ELM-based spectral–spatial classification of hyperspectral images using extended morphological profiles and composite feature mappings

Extreme Learning Machine (ELM) is a supervised learning technique for a class of feedforward neural networks with random weights that has recently been used with success for the classification of hyperspectral images. In this work, we show that the morphological techniques can be integrated in this kind of classifiers using several composite feature mappings which are proposed for ELM. In particular, we present a spectral–spatial ELM-based classifier for hyperspectral remote-sensing images that integrates the information provided by extended morphological profiles. The proposed spectral–spatial classifier allows different weights for both spatial and spectral features, outperforming other ELM-based classifiers in terms of accuracy for land-cover applications. The accuracy classification results are also better than those obtained by equivalent spectral–spatial Support-Vector-Machine-based classifiers.     

Feasibility of estimating leaf water content using spectral indices from WorldView-3’s near-infrared and shortwave infrared bands

A recently-launched high-resolution commercial satellite, DigitalGlobe’s WorldView-3, has 8 bands in the shortwave infrared (SWIR) wavelength region, which may be capable of estimating canopy water content at 3.7-m spatial resolution. WorldView-3 also has 8 multispectral bands at 1.24-m resolution with two bands in the near-infrared (NIR). The relative spectral response functions for WorldView-3 were provided by DigitalGlobe, Inc., and band reflectances were determined for reflectance spectra of PROSPECT model simulations and leaf data from maize, trees, grasses, and broadleaf herbaceous eudicots. For laboratory measurements, the range of leaf water contents was extended by including drying leaves and leaf stacks of corn, soybean, oaks, and maples. Correlations between leaf water content and spectral indices from model simulations suggested that indices using SWIR band 1 (center wavelength 1210 nm) had low variability with respect to leaf water content, but also low sensitivity. Other indices using SWIR band 5 (2165 nm) had the highest sensitivity, but also had high variability caused by different values of the leaf structure parameter in PROSPECT. Indices using SWIR bands 2, 3 and 4 (1570, 1660, and 1730 nm, respectively) had high correlations and intermediate variability from the leaf structure parameter. Spectral indices calculated from the leaf data had the same overall patterns as the simulations for variation and sensitivity; however, indices using SWIR band 1 had low correlations, and the best correlations were from indices that used SWIR bands 2, 3 and 4. Spectral indices for maize, grasses, and herbaceous crops and weeds had similar responses to leaf water content; tree leaves had higher index values and saturated at lower leaf water contents. The specified width of NIR band 2 (860–1040 nm) overlaps the water absorption feature at 970 nm wavelength; however, the normalized difference of NIR band 1 and 2 was insensitive to water content because NIR band 2’s spectral response was most heavily weighted to wavelengths less than 930 nm. The high spatial resolution of the WorldView-3 SWIR data will help analyze how variation among plant species and functional groups affects spectral responses to differences in canopy water content.     

Estimating 3D Motion and Forces of Human–Object Interactions from Internet Videos

International Journal of Computer Vision - In this paper, we introduce a method to automatically reconstruct the 3D motion of a person interacting with an object from a single RGB video. Our method...     

Predicting airline customers’ recommendations using qualitative and quantitative contents of online reviews

Customers generally give ratings and reviews for different services that they get online or offline. These reviews and ratings aspects are effectively helpful to both the company and customers to receive feedback and make the right decisions, respectively. However, the number of reviews and ratings can increase exponentially, bringing a new challenge for the company to manage and track. Under these circumstances, it will also be hard for the customer to make the right decision. In this work, we summarize text reviews and ratings given by passengers for different airlines. The objective of this research is to predict whether the recommendation made by the customer is positive or negative. Two types of features, namely, textual feature and explicit ratings, are extracted from the dataset and other attributes. We found the relationship between such sentiments and feelings expressed in online reviews and predictive consumer recommendation decisions. We have considered quantitative content with qualitative content of online reviews in predicting recommendation decisions, which shows the work’s novelty. Additionally, the obtained results yield an essential contribution to the existing literature in terms of service evaluation, making managerial policies, and predictive consumer recommendations, etc. Moreover, we hope that this work would be helpful for practitioners who wish to utilize the technique to make the quick and essential hidden information by combining textual reviews and various service aspects ratings.

     

On pressure–velocity coupled time-integration of incompressible Navier–Stokes equations using direct inversion of Stokes operator or accelerated multigrid technique

Two fully pressure–velocity coupled approaches to time-integration of two- and three-dimensional Navier–Stokes equations discretized by finite volume method are proposed and verified. The first approach utilizes a direct sparse matrix solver to inverse the Stokes operator. In the second approach a multigrid iterative solver is accelerated by a modification of CLGS smoother that allows for derivation of an analytical solution for velocity and pressure corrections belonging to a whole row or column of finite volumes. Both approaches are tested by two- and three-dimensional natural convection benchmark problems. It is concluded that the analytical solution accelerated CLGS technique (ASA-CLGS) can be considered as a promising tool for solution of time-dependent three-dimensional fluid dynamics problems.     

