Probabilistic Spatial Model Research Articles

Smart Collaborative Evolvement for Virtual Group Creation in Customized Industrial IoT

Customized Industrial Internet of Things (IoT) presents the needs of strong pertinence, energy saving, and simplified design. However, the services of process-oriented and chainoriented were not fully considered and addressed in traditional schemes. First, a spatial probabilistic model is established that can be used to enhance the location services of devices. Second, we construct a spatio-temporal relationship graph of different devices and describe the rules for generating association index among devices. Third, we create virtual groups with computing expressions for the problem solving. Through systematically evaluating the multiple indicators of different candidates for network generation, we demonstrate the superiority and stability of the smart collaborative evolvement.

Probabilistic co-occurrence assessment for suites of listed species.

Section 7 of the Endangered Species Act requires the US Environmental Protection Agency (US EPA) to consult with the Services (US Fish and Wildlife Service and National Marine Fisheries Service) over potential pesticide impacts on federally listed species. Consultation is complicated by the large number of pesticide products and listed species, as well as by lack of consensus on best practices for conducting co-occurrence analyses. Previous work demonstrates that probabilistic estimates of species' ranges and pesticide use patterns improve these analyses. Here we demonstrate that such estimates can be made for suites of sympatric listed species. Focusing on two watersheds, one in Iowa and the other in Mississippi, we obtained distribution records for 13 species of terrestrial and aquatic listed plants and animals occurring therein. We used maximum entropy modeling and bioclimatic, topographic, hydrographic, and land cover variables to predict species' ranges at high spatial resolution. We constructed probabilistic spatial models of use areas for two pesticides based on the US Department of Agriculture Cropland Data Layer and reduced classification errors by incorporating information on the relationships between individual pixels and their neighbors using object-based images analysis. We then combined species distribution and crop footprint models to derive overall probability of co-occurrence of listed species and pesticide use. For aquatic species, we also integrated an estimate of downstream residue transport. We report each separate species-by-use-area co-occurrence estimate and also combine these modeled co-occurrence probabilities across species within watersheds to produce an overall metric of potential pesticide exposure risk for these listed species at the watershed level. We propose that the consultation process between US EPA and the Services be based on such batched estimation of probabilistic co-occurrence for multiple listed species at a regional scale. Integr Environ Assess Manag 2022;18:1088-1100. © 2021 SETAC.

A new CNN training approach with application to hyperspectral image classification

Three main requirements of a successful application of deep learning are the network architecture, a large enough training dataset, and a good optimization algorithm. In this paper we mainly focus on the optimization part. We propose a training algorithm for convolutional neural networks which makes use of both first and second order derivatives for training different layers. We utilize an approximate second order algorithm for the classification layer while we train the rest of the network with the conventional approach which is backpropagation with first order derivatives. We show that this approach helps us achieve a higher classification accuracy with a much smaller number of training iterations compared to training the whole network with gradient descent based algorithms. Moreover, although second order optimization is generally costlier, we show that the proposed approach is trained faster not only in terms of the number of iterations but also training duration. We also present the integration of CNNs with a probabilistic spatial model and apply this to the land cover classification problem in hyperspectral images. The results show that the algorithm allows us to achieve superior results with a simple network even with limited training data compared to existing approaches.

An investigation into seasonal variations of groundwater nitrate by spatial modelling strategies at two levels by kriging and co-kriging models

Nitrate pollution of groundwater through spatial models is investigated in this paper by using a sample of nitrate values at monitoring wells using the data from four seasons of a year, in which data are sparse. Two spatial modelling strategies are formulated at two levels, in which Strategy 1 comprises: three variations of kriging-based models (ordinary kriging, simple kriging and universal kriging), which are constructed at Level 1 to predict nitrate concentrations; and a Multiple Co-Kriging (MCoK) model is used at Level 2 to enhance the accuracy of the predictions. Strategy 2 is also at two levels but employs Indicator Kriging (IK) at Level 1 as a probabilistic spatial model to predict areas at risk of exceeding two thresholds of 37.5 mg/L and 50 mg/L of nitrate concentration, and Multiple Co-Indicator Kriging (MCoIK) at Level 2 for a better accuracy. The improvements at Level 2 for both strategies are remarkable and hence they are used to gain an insight into inherent problems. The results of a study delineate areas with excessive nitrate concentrations, which are in the vicinity of urban areas and hence reflect poor planning practices since the 1990s. The results further reveal the patterns on sensitivities to seasonal variations driven by aquifer recharge and strong dilution processes in spring times; and on the role of pumpage impacting aquifers giving rise to possible hotspots of nitrate concentrations.

