Regression analysis of spatial data

Many of the most interesting questions ecologists ask lead to analyses of spatial data. Yet, perhaps confused by the large number of statistical models and fitting methods available, many ecologists seem to believe this is best left to specialists. Here, we describe the issues that need consideration when analysing spatial data and illustrate these using simulation studies. Our comparative analysis involves using methods including generalized least squares, spatial filters, wavelet revised models, conditional autoregressive models and generalized additive mixed models to estimate regression coefficients from synthetic but realistic data sets, including some which violate standard regression assumptions. We assess the performance of each method using two measures and using statistical error rates for model selection. Methods that performed well included generalized least squares family of models and a Bayesian implementation of the conditional auto-regressive model. Ordinary least squares also performed adequately in the absence of model selection, but had poorly controlled Type I error rates and so did not show the improvements in performance under model selection when using the above methods. Removing large-scale spatial trends in the response led to poor performance. These are empirical results; hence extrapolation of these findings to other situations should be performed cautiously. Nevertheless, our simulation-based approach provides much stronger evidence for comparative analysis than assessments based on single or small numbers of data sets, and should be considered a necessary foundation for statements of this type in future.

Influence of the Pacific Decadal Oscillation, El Niño-Southern Oscillation and solar forcing on climate and primary productivity changes in the northeast Pacific

Evidence of 11-year Schwabe solar sunspot cycles, El Niño-Southern Oscillation (ENSO) and the Pacific Decadal Oscillation (PDO) were detected in an annual record of diatomaceous laminated sediments from anoxic Effingham Inlet, Vancouver Island, British Columbia. Radiometric dating and counting of annual varves dates the sediments from AD 1947-1993. Intact sediment slabs were X-rayed for sediment structure (lamina thickness and composition based on gray-scale), and subsamples were examined for diatom abundances and for grain size. Wavelet analysis reveals the presence of ~2-3, ~4.5, ~7 and ~9-12-year cycles in the diatom record and an w11e13 year record in the sedimentary varve thickness record. These cycle lengths suggest that both ENSO and the sunspot cycle had an influence on primary productivity and sedimentation patterns. Sediment grain size could not be correlated to the sunspot cycle although a peak in the grain size data centered around the mid-1970s may be related to the 1976-1977 Pacific climate shift, which occurred when the PDO index shifted from negative (cool conditions) to positive (warm conditions). Additional evidence of the PDO regime shift is found in wavelet and cross-wavelet results for Skeletonema costatum, a weakly silicified variant of S. costatum, annual precipitation and April to June precipitation. Higher spring (April/May) values of the North Pacific High pressure index during sunspot minima suggest that during this time, increased cloud cover and concomitant suppression of the Aleutian Low (AL) pressure system led to strengthened coastal upwelling and enhanced diatom production earlier in the year. These results suggest that the 11-year solar cycle, amplified by cloud cover and upwelling changes, as well as ENSO, exert significant influence on marine primary productivity in the northeast Pacific. The expression of these cyclic phenomena in the sedimentary record were in turn modulated by the phase of PDO, as indicated by the change in period of ENSO and suppression of the solar signal in the record after the 1976-1977 regime shift. © 2013 Elsevier Ltd and INQUA. All rights reserved.

The use of ensemble empirical mode decomposition with canonical correlation analysis as a novel artifact removal technique

Biosignal measurement and processing is increasingly being deployed in ambulatory situations particularly in connected health applications. Such an environment dramatically increases the likelihood of artifacts which can occlude features of interest and reduce the quality of information available in the signal. If multichannel recordings are available for a given signal source, then there are currently a considerable range of methods which can suppress or in some cases remove the distorting effect of such artifacts. There are, however, considerably fewer techniques available if only a single-channel measurement is available and yet single-channel measurements are important where minimal instrumentation complexity is required. This paper describes a novel artifact removal technique for use in such a context. The technique known as ensemble empirical mode decomposition with canonical correlation analysis (EEMD-CCA) is capable of operating on single-channel measurements. The EEMD technique is first used to decompose the single-channel signal into a multidimensional signal. The CCA technique is then employed to isolate the artifact components from the underlying signal using second-order statistics. The new technique is tested against the currently available wavelet denoising and EEMD-ICA techniques using both electroencephalography and functional near-infrared spectroscopy data and is shown to produce significantly improved results. © 1964-2012 IEEE.