Modelling of urban sensible heat flux at multiple spatial scales: A demonstration using airborne hyperspectral imagery of Shanghai and a temperature–emissivity separation approach

Urbanization related alterations to the surface energy balance impact urban warming (‘heat islands’), the growth of the boundary layer, and many other biophysical processes. Traditionally, in situ heat flux measures have been used to quantify such processes, but these typically represent only a small local-scale area within the heterogeneous urban environment. For this reason, remote sensing approaches are very attractive for elucidating more spatially representative information. Here we use hyperspectral imagery from a new airborne sensor, the Operative Modular Imaging Spectrometer (OMIS), along with a survey map and meteorological data, to derive the land cover information and surface parameters required to map spatial variations in turbulent sensible heat flux (Q_H). The results from two spatially-explicit flux retrieval methods which use contrasting approaches and, to a large degree, different input data are compared for a central urban area of Shanghai, China: (1) the Local-scale Urban Meteorological Parameterization Scheme (LUMPS) and (2) an Aerodynamic Resistance Method (ARM). Sensible heat fluxes are determined at the full 6 m spatial resolution of the OMIS sensor, and at lower resolutions via pixel aggregation and spatial averaging. At the 6 m spatial resolution, the sensible heat flux of rooftop dominated pixels exceeds that of roads, water and vegetated areas, with values peaking at ～ 350 W m^? 2, whilst the storage heat flux is greatest for road dominated pixels (peaking at around 420 W m^? 2). We investigate the use of both OMIS-derived land surface temperatures made using a Temperature–Emissivity Separation (TES) approach, and land surface temperatures estimated from air temperature measures. Sensible heat flux differences from the two approaches over the entire 2 × 2 km study area are less than 30 W m^? 2, suggesting that methods employing either strategy maybe practica1 when operated using low spatial resolution (e.g. 1 km) data. Due to the differing methodologies, direct comparisons between results obtained with the LUMPS and ARM methods are most sensibly made at reduced spatial scales. At 30 m spatial resolution, both approaches produce similar results, with the smallest difference being less than 15 W m^? 2 in mean Q_H averaged over the entire study area. This is encouraging given the differing architecture and data requirements of the LUMPS and ARM methods. Furthermore, in terms of mean study Q_H, the results obtained by averaging the original 6 m spatial resolution LUMPS-derived Q_H values to 30 and 90 m spatial resolution are within ～ 5 W m^? 2 of those derived from averaging the original surface parameter maps prior to input into LUMPS, suggesting that that use of much lower spatial resolution spaceborne imagery data, for example from Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) is likely to be a practical solution for heat flux determination in urban areas.     

Efficient computation of 3D Morse–Smale complexes and persistent homology using discrete Morse theory

We propose an efficient algorithm that computes the Morse–Smale complex for 3D gray-scale images. This complex allows for an efficient computation of persistent homology since it is, in general, much smaller than the input data but still contains all necessary information. Our method improves a recently proposed algorithm to extract the Morse–Smale complex in terms of memory consumption and running time. It also allows for a parallel computation of the complex. The computational complexity of the Morse–Smale complex extraction solely depends on the topological complexity of the input data. The persistence is then computed using the Morse–Smale complex by applying an existing algorithm with a good practical running time. We demonstrate that our method allows for the computation of persistent homology for large data on commodity hardware.     

The assessment of leaf water content using leaf reflectance ratios in the visible,near‐, and short‐wave‐infrared

The common features of spectral reflectance from vegetation foliage upon leaf dehydration are decreasing water absorption troughs in the near‐infrared (NIR) and short‐wave‐infrared (SWIR). We studied which leaf water index in the NIR and SWIR is most suitable for the assessment of leaf water content and the detection of leaf dehydration from the laboratory standpoint. We also examined the influence of the thickness of leaves upon leaf water indices. All leaf water content indices examined exhibited basic correlations with the relative water content (RWC) of leaves, while the R ₁₃₀₀/R ₁₄₅₀ leaf water index also demonstrated a high signal strength and low variability (R ²>0.94). All examined leaf reflectance ratios could also be correlated with leaf thickness. The thickness of leaves, however, was not independent of leaf RWC but appeared to decrease substantially as a result of leaf dehydration.     