A Probabilistic Co-Occurrence Approach for Estimating Likelihood of Spatial Overlap Between Listed Species Distribution and Pesticide Use Patterns.

Characterizing potential spatial overlap between federally threatened and endangered ("listed") species distributions and registered pesticide use patterns is important for accurate risk assessment of threatened and endangered species. Because accurate range information for such rare species is often limited and agricultural pesticide use patterns are dynamic, simple spatial co-occurrence methods may overestimate or underestimate overlap and result in decisions that benefit neither listed species nor the regulatory process. Here, we demonstrate a new method of co-occurrence analysis that employs probability theory to estimate spatial distribution of rare species populations and areas of pesticide use to determine the likelihood of potential exposure. Specifically, we 1) describe a probabilistic method to estimate pesticide use based on crop production patterns; 2) construct species distribution models for 2 listed insect species whose ranges were previously incompletely described, the rusty-patched bumble bee (Bombus affinis) and the Poweshiek skipperling (Oarisma poweshiek); and 3) develop a probabilistic co-occurrence methodology and assessment framework. Using the principles of the Bayes' theorem, we constructed probabilistic spatial models of pesticide use areas by integrating information from land-cover spatial data, agriculture statistics, and remote-sensing data. We used maximum entropy methods to build species distribution models for 2 listed insects based on species collection and observation records and predictor variables relevant to the species' biogeography and natural history. We further developed novel methods for refinement of these models at spatial scales relevant to US Fish and Wildlife Service (FWS) regulatory priorities (e.g., critical habitat areas). Integrating both probabilistic assessments and focusing on USFWS priority management areas, we demonstrate that spatial overlap (i.e., potential for exposure) is not deterministic but instead a function of both species distribution and land use patterns. Our work serves as a framework to enhance the accuracy and efficiency of threatened and endangered species assessments using a data-driven likelihood analysis of species co-occurrence. Integr Environ Assess Manag 2019;00:1-12. © 2019 SETAC.

Integration of Neural Networks and Probabilistic Spatial Models for Acoustic Blind Source Separation

We formulate a generic framework for blind source separation (BSS), which allows integrating data-driven spectro-temporal methods, such as deep clustering and deep attractor networks, with physically motivated probabilistic spatial methods, such as complex angular central Gaussian mixture models. The integrated model exploits the complementary strengths of the two approaches to BSS: the strong modeling power of neural networks, which, however, is based on supervised learning, and the ease of unsupervised learning of the spatial mixture models whose few parameters can be estimated on as little as a single segment of a real mixture of speech. Experiments are carried out on both artificially mixed speech and true recordings of speech mixtures. The experiments verify that the integrated models consistently outperform the individual components. We further extend the models to cope with noisy, reverberant speech and introduce a cross-domain teacher–student training where the mixture model serves as the teacher to provide training targets for the student neural network.

Accurate, fast, data efficient and interpretable glaucoma diagnosis with automated spatial analysis of the whole cup to disc profile.

BackgroundGlaucoma is the leading cause of irreversible blindness worldwide. It is a heterogeneous group of conditions with a common optic neuropathy and associated loss of peripheral vision. Both over and under-diagnosis carry high costs in terms of healthcare spending and preventable blindness. The characteristic clinical feature of glaucoma is asymmetrical optic nerve rim narrowing, which is difficult for humans to quantify reliably. Strategies to improve and automate optic disc assessment are therefore needed to prevent sight loss.MethodsWe developed a novel glaucoma detection algorithm that segments and analyses colour photographs to quantify optic nerve rim consistency around the whole disc at 15-degree intervals. This provides a profile of the cup/disc ratio, in contrast to the vertical cup/disc ratio in common use. We introduce a spatial probabilistic model, to account for the optic nerve shape, we then use this model to derive a disc deformation index and a decision rule for glaucoma. We tested our algorithm on two separate image datasets (ORIGA and RIM-ONE).ResultsThe spatial algorithm accurately distinguished glaucomatous and healthy discs on internal and external validation (AUROC 99.6% and 91.0% respectively). It achieves this using a dataset 100-times smaller than that required for deep learning algorithms, is flexible to the type of cup and disc segmentation (automated or semi-automated), utilises images with missing data, and is correlated with the disc size (p = 0.02) and the rim-to-disc at the narrowest rim (p<0.001, in external validation).DiscussionThe spatial probabilistic algorithm is highly accurate, highly data efficient and it extends to any imaging hardware in which the boundaries of cup and disc can be segmented, thus making the algorithm particularly applicable to research into disease mechanisms, and also glaucoma screening in low resource settings.

