Centers for Environmental Prediction (NCEP) reanalysis dataset for the period 1978-2000, and (2) the simulations from the third-generation Canadian Coupled Global Climate Model (CGCM3) for emission scenarios A1B, A2, B1 and COMMIT for the period 1978-2100. The predictor variables are classified into three groups, namely A, B and C. Large-scale atmospheric variables Such as air temperature, zonal and meridional wind velocities at 925 nib which are often used for downscaling temperature are considered as predictors in Group A. Surface flux variables such as latent heat (LH), sensible heat, shortwave radiation and longwave radiation fluxes, which control temperature of the Earth's surface are tried as plausible predictors in Group B. Group C comprises of all the predictor variables in both the Groups A and B. The scatter plots and cross-correlations are used for verifying the reliability of the simulation of the predictor variables by the CGCM3 and to Study the predictor-predictand relationships. The impact of trend in predictor variables on downscaled temperature was studied. The predictor, air temperature at 925 mb showed an increasing trend, while the rest of the predictors showed no trend. The performance of the SVM models that are developed, one for each combination of predictor group, predictand, calibration period and location-based stratification (land, land and ocean) of climate variables, was evaluated. In general, the models which use predictor variables pertaining to land surface improved the performance of SVM models for downscaling T-max and T-min