Centennial-scale climate change in Ireland during the Holocene

We examine mid- to late Holocene centennial-scale climate variability in Ireland using proxy data from peatlands, lakes and a speleothem. A high degree of between-record variability is apparent in the proxy data and significant chronological uncertainties are present. However, tephra layers provide a robust tool for correlation and improve the chronological precision of the records. Although we can find no statistically significant coherence in the dataset as a whole, a selection of high-quality peatland water table reconstructions co-vary more than would be expected by chance alone. A locally weighted regression model with bootstrapping can be used to construct a ‘best-estimate’ palaeoclimatic reconstruction from these datasets. Visual comparison and cross-wavelet analysis of peatland water table compilations from Ireland and Northern Britain show that there are some periods of coherence between these records. Some terrestrial palaeoclimatic changes in Ireland appear to coincide with changes in the North Atlantic thermohaline circulation and solar activity. However, these relationships are inconsistent and may be obscured by chronological uncertainties. We conclude by suggesting an agenda for future Holocene climate research in Ireland. ©2013 Elsevier B.V. All rights reserved.

Measurement-based Method for Wind Farm Power System Oscillation Monitoring

The global increase in the penetration of renewable energy is pushing electrical power systems into uncharted territory, especially in terms of transient and dynamic stability. In particular, the greater penetration of wind generation in European power networks is, at times, displacing a significant capacity of conventional synchronous generation with fixed-speed induction generation and now more commonly, doubly-fed induction generators. The impact of such changes in the generation mix requires careful monitoring to assess the impact on transient and dynamic stability. This paper presents a measurement based method for the early detection of power system oscillations, with attention to mode damping, in order to raise alarms and develop strategies to actively improve power system dynamic stability and security. A method is developed based on wavelet transform and support vector data description (SVDD) to detect oscillation modes in wind farm output power, which may excite dynamic instabilities in the wider system. The wavelet transform is used as a filter to identify oscillations in different frequency bands, while SVDD is used to extract dominant features from different scales and generate an assessment boundary according to the extracted features. Poorly damped oscillations of a large magnitude or that are resonant can be alarmed to the system operator, to reduce the risk of system instability. Method evaluation is exemplified used real data from a chosen wind farm.

Climate change and decadal to centennial-scale periodicities recorded in a late Holocene NE Pacific marine record: Examining the role of solar forcing

We present a decadal-scale late Holocene climate record based on diatoms, biogenic silica, and grain size from a 12-m sediment core (VEC02A04) obtained from Frederick Sound in the Seymour-Belize Inlet Complex of British Columbia, Canada. Sediments are characterized by graded, massive, and laminated intervals. Laminated intervals are most common between c. 2948–2708 cal. yr BP and c. 1992–1727 cal. yr BP. Increased preservation of laminated sediments and diatom assemblage changes at this time suggest that cli- mate became moderately drier and cooler relative to the preceding and succeeding intervals. Spectral and wavelet analyses are used to test for statistically significant periodicities in time series of proxies of primary production (total diatom abundance, biogenic silica) and hydrology (grain size) preserved in the Frederick Sound record. Periodicities of c. 42–53, 60–70, 82–89, 241–243, and 380 yrs are present. Results are com- pared to reconstructed sunspot number data of Solanki et al. (2004) using cross wavelet transform to evalu- ate the role of solar forcing on NE Pacific climate. Significant common power of periodicities between c. 42– 60, 70–89, 241–243, and of 380 yrs occur, suggesting that celestial forcing impacted late Holocene climate at Frederick Sound. Replication of the c. 241–243 yr periodicity in sunspot time series is most pronounced be- tween c. 2900 cal. yr BP and c. 2000 cal. yr BP, broadly correlative to the timing of maximum preservation of laminated sedimentary successions and diatom assemblage changes. High solar activity at the Suess/de Vries band may have been manifested as a prolonged westward shift and/or weakening of the Aleutian Low in the mid-late Holocene, which would have diverted fewer North Pacific storms and resulted in the relatively dry conditions reconstructed for the Seymour-Belize Inlet Complex.