Probabilistic landslide risk assessment: Case study of Bujumbura

A spatial probabilistic landslide risk assessment and mapping model has been applied in a data scare region. The probabilistic model is based on a physical model based on Mohr coulomb failure criterion. A Monte Carlo simulation technique is applied to field collected data. The results are integrated and a probability of landslide is obtained at each cell level. The results are compared to a prepared landslide inventory. The overall accuracy of the model is 79.69%.

Spatial Probabilistic Model of Block Failure Capacity of Piles in Clay

Spatial Probabilistic Model of Block Failure Capacity of Piles in Clay

Climate-driven endemic cholera is modulated by human mobility in a megacity

Although a differential sensitivity of cholera dynamics to climate variability has been reported in the spatially heterogeneous megacity of Dhaka, Bangladesh, the specific patterns of spread of the resulting risk within the city remain unclear. We build on an established probabilistic spatial model to investigate the importance and role of human mobility in modulating spatial cholera transmission. Mobility fluxes were inferred using a straightforward and generalizable methodology that relies on mapping population density based on a high resolution urban footprint product, and a parameter-free human mobility model. In accordance with previous findings, we highlight the higher sensitivity to the El Niño Southern Oscillation (ENSO) in the highly populated urban center than in the more rural periphery. More significantly, our results show that cholera risk is largely transmitted from the climate-sensitive core to the periphery of the city, with implications for the planning of control efforts. In addition, including human mobility improves the outbreak prediction performance of the model with an 11 month lead. The interplay between climatic and human mobility factors in cholera transmission is discussed from the perspective of the rapid growth of megacities across the developing world.

Spatial probabilistic pulsatility model for enhancing photoplethysmographic imaging systems.

Photoplethysmographic imaging (PPGI) is a widefield noncontact biophotonic technology able to remotely monitor cardiovascular function over anatomical areas. Although spatial context can provide insight into physiologically relevant sampling locations, existing PPGI systems rely on coarse spatial averaging with no anatomical priors for assessing arterial pulsatility. Here, we developed a continuous probabilistic pulsatility model for importance-weighted blood pulse waveform extraction. Using a data-driven approach, the model was constructed using a 23 participant sample with a large demographic variability (11/12 female/male, age 11 to 60 years, BMI 16.4 to 35.1??kg·m?2). Using time-synchronized ground-truth blood pulse waveforms, spatial correlation priors were computed and projected into a coaligned importance-weighted Cartesian space. A modified Parzen–Rosenblatt kernel density estimation method was used to compute the continuous resolution-agnostic probabilistic pulsatility model. The model identified locations that consistently exhibited pulsatility across the sample. Blood pulse waveform signals extracted with the model exhibited significantly stronger temporal correlation (W=35,p<0.01) and spectral SNR (W=31,p<0.01) compared to uniform spatial averaging. Heart rate estimation was in strong agreement with true heart rate [r2=0.9619, error (?,?)=(0.52,1.69) bpm].

Effect of Water on the Modular Structure Conformation of “Polikon K” Material

This paper presents the developed probabilistic spatial model fragments of the structure of polyacrylonitrile fiber, the monomerization composition (condensing components of the polymer matrix), and “Polikon K” – “Polikon K1a” material. The dynamic contact angle of the investigated material was experimentally determined, and the work of adhesion (1.154 mJ/m2) and wetting (73.855 mJ/m2) of the surface material was calculated. The model of the structure of the “Polikon K1a” material indicates the most likely point of interaction of copolymer polyacrylic fiber with reactive CH3– groups of the polymer matrix, namely, the interaction with the C≡N group, by breaking one bond and forming a methylene bridge. The size of the unit cell of the model was estimated: 10.6 × 10.3 × 9.7 A. The dependence of the torsion angle near the methylene bridge on the concentration of water molecules was investigated.

