Estimating parameters for multiple datasets can be time consuming, especially when the number of datasets is large. One solution is to sample from multiple datasets simultaneously using Bayesian methods such as adaptive multiple importance sampling (AMIS). Here we use the AMIS approach to fit a von Misses distribution to multiple datasets for wind trajectories derived from a Lagrangian Particle Dispersion Model driven from a 3D meteorological data. The primary objective is to characterise the uncertainties in wind trajectories in a form that can be used as inputs for predictive models of wind-dispersed insect pests and pathogens of agricultural crops for use in evaluating risk and in planning mitigation actions. Our results show that AMIS can significantly improve the efficiency of parameter inference for multiple datasets.

The fitting and modeling of skewed, complex, symmetric, and asymmetric datasets is an exciting research topic in many fields of applied sciences, notably lifetime, medical, and financial sciences. The Heavy tailed Nadarajah Haghighi model is introduced by compounding the heavy tailed family and Nadarajah Haghighi distribution in this paper. The so obtained model has three parameters accounting for the scale and shape of the distribution. The proposed distribution's fundamental characteristics such as probability density, cumulative distribution, hazard rate, and survival functions are provided, and several key statistical properties are established, and several entropy information measures are proposed. The estimation of model parameter is performed via the ML procedure. Further, different simulation experiments are conducted to demonstrate the performance of proposed estimator’s using some measure, like the average estimate, the average bias, and associated mean square error. Finally, we are applied our proposed model to analyze three different real datasets. In our illustration, we are compared the practicality of the recommended model with several well-known competing models.

Sparse training (ST) aims to ameliorate deep learning by replacing fully connected artificial neural networks (ANNs) with sparse or ultra-sparse ones, such as brain networks are, therefore it might benefit to borrow brain-inspired learning paradigms from complex network intelligence theory. Here, we launch the ultra-sparse advantage challenge, whose goal is to offer evidence on the extent to which ultra-sparse (around 1% connection retained) topologies can achieve any leaning advantage against fully connected. Epitopological learning is a field of network science and complex network intelligence that studies how to implement learning on complex networks by changing the shape of their connectivity structure (epitopological plasticity). One way to implement Epitopological (epi- means new) Learning is via link prediction: predicting the likelihood of non-observed links to appear in the network. Cannistraci-Hebb learning theory inspired the CH3-L3 network automata rule for link prediction which is effective for general-purpose link prediction. Here, starting from CH3-L3 we propose Epitopological Sparse Meta-deep Learning (ESML) to apply Epitopological Learning to sparse training. In empirical experiments, we find that ESML learns ANNs with ultra-sparse hyperbolic (epi-)topology in which emerges a community layer organization that is meta-deep (meaning that each layer also has an internal depth due to power-law node hierarchy). Furthermore, we discover that ESML can in many cases automatically sparse the neurons during training (arriving even to 30% neurons left in hidden layers), this process of node dynamic removal is called percolation. Starting from this network science evidence, we design Cannistraci-Hebb training (CHT), a 4-step training methodology that puts ESML at its heart. We conduct experiments on 7 datasets and 5 network structures comparing CHT to dynamic sparse training SOTA algorithms and the fully connected counterparts. The results indicate that, with a mere 1% of links retained during training, CHT surpasses fully connected networks on VGG16, GoogLeNet, ResNet50, and ResNet152. This key finding is an evidence for ultra-sparse advantage and signs a milestone in deep learning. CHT acts akin to a gradient-free oracle that adopts CH3-L3-based epitopological learning to guide the placement of new links in the ultra-sparse network topology to facilitate sparse-weight gradient learning, and this in turn reduces the convergence time of ultra-sparse training. Finally, CHT offers the first examples of parsimony dynamic sparse training because, in many datasets, it can retain network performance by percolating and significantly reducing the node network size. Our code is available at: https://github.com/biomedical-cybernetics/Cannistraci-Hebb-training.

The integration of deep neural networks into sparse Synthetic Aperture Radar (SAR) imaging has been explored to enhance SAR imaging performance and reduce the system’s sampling rate. However, the scarcity of training samples and mismatches between the training data and the SAR system pose significant challenges to the method’s further development. In this paper, we propose a novel SAR imaging approach based on Deep Image Prior Powered by RED (DeepRED), enabling unsupervised SAR imaging without the need for additional training data. Initially, DeepRED is introduced as the regularization technique within the sparse SAR imaging model. Subsequently, variable splitting and the Alternating Direction Method of Multipliers (ADMM) are employed to solve the imaging model, alternately updating the magnitude and phase of the SAR image. Additionally, the SAR echo simulation operator is utilized as an observation model to enhance computational efficiency. Through simulations and real data experiments, we demonstrate that our method maintains imaging quality and system downsampling rate on par with deep neural network-based sparse SAR imaging, but without the requirement for training data.

Decision tree algorithms have been among the most popular algorithms for interpretable (transparent) machine learning since the early 1980s. On the other hand, deep learning methods have boosted the capacity of machine learning algorithms and are now being used for non-trivial applications in various applied domains. But training a fully-connected deep feed-forward network by gradient-descent backpropagation is slow and requires arbitrary choices regarding the number of hidden units and layers. In this paper, we propose near-optimal neural regression trees, intending to make it much faster than deep feed-forward networks and for which it is not essential to specify the number of hidden units in the hidden layers of the neural network in advance. The key idea is to construct a decision tree and then simulate the decision tree with a neural network. This work aims to build a mathematical formulation of neural trees and gain the complementary benefits of both sparse optimal decision trees and neural trees. We propose near-optimal sparse neural trees (NSNT) that is shown to be asymptotically consistent and robust in nature. Additionally, the proposed NSNT model obtain a fast rate of convergence which is near-optimal up to some logarithmic factor. We comprehensively benchmark the proposed method on a sample of 80 datasets (40 classification datasets and 40 regression datasets) from the UCI machine learning repository. We establish that the proposed method is likely to outperform the current state-of-the-art methods (random forest, XGBoost, optimal classification tree, and near-optimal nonlinear trees) for the majority of the datasets.

It is increasingly common for experiments in biology and medicine to involve large numbers of hypothesis tests. A natural graphical method for visualizing these tests is to construct a histogram from the p-values of these tests. In this article, we examine the shapes, both normal and abnormal, that these histograms can take on, as well as present simple inferential procedures that help to interpret the shapes in terms of diagnosing potential problems with the experiment. We examine potential causes of these problems in detail, and discuss potential remedies. Throughout, examples of abnormal-looking p-value histograms are provided and based on case studies involving real biological experiments.

In this paper we explore the known connection among sustainability, resilience, and well-being within the framework of active inference. Initially, we revisit how the notions of well-being and resilience intersect within active inference before defining sustainability. We adopt a holistic concept of sustainability denoting the enduring capacity to meet needs over time without depleting crucial resources. It extends beyond material wealth to encompass community networks, labor, and knowledge. Using the Free Energy Principle, we can emphasize the role of fostering resource renewal, harmonious system-entity exchanges, and practices that encourage self-organization and resilience as pathways to achieving sustainability, both in an agent and in collectives. We start by connecting Active Inference with well-being, building on exsiting work. We then attempt to link resilience with sustainability, asserting that resilience alone is insufficient for sustainable outcomes. While crucial for absorbing shocks and stresses, resilience must be intrinsically linked with sustainability to ensure that adaptive capacities do not merely perpetuate existing vulnerabilities. Rather, it should facilitate transformative processes that address the root causes of unsustainability. Sustainability, therefore, must manifest across extended timescales and all system strata, from individual components to the broader system, to uphold ecological integrity, economic stability, and social well-being. We explain how sustainability manifests at the level of an agent, and then at the level of collectives and systems. To model and quantify the interdependencies between resources and their impact on overall system sustainability, we introduce the application of network theory and dynamical systems theory. We emphasize the optimization of precision or learning rates through the active inference framework, advocating for an approach that fosters the elastic and plastic resilience necessary for long-term sustainability and abundance.