TRACE observations of driven loop oscillations

Aims: On 13 June 1998, the TRACE satellite was fortuitously well placed to observe the effects of a flare-induced EIT wave in the corona, and its subsequent interaction with coronal magnetic loops. In this study, we use these TRACE observations to corroborate previous theoretical work, which determined the response of a coronal loop to a harmonic driver in the context of ideal magnetohydrodynamics, as well as estimate the magnetic field strength and the degree of longitudinal inhomogeneity. Methods: Loop edges are tracked, both spatially and temporally, using wavelet modulus maxima algorithms, with corresponding loop displacements from its quiescent state analysed by fitting scaled sinusoidal functions. The physical parameters of the coronal loop are subsequently determined using seismological techniques. Results: The studied coronal loop is found to oscillate with two distinct periods, 501 ± 5 s and 274 ± 7 s, which could be interpreted as belonging to the fundamental kink mode and first harmonic, or could reflect the stage of an overdriven loop. Additional scenarios for explaining the two periods are listed, each resulting in a different value of the magnetic field and the intrinsic and sub-resolution properties of the coronal loop. When assuming the periods belong to the fundamental kink mode and its first harmonic, we obtain a magnetic field strength inside the oscillating coronal loop of 2.0 ± 0.7 G. In contrast, interpreting the oscillations as a combination of the loop's natural kink frequency and a harmonic EIT wave provides a magnetic field strength of 5.8 ± 1.5 G. Using the ratio of the two periods, we find that the gravitational scale height in the loop is 73 ± 3 Mm. Conclusions: We show that the observation of two distinct periods in a coronal loop does not necessarily lead to a unique conclusion. Multiple plausible scenarios exist, suggesting that both the derived strength of the magnetic field and the sub-resolution properties of the coronal loop depend entirely on which interpretation is chosen. The interpretation of the observations in terms of a combination of the natural kink mode of the coronal loop, driven by a harmonic EIT wave seems to result in values of the magnetic field consistent with previous findings. Other interpretations, which are realistic, such as kink fundamental mode/first harmonic and the oscillations of two sub-resolution threads result in magnetic field strengths that are below the average values found before.

Low-power DWT-based quasi-averaging algorithm and architecture for epileptic seizure detection

In this paper, we have developed a low-complexity algorithm for epileptic seizure detection with a high degree of accuracy. The algorithm has been designed to be feasibly implementable as battery-powered low-power implantable epileptic seizure detection system or epilepsy prosthesis. This is achieved by utilizing design optimization techniques at different levels of abstraction. Particularly, user-specific critical parameters are identified at the algorithmic level and are explicitly used along with multiplier-less implementations at the architecture level. The system has been tested on neural data obtained from in-vivo animal recordings and has been implemented in 90nm bulk-Si technology. The results show up to 90 % savings in power as compared to prevalent wavelet based seizure detection technique while achieving 97% average detection rate. Copyright 2010 ACM.

Using Brain Data for Sentiment Analysis

We present the results of exploratory experiments using lexical valence extracted from brain using electroencephalography (EEG) for sentiment analysis. We selected 78 English words (36 for training and 42 for testing), presented as stimuli to 3 English native speakers. EEG signals were recorded from the subjects while they performed a mental imaging task for each word stimulus. Wavelet decomposition was employed to extract EEG features from the time-frequency domain. The extracted features were used as inputs to a sparse multinomial logistic regression (SMLR) classifier for valence classification, after univariate ANOVA feature selection. After mapping EEG signals to sentiment valences, we exploited the lexical polarity extracted from brain data for the prediction of the valence of 12 sentences taken from the SemEval-2007 shared task, and compared it against existing lexical resources.

Coupled Effects of a Perturbation in a Complex Structure Observed with SDO/AIA, SDO/HMI and ROSA/HARDcam