Generative part-based Gabor object detector

Discriminative part-based models have become the approach for visual object detection. The models learn from a large number of positive and negative examples with annotated class labels and location (bounding box). In contrast, we propose a part-based generative model that learns from a small number of positive examples. This is achieved by utilizing “privileged information”, sparse class-specific landmarks with semantic meaning. Our method uses bio-inspired complex-valued Gabor features to describe local parts. Gabor features are transformed to part probabilities by unsupervised Gaussian Mixture Model (GMM). GMM estimation is robustified for a small amount of data by a randomization procedure inspired by random forests. The GMM framework is also used to construct a probabilistic spatial model of part configurations. Our detector is invariant to translation, rotation and scaling. On part level invariance is achieved by pose quantization which is more efficient than previously proposed feature transformations. In the spatial model, invariance is achieved by mapping parts to an “aligned object space”. Using a small number of positive examples our generative method performs comparably to the state-of-the-art discriminative method.

The Multidimensional Nature of Product Perceptions within Asia

This paper seeks to understand how Asian consumers perceive Asian products, a topic that has received surprisingly little academic scrutiny to date. We demonstrate that there are systematic differences in perception effects across diverse product categories. These systematic differences are multidimensional and are interpretable in terms of country image as technology and fashion expertise. The authors demonstrate empirically that country of origin effects drive product perception in the region and that country of origin is a multidimensional construct that transcends product categories and regions. We do this using a novel methodological approach that analyzes data on product evaluations and on county perceptions simultaneously using a probabilistic spatial model. Understanding perceptions in multidimensional terms imply that developing countries should not simply imitate the strongest economy in a region, but should seek strong differentiated competitive positions. It also implies that this type of methodology is needed to flesh out the nuances of multidimensionality after accounting for other systematic product perception effects, such as consumer ethnocentrism, on behavior.

Highly localized sensitivity to climate forcing drives endemic cholera in a megacity

The population dynamics of endemic cholera in urban environments--in particular interannual variation in the size and distribution of seasonal outbreaks--remain poorly understood and highly unpredictable. In part, this situation is due to the considerable demographic, socioeconomic, and environmental heterogeneity of large and growing urban centers. Despite this heterogeneity, the influence of climate variability on the population dynamics of infectious diseases is considered a large-scale, regional, phenomenon, and as such has been previously addressed for cholera only with temporal models that do not incorporate spatial structure. Here we show that a probabilistic spatial model can explain cholera dynamics in the megacity of Dhaka, Bangladesh, and afford a basis for cholera forecasts at lead times of 11 mo. Critically, we find that the action of climate variability (El Niño southern oscillation and flooding) is quite localized: There is a climate-sensitive urban core that acts to propagate risk to the rest of the city. The modeling framework presented here should be applicable to cholera in other cities, as well as to other infectious diseases in urban settings and other biological systems with spatiotemporal interactions.

A Spatial probabilistic model of pipeline failures

A spatial probabilistic model is developed and applied to predict failure patterns over a water supply pipe network. The Zalaegerszeg waterworks is used to illustrate the methodology. The ageing of water supply pipes is a worldwide concern; therefore it is of high interest to identify the best interventions in time and space. Two-part models can be used; one is an economic by formulating time horizon total costs. The other part forecasts the break patterns in time and space. Spatial modeling is necessary since elements of the cost function depend on the location of failures. A network based model is developed for the internal part of the Zalaegerszeg waterworks since the system is homogeneous in a sense that the environmental and network features do not exhibit significant correlation with the occurrence of failures. Network based failure probabilities are described by a space-time Poisson process where non-homogeneous Poisson process (NHPP) refers to time and a stochastic point process refers to space. To es timate the intensity the whole area is covered by a grid system of 250 × 250 meters with an average pipe length of 703 meter in a cell. Both the number of and the distance between failures prove the applicability of the Poisson process. It is shown how a simulation procedure can be applied to generate possible pipe failure patterns which - by combining with the spatial cost functions - leads to estimate total costs per selected time periods.