Scene classification plays an important role in the intelligent processing of high-resolution satellite (HRS) remotely sensed image. In HRS image classification, multiple features, e.g. shape, color, and texture features, are employed to represent scenes from different perspectives. Accordingly, effective integration of multiple features always results in better performance compared to methods based on a single feature in the interpretation of HRS image. In this paper, we introduce a multi-task joint sparse and low-rank representation model to combine the strength of multiple features for HRS image interpretation. Specifically, a multi-task learning formulation is applied to simultaneously consider sparse and low-rank structure across multiple tasks. The proposed model is optimized as a non-smooth convex optimization problem using an accelerated proximal gradient method. Experiments on two public scene classification datasets demonstrate that the proposed method achieves remarkable performance and improves upon the state-of-art methods in respective applications.

The free energy principle (FEP) is a mathematical and scientific principle that describes the relationship between the physical behavior of a dynamical system and the interpretation of such behavior as carrying out inference. It blurs the boundary between the ontological mode of the system of interest and the epistemological significance it acquires through its dynamic interaction with the environment. New materialism (or neo-materialism), despite lacking a single definition, refers to a range of emerging perspectives that attempt to dismantle the long-held divisions between ontology, epistemology, and even ethics, with the aim of achieving a comprehensive transformation of naturalized thinking. In this context, new materialism provides powerful tools to reframe some of the conceptual foundations of the FEP. This paper is the first in a series that aims to systematically construct a neo-materialistic perspective for the FEP, exploring its wide-ranging implications. It serves as an introduction to the series, arguing for the justification of deploying new materialism to reframe the FEP and introducing some essential concepts to be utilized in developing a neo-materialistic account of the FEP.

The spread of ideas is a fundamental concern of today’s news ecology. Understanding the dynamics of the spread of information and its co-option by interested parties is of critical importance. Research on this topic has shown that individuals tend to cluster in echo-chambers and are driven by confirmation bias. In this paper, we leverage the active inference framework to provide an in silico model of confirmation bias and its effect on echo-chamber formation. We build a model based on active inference, where agents tend to sample information in order to justify their own view of reality, which eventually leads to them to have a high degree of certainty about their own beliefs. We show that, once agents have reached a certain level of certainty about their beliefs, it becomes very difficult to get them to change their views. This system of self-confirming beliefs is upheld and reinforced by the evolving relationship between agent's beliefs and its observations, which over time will continue to provide evidence for their ingrained ideas about the world. The epistemic communities that are consolidated by these shared beliefs, in turn, tend to produce perceptions of reality that reinforce those shared beliefs. We provide an active inference account of this community formation mechanism. We postulate that agents are driven by the epistemic value that they obtain from sampling or observing the behaviors of other agents. Inspired by digital social networks like Twitter, we build a generative model in which agents generate observable social claims or posts (e.g. `tweets') while reading the socially-observable claims of other agents, that lend support towards one of two mutually-exclusive abstract topics. Agents can choose which other agent they pay attention to at each timestep, and crucially who they attend to and what they choose to read influences their beliefs about the world. Agents also assess their local network’s perspective, influencing which kinds of posts they expect to see other agents making. The model was built and simulated simulated using the freely-available Python package pymdp. The proposed active inference model can reproduce the formation of echo-chambers over social networks, and gives us insight into the cognitive processes that lead to this phenomenon.

Probabilistic inference problems have very broad practical applications. To solve this kind of problems under conditions of certainty, an effective mathematical apparatus has been developed. In real situations, obtaining deterministic estimates of relevant probabilities is often difficult; therefore, problems with handling uncertain estimates of probabilities appear. This paper examines the problem of probabilistic inference with probability trees provided that the initial probabilities are given in the form of intervals of their possible values.

A general framework for inference in dynamical systems is described, based on the language of Bayesian probability theory and making use of the maximum entropy principle. Taking as fundamental the concept of a path, the continuity equation and Cauchy's equation for fluid dynamics arise naturally, while the specific information about the system can be included using the Maximum Caliber (or maximum path entropy) principle.

We proposed a deep learning based chemometric data analysis technique. We trained L2 regularized sparse autoencoder end-to-end for reducing the size of the feature vector to handle the classic problem of curse of dimensionality in chemometric data analysis. We introduce a novel technique of automatic selection of nodes inside hidden layer of an autoencoder through pareto optimization. Moreover, linear regression, ϵ-SVR , and Gaussian process regressor are applied on the reduced size feature vector for the regression. We evaluated our technique on orange juice and wine dataset and results are compared against state-of-the-art methods. Quantitative results are shown on Normalized Mean Square Error (NMSE) and the results show considerable improvement in the state-of- the-art.

Clustering is an important task in data mining that has become more challenging due to the ever-increasing size of available datasets. To cope with these big data scenarios, a high-performance clustering approach is required. Sparse grid clustering is a density-based clustering method that uses a sparse grid density estimation as its central building block. The underlying density estimation approach enables the detection of clusters with non-convex shapes and without a predetermined number of clusters. In this work, we introduce a new distributed and performance-portable variant of the sparse grid clustering algorithm that is suited for big data settings. Our compute kernels were implemented in OpenCL to enable portability across a wide range of architectures. For distributed environments, we added a manager-worker scheme that was implemented using MPI. In experiments on two supercomputers, Piz Daint and Hazel Hen, with up to 100 million data points in a 10-dimensional dataset, we show the performance and scalability of our approach. The dataset with 100 million data points was clustered in 1198s using 128 nodes of Piz Daint. This translates to an overall performance of 352TFLOPS. On the node-level, we provide results for two GPUs, Nvidia's Tesla P100 and the AMD FirePro W8100, and one processor-based platform that uses Intel Xeon E5-2680v3 processors. In these experiments, we achieved between 43% and 66% of the peak performance across all compute kernels and devices, demonstrating the performance portability of our approach.

Reconstruction of fine-scale information from sparse data is often needed in practical fluid dynamics where the sensors are typically sparse and yet, one may need to learn the underlying flow structures or inform predictions through assimilation into data-driven models. Given that sparse reconstruction is inherently an ill-posed problem, the most successful approaches encode the physics into an underlying sparse basis space that spans the manifold to generate well-posedness. To achieve this, one commonly uses generic orthogonal Fourier basis or data specific proper orthogonal decomposition (POD) basis to reconstruct from sparse sensor information at chosen locations. Such a reconstruction problem is well-posed as long as the sensor locations are incoherent and can sample the key physical mechanisms. The resulting inverse problem is easily solved using $l_2$ minimization or if necessary, sparsity promoting $l_1$ minimization. Given the proliferation of machine learning and the need for robust reconstruction frameworks in the face of dynamically evolving flows, we explore in this study the suitability of non-orthogonal basis obtained from Extreme Learning Machine (ELM) auto-encoders for sparse reconstruction. In particular, we assess the interplay between sensor quantity and sensor placement for a given system dimension for accurate reconstruction of canonical fluid flows in comparison to POD-based reconstruction.

Multispectral image (MSI) and hyperspectral image (HSI) fusion (MHIF) aims to address the challenge of acquiring high-resolution (HR) HSI images. This field combines a low-resolution (LR) HSI with an HR-MSI to reconstruct HR-HSI. Existing methods directly utilize transformers to perform feature extraction and fusion. Despite the demonstrated success, there exist two limitations: 1) Employing the entire transformer model for feature extraction and fusion fails to fully harness the transformer’s potential in integrating the spectral of the HSI and spatial information of the MSI. 2) HSI has a strong spectral correlation and exhibits sparsity in the spatial domain. Existing transformer-based models do not optimize this physical property, which makes their methods prone to spectral distortion. To accomplish these issues, this paper introduces a novel framework for MHIF called Sparse Mix-Attention Transformer (SAMformer). Specifically, to fully harness the advantages of the Transformer architecture, we propose a Spectral Mix Attention Block (SMAB), which concatenates the keys and values extracted from LR-HSI and HR-MSI to create a new multi-head attention module. This design facilitates the extraction of detailed long-range information across spatial and spectral dimensions. Besides, to address the spatial sparsity inherent in HSI, we incorporated a sparse mechanism within the core of SMAB called Sparse Spectral Mix Attention Block (SSMAB). In the SSMAB, we compute attention maps from queries and keys and select the K highly correlated values as the sparse attention map. This approach enables us to achieve a sparse representation of spatial information while eliminating spatially disruptive noise. Extensive experiments conducted on three benchmark datasets, namely Cave, Harvard, and Pavia Center, demonstrate the SMAformer method outperforms state-of-the-art methods.