We study properties of intensity fluctuations in NOAA Active Region 11250 observed on 13 July 2011 starting at UT 13:32. Included are data obtained in the EUV bands of the Atmospheric Imaging Assembly on board the Solar Dynamics Observatory (SDO/AIA) as well as nearly simultaneous observations of the chromosphere made, at much higher spatial and temporal resolution, with the Rapid Oscillations in the Solar Atmosphere (ROSA) and Hydrogen-Alpha Rapid Dynamics camera (HARDcam) systems at the Dunn Solar Telescope. A complex structure seen in both the ROSA/HARDcam and SDO data sets comprises a system of loops extending outward from near the boundary of the leading sunspot umbra. It is visible in the ROSA Ca II K and HARDcam Hα images, as well as the SDO 304 Å, 171 Å and 193 Å channels, and it thus couples the chromosphere, transition region and corona. In the ground-based images the loop structure is 4.1 Mm long. Some 17.5 Mm, can be traced in the SDO/AIA data. The chromospheric emissions observed by ROSA and HARDcam appear to occupy the inner, and apparently cooler and lower, quarter of the loop. We compare the intensity fluctuations of two points within the structure. From alignment with SDO/HMI images we identify a point "A" near the loop structure, which sits directly above a bipolar magnetic feature in the photosphere. Point "B" is characteristic of locations within the loops that are visible in both the ROSA/HARDcam and the SDO/AIA data. The intensity traces for point A are quiet during the first part of the data string. At time ~ 19 min they suddenly begin a series of impulsive brightenings. In the 171 Å and 193 Å coronal lines the brightenings are localized impulses in time, but in the transition region line at 304 Å they are more extended in time. The intensity traces in the 304 Å line for point B shows a quasi-periodic signal that changes properties at about 19 min. The wavelet power spectra are characterized by two periodicities. A 6.7 min period extends from the beginning of the series until about 25 minutes, and another signal with period ~3 min starts at about 20 min. The 193 Å power spectrum has a characteristic period of 5 min, before the 20 min transition and a 2.5 min periodicity afterward. In the case of HARDcam Hα data a localized 4 min periodicity can be found until about 7 min, followed by a quiet regime. After ~20 min a 2.3 min periodicity appears. Interestingly a coronal loop visible in the 94 Å line that is centrally located in the AR, running from the leading umbra to the following polarity, at about time 20 min undergoes a strong brightening beginning at the same moment all along 15 Mm of its length. The fact that these different signals all experience a clear-cut change at time about 20 min suggests an underlying organizing mechanism. Given that point A has a direct connection to the photospheric magnetic bipole, we conjecture that the whole extended structure is connected in a complex manner to the underlying magnetic field. The periodicities in these features may favor the wave nature rather than upflows and interpretations will be discussed.

Rapid Oscillations in the Solar Atmosphere: Spectra and Physical Effects

High-frequency fluctuations are observed with the Rapid Oscillations in the Solar Atmosphere (ROSA) instrument (Jess et al. 2010, Solar Phys, 261, 363) at the Dunn Solar Telescope. This can produce simultaneous observations in up to six channels, at different heights in the photosphere and chromosphere, at an unprecedentedly high cadence of 0.5 seconds, and at a spatial resolution of 100 km after photometrically correct speckle reconstruction. Here we concentrate on observations at two levels. The first is in the G-band of the CH radical at 4305.5Å, bandpass 9.2Å, with height of formation z <250 km at a cadence of 0.525 sec corresponding to Nyquist frequency 950 mHz. The second is in the Ca II K-line core at 3933.7Å, bandpass 1.0Å, with height of formation z <1300 km, and cadence 4.2 sec giving Nyquist frequency 120 mHz. The data span 53 min, and the maximum field of view is 45 Mm. The data were taken on 28 May 2009 in internetwork and network near disk center. Using both Fourier and Morlet wavelet methods we find evidence in the G-band spectra for intensity fluctuations above noise out to frequencies f >> 100 mHz. The K-line signal is noisier and is seen only for f <50 mHz. With wavelet techniques we find that G-band spectral power with 20 <f <100 mHz is clearly concentrated in the intergranular lanes and especially at the locations of magnetic elements indicated by G-band bright points. This wavelet power is highly intermittent in time. By cross-correlating the data we find that pulses of high-frequency G-band power in the photosphere tend to be followed by increases in K-line emission in the chromosphere with a time lag of about 2 min.