Cross-application used to validate landslide susceptibility maps using a probabilistic model from Korea

A study of landslides in Youngin, Janghung and Boeun, Korea, using the geographic information system (GIS) validates a spatial probabilistic model for landslide susceptibility analysis. Locations were identified from aerial photographs, satellite images and field surveys. Topography, soil-type, forest-cover and land-cover maps were constructed from spatial data sets. Landslide occurrence is influenced by 13 factors, evidence for which was extracted from the database with the frequency ratio of each factor computed. Landslide susceptibility maps use frequency ratios derived not only from data for each area but also ratios, one from the probabilistic model, calculated from the other two areas (nine maps in all) as a cross-check of method validity. For validation, analytical results were compared in each study area with actual landslide locations: Boeun based on its frequency ratio showed the best accuracy (82.49%) whereas Janghung based on the Boeun frequency ratio showed the worst (69.53%).

Simulating demand for innovative radiotherapies: An illustrative model based on carbon ion and proton radiotherapy

Background and purpose Innovative therapies are not only characterized by major uncertainties regarding clinical benefit and cost but also the expected recruitment of patients. An original model was developed to simulate patient recruitment to a costly particle therapy by varying layout of the facility and patient referral (one vs. several countries) and by weighting the treated indication by the expected benefit of particle therapy. Material and methods A multi-step probabilistic spatial model was used to allocate patients to the optimal treatment strategy and facility taking into account the estimated therapeutic gain from the new therapy for each tumour type, the geographical accessibility of the facilities and patient preference. Recruitment was simulated under different assumptions relating to the demand and supply. Results Extending the recruitment area, reducing treatment capacity, equipping all treatment rooms with a carbon ion gantry and inclusion of proton protocols in carbon ion facilities led to an increased proportion of indications with the highest expected benefit. Assuming the existence of a competing carbon ions facility, lower values of therapeutic gain, and a greater unwillingness of patients to travel for treatment increased the proportion of indications with low expected benefit. Conclusions Modelling patient recruitment may aid decision-making when planning new and expensive treatments.

Extreme Compression and Modeling of Bidirectional Texture Function

The recent advanced representation for realistic real-world materials in virtual reality applications is the Bidirectional Texture Function (BTF) which describes rough texture appearance for varying illumination and viewing conditions. Such a function can be represented by thousands of measurements (images) per material sample. The resulting BTF size excludes its direct rendering in graphical applications and some compression of these huge BTF data spaces is obviously inevitable. In this paper we present a novel, fast probabilistic model-based algorithm for realistic BTF modeling allowing an extreme compression with the possibility of a fast hardware implementation. Its ultimate aim is to create a visual impression of the same material without a pixel-wise correspondence to the original measurements. The analytical step of the algorithm starts with a BTF space segmentation and a range map estimation by photometric stereo of the BTF surface, followed by the spectral and spatial factorization of selected sub-space color texture images. Single mono-spectral band-limited factors are independently modeled by their dedicated spatial probabilistic model. During rendering, the sub-space images of arbitrary size are synthesized and both color (possibly multi-spectral) and range information is combined in a bump-mapping filter according to the view and illumination directions. The presented model offers a huge BTF compression ratio unattainable by any alternative sampling-based BTF synthesis method. Simultaneously this model can be used to reconstruct missing parts of the BTF measurement space.

Influence of fire regimes on lodgepole pine stand age and density across the Yellowstone National Park (USA) landscape

A probabilistic spatial model was created based on empirical data to examine the influence of different fire regimes on stand structure of lodgepole pine (Pinus contorta var. latifolia) forests across a >500,000-ha landscape in Yellowstone National Park, Wyoming, USA. We asked how variation in the frequency of large fire events affects (1) the mean and annual variability of age and tree density (defined by postfire sapling density and subsequent stand density) of lodgepole pine stands and (2) the spatial pattern of stand age and density across the landscape. The model incorporates spatial and temporal variation in fire and serotiny in predicting postfire sapling densities of lodgepole pine. Empirical self-thinning and in-filling curves alter initital postfire sapling densities over decades to centuries. In response to a six-fold increase in the probability of large fires (0.003 to 0.018 year−1), mean stand age declined from 291 to 121 years. Mean stand density did not increase appreciably at high elevations (1,029 to 1,249 stems ha−1) where serotiny was low and postfire sapling density was relatively low (1,252 to 2,203 stems ha−1). At low elevations, where prefire serotiny and postfire lodgepole pine density are high, mean stand densities increased from 2,807 to 7,664 stems ha−1. Spatially, the patterns of stand age became more simplified across the landscape, yet patterns of stand density became more complex. In response to more frequent stand replacing fires, very high annual variability in postfire sapling density is expected, with higher means and greater variation in stand density across lodgepole pine landscapes, especially in the few decades following large fires.