In this paper, we propose a novel approach to recognize radar targets on inverse synthetic aperture radar (ISAR) and synthetic aperture radar (SAR) images. This approach is based on the multiple salient keypoint descriptors (MSKD) and multitask sparse representation based classification (MSRC). Thus, to characterize the targets in the radar images, we combine the scale-invariant feature transform (SIFT) and the saliency map. The goal of this combination is to reduce the SIFT keypoints and their time computing time by maintaining only those located in the target area (salient region). Then, we compute the feature vectors of the resulting salient SIFT keypoints (MSKD). This methodology is applied for both training and test images. The MSKD of the training images leads to construct the dictionary of a sparse convex optimization problem. To achieve the recognition, we adopt the MSRC taking into consideration each vector in the MSKD as a task. This classifier solves the sparse representation problem for each task over the dictionary and determines the class of the radar image according to all sparse reconstruction errors (residuals). The effectiveness of the proposed approach method has been demonstrated by a set of extensive empirical results on ISAR and SAR images databases. The results show the ability of our method to predict adequately the aircraft and the ground targets.

This paper is concerned with developing an efficient numerical algorithm for fast implementation of the sparse grid method for computing the $d$-dimensional integral of a given function. The new algorithm, called the MDI-SG ({\em multilevel dimension iteration sparse grid}) method, implements the sparse grid method based on a dimension iteration/reduction procedure, it does not need to store the integration points, nor does it compute the function values independently at each integration point, instead, it reuses the computation for function evaluations as much as possible by performing the function evaluations at all integration points in a cluster and iteratively along coordinate directions. It is shown numerically that the computational complexity (in terms of CPU time) of the proposed MDI-SG method is of polynomial order $O(Nd^3 )$ or better, compared to the exponential order $O(N(\log N)^{d-1})$ for the standard sparse grid method, where $N$ denotes the maximum number of integration points in each coordinate direction. As a result, the proposed MDI-SG method effectively circumvents the curse of dimensionality suffered by the standard sparse grid method for high-dimensional numerical integration.

We present a new penalized method for estimation in sparse logistic regression models with group structure. Group sparsity suggests us to consider the Group Lasso penalty. Being different from penalized log-likelihood estimation, our method can be viewed as a penalized weighted score function method. Under some mild conditions, we provide non-asymptotic oracle inequalities promoting group sparsity of predictors. A modified block coordinate descent algorithm based on a weighted score function is also employed. The net advantage of our algorithm over the existing Group Lasso-type procedures is that the tuning parameter can be pre-specified. The simulations show that this algorithm is considerably faster and more stable than competing methods. Finally, we illustrate our methodology with two real data sets.

In this article we introduce an extension of the Akash distribution. We use the slash 1 methodology to make the kurtosis of the Akash distribution more flexible. We study the general 2 density of this new distribution, some properties, moments, coefficients of asymmetry and kurtosis. 3 Statistical inference is performed using the methods of moments and maximum likelihood via the 4 EM algorithm. A simulation study is carried out to observe the behavior of the maximum likelihood 5 estimator. An application to a real data set with high kurtosis is considered, where it is shown that 6 the new distribution fits better than other extensions of the Akash distribution.

Classical methods for inverse problems are mainly based on regularization theory. In particular those which are based on optimization of a criterion with two parts: a data-model matching and a regularization term. Different choices for these two terms and great number of optimization algorithms have been proposed. When these two terms are distance or divergence measures, they can have a Bayesian Maximum A Posteriori (MAP) interpretation where these two terms correspond, respectively, to the likelihood and prior probability models.

In this paper, we unite concepts from Husserlian phenomenology, the active inference framework in theoretical biology, and category theory in mathematics to develop a comprehensive framework for understanding social action premised on shared goals. We begin with an overview of Husserlian phenomenology, focusing on aspects of inner time consciousness, namely, retention, primal impression, and protention. We then review active inference as a formal approach to modeling agent behavior, based on variational (approximate Bayesian) inference. Expanding upon Husserl’s model of time consciousness, we consider collective goal-directed behavior, emphasizing shared protentions among agents and their connection to the shared generative models of active inference. This integrated framework aims to formalize shared goals in terms of shared protentions, and to thereby shed light on the emergence of group intentionality. Building on this foundation, we incorporate mathematical tools from category theory; particularly, sheaf and topos theory, to furnish a mathematical image of individual and group interactions within a stochastic environment. Specifically, we employ morphisms between polynomial representations of individual agent models, allowing predictions not only of their own behaviors but also those of other agents and environmental responses. Sheaf and topos theory facilitate the construction of coherent agent worldviews and provides a way of representing consensus or shared understanding. We explore the emergence of shared protentions, bridging the phenomenology of temporal structure, multi-agent active inference systems, and category theory. Shared protentions are highlighted as pivotal for coordination and achieving common objectives. We conclude by acknowledging the intricacies stemming from stochastic systems and uncertainties in realizing shared goals.

The mutual information between the state of a neural network and the state of the external world represents the amount of information stored in the neural network that is associated with the external world. In contrast, the surprise of the sensory input indicates the unpredictability of the current input. In other words, this is a measure of inference ability, and an upper bound of the surprise is known as the variational free energy. According to the free-energy principle (FEP), a neural network continuously minimizes the free energy to perceive the external world. For the survival of animals, inference ability is considered to be more important than simply memorized information. In this study, the free energy is shown to represent the gap between the amount of information stored in the neural network and that available for inference. This concept involves both the FEP and the infomax principle, and will be a useful measure for quantifying the amount of information available for inference.

The performance of lattice-Boltzmann solver implementations usually depends mainly on memory access patterns. Achieving high performance requires then complex code which handles careful data placement and ordering of memory transactions. In this work, we analyse the performance of an implementation based on a new approach called the data-oriented language, which allows the combining of complex memory access patterns with simple source code. As a use case, we present and provide the source code of a solver for D2Q9 lattice and show its performance on GTX Titan Xp GPU for dense and sparse geometries up to 4096 2 nodes. The obtained results are promising, around 1000 lines of code allowed us to achieve performance in the range of 0.6 to 0.7 of maximum theoretical memory bandwidth (over 2.5 and 5.0 GLUPS for double and single precision, respectively) for meshes of size above 1024 2 nodes, which is close to the current state-of-the-art. However, we also observed relatively high and sometimes difficult to predict overheads, especially for sparse data structures. The additional issue was also a rather long compilation, which extended the time of short simulations, and a lack of access to low-level optimisation mechanisms.

Model-based image reconstruction has brought improvements in terms of contrast and spatial resolution to imaging applications such as magnetic resonance imaging and emission computed tomography. However, their use for pulse-echo techniques like ultrasound imaging is limited by the fact that model-based algorithms assume a finite grid of possible locations of scatterers in a medium -- which does not reflect the continuous nature of real world objects and creates a problem known as off-grid deviation. To cope with this problem, we present a method of dictionary expansion and constrained reconstruction that approximates the continuous manifold of all possible scatterer locations within a region of interest. The expanded dictionary is created using a highly coherent sampling of the region of interest, followed by a rank reduction procedure based on a truncated singular value decomposition. We develop a greedy algorithm, based on the Orthogonal Matching Pursuit (OMP), that uses a correlation-based non-convex constraint set that allows for the division of the region of interest into cells of any size. To evaluate the performance of the method, we present results of 2-dimensional ultrasound image reconstructions with simulated data in a nondestructive testing application. Our method succeeds in the reconstructions of sparse images from noisy measurements, providing higher accuracy than previous approaches based on regular discrete models.