Planning and scheduling a fleet of rigs using simulation–optimization

Some of the most important and expensive activities in the oil field development and production phases relate to using rigs. These can be used for drilling wells, or for maintenance activities. As rigs are usually scarce compared to the number of wells requiring service, a schedule of wells to be drilled or repaired must be devised. The objective is to minimize opportunity costs within certain operating constraints. This paper present the first stochastic approach to deals with the problem of planning and scheduling a fleet of offshore oil rigs, where the service time is assumed being uncertain. A simulation–optimization method is used to generate “expected solutions” and performance measures for rigs, as well as statistics about well allocation to rigs. The methodology can be used in two different ways – to schedule an existing fleet of rigs or to scale the size of the fleet – both contemplating the uncertain nature of the problem. The method’s expected results include performance measures for each rig, expected delay for a well to be served, the expected schedule of rigs, and a distribution of the well servicing order. The experiments based on real situations demonstrate the effectiveness of the simulation–optimization approach.     

Estimating soil thermal properties from sequences of land surface temperature using hybrid Genetic Algorithm–Finite Difference method

Most models used in land surface hydrology, vadose zone hydrology, and hydro-climatology require an accurate representation of soil thermal properties (soil thermal conductivity and volumetric heat capacity). Various empirical relations have been suggested to estimate soil thermal properties. However, they require many input parameters such as soil texture, mineralogical composition, porosity and water content, which are not always available from laboratory experiments and field measurements. In this paper, to overcome the above challenge, a hybrid numerical method, Genetic Algorithm–Finite Difference (GA–FD), is proposed to estimate soil thermal properties using land surface temperature (LST) as the only input. The genetic algorithm (GA) optimization method coupled with the finite difference (FD) modeling technique is a viable hybrid approach for estimating soil thermal properties. The finite difference method is employed to solve the heat diffusion equation and simulate LST, while a robust optimization technique (GA) is used to retrieve soil thermal properties by minimizing the difference between observed and simulated LST. Furthermore, a generalization of the hybrid model is developed for inhomogeneous soil, in which soil thermal properties are not constant throughout the soil slab. The proposed model is applied to the First International Satellite Land Surface Climatology Project (ISLSCP) Field Experiment (FIFE). The results show that the proposed hybrid numerical method is able to estimate soil thermal properties accurately, and therefore effectively eliminate the need for the unavailable soil parameters which are required by empirical methods for determining the soil thermal conductivity and volumetric heat capacity. Remarkably, the temporal variation of the retrieved soil thermal conductivity is consistent with the volumetric water content, even though no water content information is used in the model.     

3D reconstruction of specular surfaces using a calibrated projector–camera setup

Structured light is widely used for shape measurement of beamless surfaces using the triangulation principle. In the case of specular surfaces deflectometry is an appropriate method. Hereby the reflection of a light pattern is observed by a camera. The distortion of the reflected pattern is evaluated to obtain information about the reflecting surface. An important requirement for a 3d reconstruction of a specular surface by deflectometry is a calibrated measurement setup. We propose a method for the overall calibration of a setup consisting of a structured light source, a projection screen and a camera. We consider all extrinsic and intrinsic parameters for the optical mapping including a distortion model for the projector and for the camera, respectively. Given the deflectometric data obtained by the calibrated setup two methods are described which allow the 3d reconstruction of points on a specular surface. This is not trivial as a reconstruction using solely deflectometric data shows ambiguity. In the first method screen displacement between two deflectometric measurements is used to overcome this ambiguity. In the second method curvature-like features on the surface are determined to serve as starting points for a region growing approach. Results of the reconstruction of a specular surface are shown and the performance of the described reconstruction methods are compared to each other.     

Identification and spatio-temporal analysis of earthquake clusters using SOM–DBSCAN model

Neural Computing and Applications - Seismic catalogs are vital to understanding and analyzing the progress of active fault systems. The background seismicity rate in a seismic catalog, strongly...     

Implementation and solution of the diffusion–reaction equation using high-order methods

The orthogonal collocation, Galerkin, tau and least-squares methods are applied to solve a diffusion–reaction problem. In general, the least-squares method suffers from lower accuracy than the other weighted residual methods. The least-squares method holds the most complex linear algebra theory and is thus associated with the most complex implementation. On the other hand, an advantage of the least-squares method is that it always produces a symmetric and positive definite system matrix which can be solved with an efficient iterative technique such as the conjugate gradient method or its preconditioned version. For the present problem, neither the Galerkin, tau and orthogonal collocation techniques produce symmetric and positive definite system matrices, hence the conjugate gradient method is not applicable for these numerical techniques.     