Wave Damping Observed in Upwardly Propagating Sausage-Mode Oscillations Contained within a Magnetic Pore

We present observational evidence of compressible MHD wave modes propagating from the solar photosphere through to the base of the transition region in a solar magnetic pore. High cadence images were obtained simultaneously across four wavelength bands using the Dunn Solar Telescope. Employing Fourier and wavelet techniques, sausage-mode oscillations displaying significant power were detected in both intensity and area fluctuations. The intensity and area fluctuations exhibit a range of periods from 181 to 412 s, with an average period∼290 s, consistent with the global p-mode spectrum. Intensity and area oscillations present in adjacent band passes were found to be out of phase with one another, displaying phase angles of 6.°12, 5.°82,and 15.°97 between the 4170 Å continuum–G-band,G-band–Na i D1, and Na i D1–Ca ii K heights, respectively, reiterating the presence of upwardly propagating sausage-mode waves. A phase relationship of ∼0° between same-bandpass emission and area perturbations of the pore best categorizes the waves as belonging to the “slow” regime of a dispersion diagram. Theoretical calculations reveal that the waves are surface modes, with initial photospheric energies in excess of 35,000 Wm‑2. The wave energetics indicate a substantial decrease in energy with atmospheric height, confirming that magnetic pores are able to transport waves that exhibit appreciable energy damping, which may release considerable energy into the local chromospheric plasma.

Ultrasound entropy may be a new non-invasive measure of pre-clinical vascular damage in young hypertensive patients

Background: The identification of pre-clinical microvascular damage in hypertension by non-invasive techniques has proved frustrating for clinicians. This proof of concept study investigated whether entropy, a novel summary measure for characterizing blood velocity waveforms, is altered in participants with hypertension and may therefore be useful in risk stratification.

Methods: Doppler ultrasound waveforms were obtained from the carotid and retrobulbar circulation in 42 participants with uncomplicated grade 1 hypertension (mean systolic/diastolic blood pressure (BP) 142/92 mmHg), and 26 healthy controls (mean systolic/diastolic BP 116/69 mmHg). Mean wavelet entropy was derived from flow-velocity data and compared with traditional haemodynamic measures of microvascular function, namely the resistive and pulsatility indices.

Results: Entropy, was significantly higher in control participants in the central retinal artery (CRA) (differential mean 0.11 (standard error 0.05 cms(-1)), CI 0.009 to 0.219, p 0.017) and ophthalmic artery (0.12 (0.05), CI 0.004 to 0.215, p 0.04). In comparison, the resistive index (0.12 (0.05), CI 0.005 to 0.226, p 0.029) and pulsatility index (0.96 (0.38), CI 0.19 to 1.72, p 0.015) showed significant differences between groups in the CRA alone. Regression analysis indicated that entropy was significantly influenced by age and systolic blood pressure (r values 0.4-0.6). None of the measures were significantly altered in the larger conduit vessel.

Conclusion: This is the first application of entropy to human blood velocity waveform analysis and shows that this new technique has the ability to discriminate health from early hypertensive disease, thereby promoting the early identification of cardiovascular disease in a young hypertensive population.

Forward and backward least angle regression for nonlinear system identification

A forward and backward least angle regression (LAR) algorithm is proposed to construct the nonlinear autoregressive model with exogenous inputs (NARX) that is widely used to describe a large class of nonlinear dynamic systems. The main objective of this paper is to improve model sparsity and generalization performance of the original forward LAR algorithm. This is achieved by introducing a replacement scheme using an additional backward LAR stage. The backward stage replaces insignificant model terms selected by forward LAR with more significant ones, leading to an improved model in terms of the model compactness and performance. A numerical example to construct four types of NARX models, namely polynomials, radial basis function (RBF) networks, neuro fuzzy and wavelet networks, is presented to illustrate the effectiveness of the proposed technique in comparison with some popular methods.

Material Identification of Loose Particles in Sealed Electronic Devices Using PCA and SVM

The existence of loose particles left inside the sealed electronic devices is one of the main factors affecting the reliability of the whole system. It is important to identify the particle material for analyzing their source. The conventional material identification algorithms mainly rely on time, frequency and wavelet domain features. However, these features are usually overlapped and redundant, resulting in unsatisfactory material identification accuracy. The main objective of this paper is to improve the accuracy of material identification. First, the principal component analysis (PCA) is employed to reselect the nine features extracted from time and frequency domains, leading to six less correlated principal components. And then the reselected principal components are used for material identification using a support vector machine (SVM). Finally, the experimental results show that this new method can effectively distinguish the type of materials including wire, aluminum and tin particles.