This study introduces an innovative optimization method to identify the optimal configuration of a sparse symmetric 2D array for applications in security, particularly multistatic imaging. Utilizing Genetic Algorithms (GA) in a sophisticated optimization process, the research focuses on achieving the most favorable antenna distribution while mitigating the common issue of secondary lobes in sparse arrays. The main objective is to determine the ideal configuration from specific design parameters, including hardware specifications such as number of radiating elements, minimum spacing, operating frequency range, and image separation distance. The study employs a cost function based on the the point spread function (PSF), the system response to a point source, with the goal of minimizing the secondary lobe levels and maximizing their separation from the main lobe. Advanced simulation algorithms based on Physical Optics (PO) are used to validate the presented methodology and results.

We discuss the optimal control formulation for enhancement and denoising of satellite multiband images and propose to take it in the form of an L1-control problem for quasi-linear parabolic equation with non-local p[u]-Laplacian and with a cost functional of a tracking type. The main characteristic feature of the considered class of parabolic problems is the fact that the variable exponent p(t,x) and the anisotropic diffusion tensor D(t,x) are not well predefined a priori, but instead these characteristic non-locally depend on a solution of this problem, i.e., pu=p(t,x,u) and Du=D(t,x,u). We prove the existence of optimal pairs with sparse L1-controls using for that the indirect approach and a special family of approximation problems.

Cerebrovascular and airway structures are tubular structures used for transporting blood and gases, respectively, providing essential support for the normal activities of the human body. Accurately segmenting these tubular structures is the basis of morphology research and patho-logical detection. Nevertheless, accurately segmenting these structures from images presents great challenges due to their complex morphological and topological characteristics. To address this challenge, this paper proposes a framework UARAI based on the U-Net multi-scale reverse at-tention network and sparse convolution network. The framework utilizes a multi-scale structure to effectively extract the global and deep detail features of vessels and airways. Further, it enhances the extraction ability of fine-edge features by a joint reverse attention module. In addition, the sparse convolution structure is introduced to improve the features' expression ability without increasing the model's complexity. Finally, the proposed training sample cropping strategy re-duces the influence of block boundaries on the accuracy of tubular structure segmentation. The experimental findings demonstrate that the UARAI-based metrics, namely Dice and IoU, achieve impressive scores of 90.31% and 82.33% for cerebrovascular segmentation and 93.34% and 87.51% for airway segmentation, respectively. Compared to commonly employed segmentation tech-niques, the proposed method exhibits remarkable accuracy and robustness in delineating tubular structures such as cerebrovascular and airway. These results hold significant promise in facilitating medical image analysis and clinical diagnosis, offering invaluable support to healthcare profes-sionals.

Phylogenomics has enriched our understanding that the Tree of Life can have network-like or reticulate structures among some taxa and genes. Non-vertical modes of evolution—such as hybridization/introgression and horizontal gene transfer—deviate from a strictly bifurcating tree model, causing non-treelike patterns. Here, we present a brief overview of a phylogenomic workflow for inferring organismal histories and compare methods for detecting reticulate evolution. We discuss how the timing of coalescent events can help disentangle introgression from incomplete lineage sorting and how horizontal gene transfer events can help determine the relative timing of speciation events. In doing so, we identify pitfalls of certain methods and discuss how to extend their utility across the Tree of Life. Workflows, methods, and future directions discussed herein underscore the need to embrace reticulate evolutionary patterns for understanding the timing and rates of evolutionary events, providing a clearer understanding of life’s history.

Coastal marine ecosystems worldwide, like Florida Bay, are increasingly affected by tide alteration and anthropogenic disturbances which affect water quality imbalance leading to algal blooms. Increased bloom persistence is a serious threat due to the long-lasting impact on processes like carbon cycle and services like species presence. However, exploring eco-environmental feedback patterns of algal blooms remains challenging and poorly investigated, also due to the paucity of data. Florida Bay, taken as an epitome, has long experienced algal blooms in its central and western regions, and in 2006 an unprecedented bloom occurred in the eastern habitats. We analyzed the occurrence of blooms from three perspectives: (1) the spatial spreading networks of chlorophyll-a (CHLa) that pinpoints source and unbalanced habitats; (2) the fluctuations of water quality factors pre- and post-bloom outbreaks to in assess environmental impacts of ecological dysbiosis and target prevention and control of algal of blooms; and (3) the biogeochemical-spreading network topological co-evolution to quantify ecosystemic stability and ecological shift likelihood in long-term. Here, we propose Transfer Entropy (TE) to quantify dynamical interactions between spatial areas and biogeochemical factors (ecosystem connectome) underpinning bloom emergence and spreading, as well as environmental effects; the Pareto principle is defined for identifying the salient eco-environmental interactions of CHLa. We quantified the spatial dynamics of algal blooms, and thus obtained areas in need for ecological monitoring and potential bloom control. Results show that algal blooms are increasingly persistent over space with long-term negative effects on water quality factor. A dichotomy is reported between spatial ecological corridors of spreading and biogeochemical networks as well as divergence from the optimal eco-organization: randomization of the former due to nutrients' overload and temperature increase leads to scale-free CHLa spreading and extreme outbreaks a posteriori. Subsequently this increases bloom persistence, turbidity and salinity with potentially strong ecological effects on highly biodiverse and vulnerable areas such as tidal flats and marshes. Algal blooms are important ecosystem regulators of nutrient cycles; however, beyond limit chlorophyll-a outbreaks cause aquatic species mortality due to their effect on water turbidity, nutrient balance (nitrogen and phosphorus in particular), salinity and temperature. Beyond compromising local environmental quality, socio-ecological services are also compromised at large scales, yet ecological assessment models like the one presented are in need of application in subtropical and tropical bays worldwide.

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions to handle the computational demands. In this paper, we explore the utilization of CPUs for accelerating the inference of large language models. Specifically, we introduce a parallelized approach to enhance throughput by 1) Exploiting the parallel processing capabilities of modern CPU architectures, 2) Batching the inference request. Our evaluation shows the accelerated inference engine gives an 18-22x improvement in the generated token per sec. The improvement is more with longer sequence and larger models. In addition to this, we can also run multiple workers in the same machine with NUMA node isolation to further improvement in tokens/s. Table 2, we have received 4x additional improvement with 4 workers. This would also make Gen-AI based products and companies’ environment friendly, our estimates shows that CPU usage for Inference could reduce the power consumption of LLMs by 48.9% (1252 W for A100 with AMD EPYC 7V13 vs 613 W for Intel® Xeon® Gold 6538N) while providing production ready throughput & latency.

In this paper, we shall introduce the interval-valued spatial error model. Based on the idea of least square method of single-valued case, we give the parameter estimator for interval-valued spatial error model. The theoretical properties of the proposed estimator are proved. Finally, we give the numerical analysis and a real example.

Time-modulated sparse circular array (TMSCA) with elements uniformly excited is designed and synthesized in this paper. By utilizing rotationally symmetric structure, the array geometry and the time modulation of the TMSCA is presented, and the radiation patterns in frequency domain are formulated. In order to achieve the desired radiation pattern at the operating frequency and suppress the sideband radiation, the synthesis problem is established and solved by the proposed harmony search-convex programming (HS-CP) algorithm in two dependent optimizations. Two designs are presented, and the numerical results indicate that the TMSCA with rotationally symmetric structure has the advantages of designing time-modulated sparse arrays with superior performance.

In the era of big data, feature engineering has proved its efficiency and importance in dimensionality reduction and useful information extraction from original features. Feature engineering can be expressed as dimensionality reduction and is divided into two types of methods such as feature selection and feature extraction. Each method has its pros and cons. There are a lot of studies to combine these methods. Sparse autoencoder (SAE) is a representative deep feature learning method that combines feature selection with feature extraction. However, existing SAEs do not consider the feature importance during training. It causes extracting irrelevant information. In this paper, we propose a parallel guiding sparse autoencoder (PGSAE) to guide the information by two parallel guiding layers and sparsity constraints. The parallel guiding layers keep the main distribution using Wasserstein distance which is a metric of distribution difference, and it suppresses the leverage of guiding features to prevent overfitting. We perform our experiments using four datasets that have different dimensionality and number of samples. The proposed PGSAE method produces a better classification performance compared to other dimensionality reduction methods.