Numerical solutions of generalized Burgers–Fisher and generalized Burgers–Huxley equations using collocation of cubic B-splines

In this work, we propose a numerical scheme to obtain approximate solutions of generalized Burgers–Fisher and Burgers–Huxley equations. The scheme is based on collocation of modified cubic B-spline functions and is applicable for a class of similar diffusion–convection–reaction equations. We use modified cubic B-spline functions for space variable and for its derivatives to obtain a system of first-order ordinary differential equations in time. We solve this system by using SSP-RK54 scheme. The stability of the method has been discussed and it is shown that the method is unconditionally stable. The approximate solutions have been computed without using any transformation or linearization. The proposed scheme needs less storage space and execution time. The test problems considered by the different researchers have been discussed to demonstrate the strength and utility of the proposed scheme. The computed numerical solutions are in good agreement with the exact solutions and competent with those available in the literature. The scheme is simple as well as computationally efficient. The scheme provides approximate solution not only at the grid points but also at any point in the solution range.     

Automatic extraction of the topology of 3D electrical mock-ups using a mixed octree–voxel method

This paper presents a method for the automatic identification of wiring routing and electrical topology of large aircraft harnessing mock-ups. This task constitutes one of the initial steps of an enrichment process that seeks to add electrical information to the 3D geometrical representation of the mock-ups in order to perform thermal and electrical simulations with them. The proposed solution uses spatial partition techniques of the scene containing the mock-up, combining both octrees and voxels. This method analyses large mock-ups and offers a good resolution of the wire routing with a low execution time. Results of the implementation are presented and compared with similar algorithms that use alternative partitioning techniques.     

A study of substitution,using nominal techniques and Fraenkel–Mostowksi sets

Fraenkel–Mostowski (FM) set theory delivers a model of names and alpha-equivalence. This model, now generally called the ‘nominal’ model, delivers inductive datatypes of syntax with alpha-equivalence — rather than inductive datatypes of syntax, quotiented by alpha-equivalence.The treatment of names and alpha-equivalence extends to the entire sets universe. This has proven useful for developing ‘nominal’ theories of reasoning and programming on syntax with alpha-equivalence, because a sets universe includes elements representing functions, predicates, and behaviour.Often, we want names and alpha-equivalence to model capture-avoiding substitution. In this paper we show that FM set theory models capture-avoiding substitution for names in much the same way as it models alpha-equivalence; as an operation valid for the entire sets universe which coincides with the usual (inductively defined) operation on inductive datatypes.In fact, more than one substitution action is possible (they all agree on sets representing syntax). We present two distinct substitution actions, making no judgement as to which one is ‘right’ — we suspect this question has the same status as asking whether classical or intuitionistic logic is ‘right’. We describe the actions in detail, and describe the overall design issues involved in creating any substitution action on a sets universe.Along the way, we think in new ways about the structure of elements of FM set theory. This leads us to some interesting mathematical concepts, including the notions of planes and crucial elements, which we also describe in detail.     

Estimating and source analysis of surface PM2.5 concentration in the Beijing–Tianjin–Hebei region based on MODIS data and air trajectories

Particulate matter (PM) with an aerodynamic diameter of <2.5 μm (PM_2.5) has become the primary air pollutant in most major cities in China. Some studies have indicated that there is a positive correlation between the aerosol optical thickness (AOT) and surface-level PM_2.5 concentration. In order to estimate PM_2.5 concentration over large areas, a model relating the concentration of PM_2.5 and AOT has been established. The scale height of aerosol and relative humidity as well as the effect of surface temperature and wind velocity were introduced to enhance the model. 2013 full year Moderate Resolution Imaging Spectroradiometer (MODIS) AOT data and ground measurements of the PM_2.5 concentration in the Beijing–Tianjin–Hebei region were used to fit a seasonal multivariate linear equation relating PM_2.5 concentration and AOT, and the accuracy of the model has been determined. When comparing MODIS-estimated PM_2.5 with the measurements from ground monitoring stations during spring, summer, autumn and winter, we found the R² values were 0.45, 0.45, 0.37, and 0.31, respectively. Based on this model, the spatial distribution of PM_2.5 concentration during four typical haze events sampled by seasons was derived, and displayed with the backward air trajectories calculated using the Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model. We undertook a preliminary analysis about the source of surface-level PMs and the process of its accumulation and dispersion during the haze episodes by analysing the effect of terrain and topography in the specific location of the Beijing–Tianjin–Hebei region. The spatial distribution of the PM_2.5 concentration showed that the high value region was generally in the southeast of the study area, which approximately overlapped an area of lower vegetation coverage, and the temporal variation of PM_2.5 concentration indicated that the air pollution was more severe during winter and spring than summer and autumn. The results of the analysis of backward air trajectories suggested that the hazy weather in the Beijing–Tianjin–Hebei region was mainly caused by unfavourable terrain and weather conditions.