The Marchenko method is a data-driven way which makes it possible to calculate Green's functions from virtual points in the subsurface by the reflection data at the surface, only requiring a macro velocity model. This method requires collocated sources and receivers. However, in practice, subsampling of sources or receivers will cause gaps and distortions in the obtained focusing functions and Green's functions. To solve this problem, this paper proposes to integrate sparse inversion into the iterative Marchenko scheme. Specifically, we add sparsity constraints to the Marchenko equations and apply sparse inversion during the iterative process. Our work not only reduces the strict requirements on acquisition geometries, but also avoids the complexity and instability of direct inversion for Marchenko equations. This new method is applied to a two-dimensional numerical example with irregular sampled data. The result shows that it can effectively fill gaps of the obtained focusing functions and Green's functions in the Marchenko method.

Satellite scene classification is challenging because of the high variability inherent in satellite data. Although rapid progress in remote sensing techniques has been witnessed in recent years, the resolution of the available satellite images remains limited compared with the general images acquired using a common camera. On the other hand, a satellite image usually has a greater number of spectral bands than a general image, thereby permitting the multi-spectral analysis of different land materials and promoting low-resolution satellite scene recognition. This study advocates multi-spectral analysis and explores the middle-level statistics of spectral information for satellite scene representation instead of using spatial analysis. This approach is widely utilized in general image and natural scene classification and achieved promising recognition performance for different applications. The proposed multi-spectral analysis firstly learns the multi-spectral prototypes (codebook) for representing any pixel-wise spectral data, and then based on the learned codebook, a sparse coded spectral vector can be obtained with machine learning techniques. Furthermore, in order to combine the set of coded spectral vectors in a satellite scene image, we propose a hybrid aggregation (pooling) approach, instead of conventional averaging and max pooling, which includes the benefits of the two existing methods but avoids extremely noisy coded values. Experiments on three satellite datasets validated that the performance of our proposed approach is much more accurate than even the deep learning framework for spatial analysis.

The human-readable simplicity with which the CSV format was devised, together with the absence of a standard that strictly defines this format, has allowed the proliferation of several variants in the dialects with which these files are written. The latter has meant that the exchange of information between data management systems, or between countries and regions, requires human intervention during the data mining and cleansing process. This has led to the development of various computational tools that aim to accurately determine the dialects of CSV files, in order to avoid data loss at data loading stage in a given system. However, the dialect detection is a complex problem and current systems have limitations or make assumptions that need to be improved and/or extended. This paper proposes a method for determining CSV file dialects through table uniformity, a statistical approach based on table consistency and records dispersion measurement along with the detection of data type over each field. The new method has a 100\% accuracy on a dataset with 148 CSV files composed of samples coming from a data load testing framework and some others added as verification of the parsing routines. In tests on truly messy data, the proposed solution outperforms the state-of-the-art tool by achieving an improvement of about 10\% in the accuracy with which dialects are detected. Furthermore, the proposed method is accurate enough to determine dialects by reading only ten records, requiring more data to disambiguate those cases where the first records do not contain the necessary information to conclude with a dialect determination.

We present a formalism to assess the safety of the COVID19 vaccines and infer a causal relation between vaccine administration and adverse effects, in particular death. We use data on adverse effects from VAERS covering the time interval [01-10-2020, 31-12-2021] (downloaded on 1 Feb 2022). We measure a vaccine fatality rate of order 0.01 for all vaccine manufacturers and identify a strong heterogeneity in the vaccine toxicity across vaccine lots, spanning up to four orders of magnitude. We compute the correlation between vaccination dates and death dates, and produce an estimate of the time lag that maximises the correlation, finding that the onset of adverse effects happened statistically (i.e. 32-41 percentiles) within one day after the vaccine administration and that death happened statistically (i.e. 22-50 percentiles) within about two weeks after the vaccine administration. These results provide data-based insights that can guide public health measures and health insurance policies.

The effectiveness of Fuzzy Inference Systems (FISs) in manipulating uncertainty and nonlinearity makes them a subject of significant interest for decision-making in embedded systems. Accordingly, optimizing FIS hardware improves its performance, efficiency, and capabilities, leading to a better user experience, increased productivity, and cost savings. To be compatible with the limited power budget in most embedded systems, this paper presents a framework to realize ultra-low power FIS hardware. It supports optimizations for both conventional arithmetic as well as MSDF-computing to be highly consistent with MSDF-based sensors. In MSDF-computing FIS all the processes of fuzzification, inference, and defuzzification are done on serially coming data bits. To demonstrate the efficiency of the proposed framework, we utilized Matlab, Chisel3, and Vivado to implement it from high-level descriptions of FIS to hardware synthesis. We also developed a Scala library in Chisel3 to establish a connection between these tools, bridging the gap, and facilitating design space exploration at the arithmetic level. Furthermore, we realized an FIS for the navigation of autonomous mobile robots in unknown environments. Synthesis results show the superiority of the output of our suggested design framework in terms of resource usage as well as power and energy consumption compared to the Matlab HDL code generator output.

Safety is very important in aviation since a loss of safety frequently results in both fatalities and financially damaging situations that are typically unrecoverable. Thus, achieving safety as much as possible is the primary goal of practically all aviation technology work. In this study, an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based classifier is created to estimate the fault risk factor of airplanes. Five categories of real fleet data belonging to structure, electrical, avionic, motor systems, and incident statistics of the planes have been used for classifier development. A risk factor determination for each plane is the output of the developed intelligent classifier, and it can be used to identify general overhaul candidate planes and stop defects and crashes before they happen. The obtained results show that using ANFIS provides a great capability in processing many inputs and outputs depending on different types and classes in the aviation industry and thus predicting the failure risk of the airplane efficiently.

By combining stochastic variational inference with message passing algorithms we show how to solve the highly complex problem of navigation and avoidance in distributed multi-robot systems in a computationally tractable manner, allowing online implementation. Subsequently, the proposed variational method lends itself to more flexible solutions than prior methodologies. Furthermore, the derived method is verified both through simulations with multiple mobile robots and a real world experiment with two mobile robots. In both cases the robots shares the operating space and needs to cross each other’s paths multiple times without colliding.

P versus NP is considered as one of the most important open problems in computer science. This consists in knowing the answer of the following question: Is P equal to NP? A precise statement of the P versus NP problem was introduced independently by Stephen Cook and Leonid Levin. Since that date, all efforts to find a proof for this problem have failed. Another major complexity class is coNP. Whether NP = coNP is another fundamental question that it is as important as it is unresolved. In 1979, Fortune showed that if any sparse language is coNP-complete, then P = NP. We prove there is a possible sparse language in coNP-complete. In this way, we demonstrate the complexity class P is equal to NP.

Deep Learning is developing interesting tools which are of great interest for inverse imaging applications. In this work, we consider a medical imaging reconstruction task from subsampled measurements, which is an active research field where Convolutional Neural Networks have already revealed their great potential. However, the commonly used architectures are very deep and, hence, prone to overfitting and unfeasible for clinical usages. Inspired by the ideas of the green-AI literature, we here propose a shallow neural network to perform an efficient Learned Post-Processing on images roughly reconstructed by the filtered backprojection algorithm. The results obtained on images from the training set and on unseen images, using both the non-expensive network and the widely used very deep ResUNet show that the proposed network computes images of comparable or higher quality in about one fourth of time.

Increased data acquisition by uncalibrated, heterogeneous digital sensor systems such as smartphones present new challenges. Binary metrics are proposed for the quantification of cyber-physical signal characteristics and features, and a standardized constant-Q variation of the Gabor atom is developed for use with wavelet transforms. Two different continuous wavelet transform (CWT) reconstruction formulas are presented and tested under different signal to noise ratio (SNR) conditions. A sparse superposition of Nth order Gabor atoms worked well against a synthetic blast transient using the wavelet entropy and an entropy-like parametrization of the SNR as the CWT coefficient-weighting functions. The proposed methods should be well suited for sparse feature extraction and dictionary-based machine learning across multiple sensor modalities.

In recent years, Edge Intelligence (EI) has emerged, combining edge computing with AI, specifically deep learning, to run AI algorithms directly on edge devices. In practical applications, EI faces challenges related to computational power, power consumption, size, and cost, with the primary challenge being the trade-off between computational power and power consumption. This has rendered traditional computing platforms unsustainable, making heterogeneous parallel computing platforms a crucial pathway for implementing EI. In our research, we leveraged the Xilinx Zynq 7000 heterogeneous computing platform, employed High-Level Synthesis (HLS) for design, and implemented two different accelerators for LeNet-5 using loop unrolling and pipelining optimization techniques. The experimental results show that when running at a clock speed of 100 MHz, the PIPELINE accelerator, compared to the UNROLL accelerator, experiences an 8.09% increase in power consumption but speeds up by 14.972 times, making the PIPELINE accelerator superior in performance. Compared to the CPU, the PIPELINE accelerator reduces power consumption by 91.37% and speeds up by 70.387 times, while compared to the GPU, it reduces power consumption by 93.35%.This study provides two different optimization schemes for edge intelligence applications through design and experimentation, and demonstrates the impact of different quantization methods on FPGA resource consumption. These experimental results can provide a reference for practical applications, thereby providing a reference hardware acceleration scheme for edge intelligence applications.

This work presents significant results obtained by the application of global optimization techniques to the design of finite, normal form games with mixed strategies. To that end, the Fuzzy ASA global optimization method is applied to several design examples of strategic games, demonstrating its effectiveness in obtaining payoff functions whose corresponding games present a previously established Nash equilibrium. In other words, the game designer becomes able to choose a convenient Nash equilibrium for a generic finite state strategic game and the proposed method computes payoff functions that will realize the desired equilibrium, making it possible for the players to reach the favorable conditions represented by the chosen equilibrium. Considering that game theory is a very significant approach for modeling interactions between competing agents, and Nash equilibrium represents a powerful solution concept, portraying situations in which joint strategies are optimal in the sense that players cannot benefit from individually modifying their current strategies provided that other players do not change their strategies as well, it is natural to infer that the proposed method may be very useful for strategists in general. In summary, it is a genuine instance of artificial inference of payoff functions after a process of global machine learning, applied to their numerical components.

In the era of big data with increasingly complex data structures and ever-larger data scales, matrix-type data are becoming highly valued and their applications in the fields of medicine, industry, education, geography, and astronomy are growing in extent. In recent years, significant progress has been made in the practical use of matrix variable t-distribution finite mixture models for handling data in order to address the issues of multi-subgroup structures and long data tails. In this paper, the expectation-maximization (EM) algorithm with penalized maximum likelihood is proposed to resolve the problem of the unbounded nature of the likelihood function applied to the model by considering the degeneracy of the variance-covariance matrix of this model. Our data were analyzed through simulations and real data, and the results demonstrate that our model is effective in both preventing the likelihood function from being unbounded and in ensuring the accuracy of the estimated parameters of the EM algorithm.

Computer systems are involved in many critical human applications today, so that a small error can lead to serious and dangerous problems. These errors can be from an error in the incorrect design of the user interface to an error in the program code. The success of a software product depends on several factors. Given that different organizations and institutions use software products, the need to have a quality and desirable Software according to the goals and needs of the organization makes measuring the quality of software products. an important issue for most organizations and institutions, To be sure of having the right software. It is necessary to use a standard quality model to examine the features and sub-features for a detailed and principled study in the quality discussion. In this study, the quality of Word software was measured by Adaptive Neural Fuzzy Inference System. In recent years, powerful systems called fuzzy inference systems on The basis of adaptive neural network (ANFIS) has been used in various sciences. Using the power of neural network training and the linguistic advantage of fuzzy systems, these types of systems have been able to realize the advantages of the two in terms of analyzing very powerful complex processes. Considering the importance of software quality and to have a good and usable software in terms of quality and measuring the quality of software during the study. It was applied at different levels to make the result of measuring the quality of Word software more accurate and closer to reality. In this research, the quality of the software product is measured based on the adaptive neural-fuzzy inference system in ISO standard. According to the results obtained in this study, it is understood that quality is a continuous and hierarchical concept and the quality of each part of the software at any stage of production can lead to high quality products.

The maximization of entropy S within a closed system is accepted as an inevitability (as the second law of thermodynamics) by statistical inference alone. The Maximum Entropy Production Principle (MEPP) states that not only S maximizes, but $\dot{S}$ as well: a system will dissipate as fast as possible. There is still no consensus on the general validity of this MEPP, even though it shows remarkable explanatory power (both qualitatively and quantitatively), and has been empirically demonstrated for many domains. In this theoretical paper I provide a generalization of entropy gradients, to show that the MEPP actually follows from the same statistical inference, as that of the 2nd law of thermodynamics. For this generalization I only use the concepts of super-statespaces and microstate-density. These concepts also allow for the abstraction of 'Self Organizing Criticality' to a bifurcating local difference in this density, and allow for a generalization of the fundamentally unresolved concepts of 'chaos' and 'order'.

Medical insurance claims are becoming increasingly common data sources to answer a variety of questions in biomedical research. Although comprehensive in terms of longitudinal characterization of disease development and progression for a potentially large number of patients, population-based studies using these datasets require thoughtful modification to sample selection and analytic strategies, relative to other types of studies. Along with complex selection bias and missing data issues, claims-based studies are purely observational, which limits effective understanding and characterization of the treatment differences between groups being compared. All these issues contribute to a crisis in reproducibility and replication of comparative findings. This paper offers some practical guidance to the full analytical process, demonstrates methods for estimating causal treatment effects on several types of outcomes common to such studies, such as binary, count, time to event and longitudinally varying repeated measures outcomes, and aims to increase transparency and reproducibility. We provide an online version of the paper with readily implementable code for the entire analysis pipeline to serve as a guided tutorial for practitioners. The online version can be accessed at https://rydaro.github.io/. The analytic pipeline is illustrated using a sub-cohort of patients with advanced prostate cancer from the large Clinformatics TM Data Mart Database (OptumInsight, Eden Prairie, Minnesota), consisting of 73 million distinct private payer insurees from 2001-2016.

Ridge regression is one of the most popular shrinkage estimation methods for linear models. Ridge regression effectively estimates regression coefficients in the presence of high-dimensional regressors. Recently, a generalized ridge estimator was suggested by generalizing the uniform shrinkage of ridge regression to the non-uniform shrinkage, which was shown to perform well under sparse and high-dimensional linear models. In this paper, we introduce our newly developed R package “g.ridge” (the first version published on 2023-12-07 at https://cran.r-project.org/package=g.ridge) that implements both the ridge estimator and generalized ridge estimators. The package equips with the generalized cross-validation for automatic estimation of shrinkage parameters. The package also includes a convenient tool for generating a design matrix. By simulations, we test the performance of the R package under sparse and high-dimensional settings with the normal and skew-normal error distributions. From the simulation results, we conclude that the generalized ridge estimator is superior to the benchmark ridge estimator based on “glmnet”, and hence, it can be the most recommended estimator under sparse and high-dimensional models. We demonstrate the package using the intracerebral hemorrhage data.

Sparse recovery of fluid flows using data-driven proper orthogonal decomposition (POD) basis is systematically explored in this work. Fluid flows are manifestations of nonlinear multiscale PDE dynamical systems with inherent scale separation that impact the system dimensionality. Given that sparse reconstruction is inherently an ill-posed problem, the most successful approaches require the knowledge of the underlying basis space spanning the manifold in which the system resides. In this study, we employ an approach that learns basis from singular value decomposition (SVD) of training data to reconstruct sparsely sensed information. This results in a set of four control parameters for sparse recovery, namely, the choice of basis, system dimension required for sufficiently accurate reconstruction, sensor budget and their placement. The choice of control parameters implicitly determines the choice of algorithm as either $l_2$ minimization reconstruction or sparsity promoting $l_1$ norm minimization reconstruction. In this work, we systematically explore the implications of these control parameters on reconstruction accuracy so that practical recommendations can be identified. We observe that greedy-smart sensor placement provides the best balance of computational complexity and robust reconstruction for marginally oversampled cases which happens to be the most challenging regime in the explored parameter design space.

Consistent data is seldom available for whole-catchment flood modelling in many developing regions, thus this study demonstrates how the complementary strengths of open and readily available geospatial datasets and tools can be leverage to map flood risk within acceptable levels of uncertainty for flood risk management. Available fragmented remotely-sensed and in situ datasets (including hydrological data, altimetry, digital elevation model, bathymetry, aerial photos, optical and radar imageries) are systematically integrated using 2-dimensional CAESAR-LISFLOOD model to quantify and recreate the extent and impact of the historic 2012 flood in Nigeria. Experimental modelling, calibration and validation is undertaken for the whole Niger-South hydrological catchment area of Nigeria, then segmented into sub-domains for re-validation to understand how data variability and uncertainties impact on the accuracy of model outcomes. Furthermore, aerial photos are applied for the first time in the study area for flood model validation and to understand how different physio-environmental properties influence synthetic aperture radar flood delineation capacity in the Niger Delta region of Nigeria.

In this paper we present an efficient technique for the synthesis of very large sparse arrays, with arbitrary circularly symmetrical upper bounds for the pattern specifications. The algorithm, that is based on iterative smooth re-weighted L1 minimizations is very flexible, and is capable of achieving very good performances with respect to competitive algorithms. Furthermore, thanks to its efficiency, planar arrays of hundreds of wavelengths can be synthesized with limited computational effort.

Reliable quantification of pulmonary arterial pressure is essential in the diagnostic and prognostic assessment of a range of cardiovascular pathologies including rheumatic heart disease, yet an accurate and routinely available method for its quantification remains elusive. This work proposes an approach to infer pulmonary arterial pressure based on scientific machine learning techniques and non-invasive, clinically available measurements. A 0-D multicompartment model of the cardiovascular system was optimized using several optimization algorithms, subject to forward-mode automatic differentiation. Measurement data were synthesized from known parameters to represent the healthy, mitral regurgitant, aortic stenosed and combined valvular disease situations with and without pulmonary hypertension. Eleven model parameters were selected for optimization based on 95 % explained variation in mean pulmonary arterial pressure. A hybrid Adam and limited-memory Broyden-Fletcher-Goldfarb-Shanno optimizer yielded the best results with input data including valvular flow rates, heart chamber volume changes and systematic arterial pressure. Mean absolute percentage errors ranged from 1.8 % to 3.78 % over the simulated test cases. The model was able to capture pressure dynamics under hypertensive conditions with pulmonary arterial systole, diastole, and mean pressure average percentage errors of 1.12 %, 2.49 % and 2.14 %, respectively. The relatively low errors highlight the potential of the proposed model to recover pulmonary pressures for diseased heart valve and pulmonary hypertensive conditions.

An approach to the assessment of probabilistic inference is described which quantifies the performance on the probability scale. From both information and Bayesian theory, the central tendency of an inference is proven to be the geometric mean of the probabilities reported for the actual outcome and is referred to as the “Accuracy.” Upper and lower error bars on the accuracy are provided by the arithmetic mean and the -2/3 mean. The arithmetic is called the “Decisiveness” due to its similarity with the cost of a decision and the -2/3 mean is called the “Robustness”, due to its sensitivity to outlier errors. Visualization of inference performance is facilitated by plotting the reported model probabilities versus the histogram calculated source probabilities. The visualization of the calibration between model and source is summarized on both axes by the arithmetic, geometric, and -2/3 means. From information theory, the performance of the inference is related to the cross-entropy between the model and source distribution. Just as cross-entropy is the sum of the entropy and the divergence; the accuracy of a model can be decomposed into a component due to the source uncertainty and the divergence between the source and model. Translated to the probability domain these quantities are plotted as the average model probability versus the average source probability. The divergence probability is the average model probability divided by the average source probability. When an inference is over/under-confident, the arithmetic mean of the model increases/decreases, while the -2/3 mean decreases/increases, respectively.

Studies employing Arellano-Bond and Blundell-Bond GMM estimation for single linear dynamic panel data models are growing exponentially in number. However, for researchers it is hard to make a reasoned choice between many different possible implementations of these estimators and associated tests. By simulation the effects are examined of many options regarding: (i) reducing, extending or modifying the set of instruments; (ii) specifying the weighting matrix in relation to the type of heteroskedasticity; (iii) using (robustified) 1-step or (corrected) 2-step variance estimators; (iv) employing 1-step or 2-step residuals in Sargan-Hansen overall or incremental overidentification restrictions tests. This is all done for models in which some regressors may be either strictly exogenous, predetermined or endogenous. Surprisingly, particular asymptotically optimal and relatively robust weighting matrices are found to be superior in finite samples to ostensibly more appropriate versions. Most of the variants of tests for overidentification restrictions show serious deficiencies. A recently developed modification of GMM is found to have great potential when the cross-sectional heteroskedasticity is pronounced and the time-series dimension of the sample not too small. Finally all techniques are employed to actual data and lead to some profound insights.

Dynamic sparse training is an effective strategy to alleviate the training and inference demands of artificial neural networks. However, current sparse training methods face a challenge in achieving high levels of sparsity while maintaining performance comparable to that of their fully connected counterparts. The Cannistraci-Hebb training (CHT) method produces an ultra-sparse advantage compared to fully connected training in various tasks by using a gradient-free link regrowth method, which relies solely on the network topology. However, its rigid selection based on link prediction scores may lead to epitopological local minima, especially at the beginning of the training process when the network topology might be noisy and unreliable. In this article, we introduce the Cannistraci-Hebb training soft rule (CHTs), which applies a flexible approach to both the removal and regrowth of links during training, fostering a balance between exploring and exploiting network topology. Additionally, we investigate the network topology initialization using several approaches, including the bipartite scale-free and bipartite small-world network models. Empirical results show that CHTs can surpass the performance of fully connected networks with MLP architecture by using only 1% of the connections (99% sparsity) on the MNIST, EMNIST, and Fashion MNIST datasets and can provide remarkable results with only 0.1% of the links (99.9% sparsity). In some MLPs for image classification tasks, CHTs can reduce the active neuron network size to 20% of the original nodes (neurons), demonstrating a remarkable ability to generalize better than fully connected architectures, reducing the entire model size. This represents a relevant result for dynamic sparse training. Finally, we present evidence from larger network models such as Transformers, with 10% of the connections (90% sparsity), where CHTs outperform other prevalent dynamic sparse training methods in machine translation tasks.

Deep learning heavily relies on statistical correlations to drive artificial intelligence (AI) innovations, particularly in computer vision applications like autonomous driving and robotics. However, despite providing a solid foundation for deep learning, these statistical correlations can be vulnerable to unforeseen and uncontrolled factors. The lack of prior knowledge guidance can result in spurious correlations, introducing confounding factors and affecting the model's robustness. To address this challenge, recent research efforts have focused on integrating causal theory into deep learning methodologies. By modelling the inherent and unbiased causal structure, causal theory can potentially mitigate the impact of spurious correlations effectively. Hence, this paper explores the basics of causal methodologies in image classification.

Sparse direction-of-arrival (DOA) estimation of wideband signal has attracted widespread researches for its unique high-resolution performance. Numerous existing methods based on sparse Bayesian learning (SBL) don’t possess the ability to enhance sparsity even if they have already enjoyed high favor among sparse recovery approaches. In view of this, we propose a novel hierarchical Bayesian prior framework that enhance sparsity evidently and derive its corresponding iterative algorithm. On analysis, the computational complexity of the iterative are less than most existing other state-of-the-art algorithms. Not only that, proposed method possesses high angular estimation precision and sparsity performance by utilizing joint sparsity of multiple measure vector (MMV) models. Last but not least, the method obtains the ability to stabilize the estimated values between different frequencies or snapshots such that flat spatial spectrum. Extensive simulation results are presented to prove the superior performance of our methods

The description of stellar interiors remains as a big challenge for the nuclear astrophysics community. The consolidated knowledge is restricted to density regions around the saturation of hadronic matter $\rho _{0} = 2.8\times 10^{14} {\rm\ g\ cm^{-3}}$, regimes where our nuclear models are successfully applied. As one moves towards higher densities and extreme conditions up to five to twenty times $\rho_{0}$, little can be said about the microphysics of such obejects. Here, we employ an MCMC strategy in order to access the variability of polytropic three-pircewised models for neutron star equation of states. With a fixed description of the hadronic matter we explore a variety of models for the high density regimes leading to stellar masses up to 2.5 $M_{\odot}$. In addition, we also discuss the use of a Bayesian power regression model with heteroscedastic error. The set of EoS from LIGO was used as inputs and treated as data set for testing case.

This paper investigates an inverse problem of option pricing in the extended Black--Scholes model. We identify the model coefficients from the measured data and attempt to find arbitrage opportunities in financial markets using a Bayesian inference approach. The posterior probability density function of the parameters is computed from the measured data. The statistics of the unknown parameters are estimated by Markov Chain Monte Carlo (MCMC), which explores the posterior state space. The efficient sampling strategy of MCMC enables us to solve inverse problems by the Bayesian inference technique. Our numerical results indicate that the Bayesian inference approach can simultaneously estimate the unknown drift and volatility coefficients from the measured data.

Multimodal medical image fusion is a fundamental but challenging problem in the fields of brain science research and brain disease diagnosis, and it is challenging for sparse representation (SR)-based fusion to characterize activity level with single measurement and no loss of effective information. In this paper, the Kronecker-criterion-based SR framework is applied for medical image fusion with a patch-based activity level integrating salient features of multiple domains. Inspired by the formation process of vision system, the spatial saliency is characterized by textural contrast (TC), which is composed of luminance and orientation contrasts to promote more highlighted texture information to participate in the fusion process. As substitution of the conventional l1-norm-based sparse saliency, a metric of sum of sparse salient features (SSSF) is used for promoting more significant coefficients to participate in the composition of activity level measure. The designed activity level measure is verified to be more conducive to maintain the integrity and sharpness of detailed information. Various experiments on multiple groups of clinical medical images verify the effectiveness of the proposed fusion method on both visual quality and objective assessment. Furthermore, the research work of this paper is helpful for further detection and segmentation of medical images.

What is the function of cognition? On one influential account, cognition evolved to co-ordinate behaviour with environmental change or complexity (Godfrey-Smith 1996). Liberal interpretations of this view ascribe cognition to an extraordinarily broad set of biological systems – even bacteria, which modulate their activity in response to salient external cues, would seem to qualify as cognitive agents. However, equating cognition with adaptive flexibility per se glosses over important distinctions in the way biological organisms deal with environmental complexity. Drawing on contemporary advances in theoretical biology and computational neuroscience, we cash these distinctions out in terms of different kinds of generative models, and the representational and uncertainty-resolving capacities they afford. This analysis leads us to propose a formal criterion for delineating cognition from other, more pervasive forms of adaptive plasticity. On this view, biological cognition is rooted in a particular kind of functional organisation; namely, that which enables the agent to detach from the present and engage in counterfactual (active) inference.

In complex systems constrained by multiple factors, it is of great significance to accurately identify the key influencing factors for mastering the evolution and development law of the system and obtaining scientific decision-making suggestions or schemes. At present, the method based on experimental simulation is limited by the difficulty of system model construction; the method based on decision trial and Evaluation laboratory (DEMATEL) involves a wide range of subjects and is greatly influenced by subjective factors. In view of this, we propose a novel model based on heuristic causal inference. The model uses the FCI algorithm with prior knowledge to learn the global causal network among multiple factors of the complex system. The causal effect among variables in the causal network is calculated by using heuristic causal inference method. Specifically, the causal path contribution degree of cause variable to target variable is calculated to replace the causal effect of each cause variable to target variable. The key influencing factors in the system are screened out according to the contribution degree of causal pathways. Based on the dataset generated in the production process of a semiconductor manufacturing system, we carried out simulation experiments, identified several factors that have a key impact on product quality, and proved the feasibility and effectiveness of the proposed model.

A Mamdani-type fuzzy-logic model has been developed to link Mediterranean seagrass abundance to the prevailing environmental conditions. Big Databases, as UNEP-WCMC (seagrass abundance), CMEMS and EMODnet (oceanographic/environmental) and human-impact parameters were utilized for this expert system. Model structure and input parameters were tested according to their capacity to accurately predict seagrass families at specific locations. The optimum FIS comprised of four input variables: water depth, sea surface temperature and nitrates and bottom chlorophyll-a concentration, exhibiting fair accuracy (76%). Results illustrated that Posidoniaceae prefers cool (16-18oC) and low chlorophyll-a presence (< 0.2 mg/m3); Zosteraceae favors cool (16-18oC) and mesotrophic waters (Chl-a > 0.2 mg/m3), but also slightly warmer (18-19.5 oC) with lower Chl-a levels (< 0.2 mg/m3); Cymodoceaceae lives from warm, oligotrophic (19.5-21.0oC and Chl-a < 0.3 mg/m3) to moderately warm mesotrophic sites (18-21.3oC and 0.3 – 0.4 mg/m3 Chl-a). Finally, Hydrocharitaceae thrives in warm Mediterranaean waters (21-23oC) of low chlorophyll-a content (< 0.25 mg/m3). Climate change scenarios showed that Posidoniaceae and Zosteraceae tolerate bathymetric changes, Posidoniaceae and Zosteraceae are mostly affected by sea temperature rise, while Hydrocharitaceae exhibits tolerance in higher sea temperature rise. This FIS could be used by national and regional policy-makers and public authorities.

In this study, based on our previous study, we examined the mathematical properties, especially the stability of the equilibrium for our proposed mathematical model. By means of the results of the stability in this study, we also used actual data representing transient booms and resurgent booms, and conducted parameter estimation for our proposed model using Bayesian inference. In addition, we conducted a model fitting to five actual data. By this study, we reconfirmed that we can express the resurgences or minute vibrations of actual data by means of our proposed model.

In the past few decades, probabilistic interpretations of brain functions have become widespread in cognitive science and neuroscience. In particular, the free energy principle and active inference are increasingly popular theories of cognitive functions that claim to offer a unified understanding of life and cognition within a general mathematical framework derived from information and control theory, and statistical mechanics. However, we argue that if the active inference proposal is to be taken as a general process theory for biological systems, it is necessary to understand how it relates to existing control theoretical approaches routinely used to study and explain biological systems. For example, recently, PID control has been shown to be implemented in simple molecular systems and is becoming a popular mechanistic explanation of behaviours such as chemotaxis in bacteria and amoebae, and robust adaptation in biochemical networks. In this work, we will show how PID controllers can fit a more general theory of life and cognition under the principle of (variational) free energy minimisation when using approximate linear generative models of the world. This more general interpretation provides also a new perspective on traditional problems of PID controllers such as parameter tuning as well as the need to balance performances and robustness conditions of a controller. Specifically, we then show how these problems can be understood in terms of the optimisation of the precisions (inverse variances) modulating different prediction errors in the free energy functional.

The storm 'Daniel' has caused the most severe flood phenomenon that Greece has ever experienced, with thousands of hectares of farmland submerged for days. This led to sediment deposition in the inundated areas, which significantly altered the chemical properties of the soil, as revealed by extensive soil sampling and laboratory analysis. Causal relationships between soil chemical properties and sediment deposition were extracted using the DirectLiNGAM algorithm. Results of causality analysis showed that the sediment deposition affected the CaCO3 concentration in the soil. Also, causal relationships were identified between CaCO3 and available phosphorus (P-Olsen), as well as between sediment deposit depth and available manganese. The quantified relationships between the soil variables were then used to generate data using a Multiple Linear Perceptron (MLP) regressor for various levels of deposit depth (0, 5, 10, 15, 20, 25 and 30 cm). Then linear regression equations were fitted across the different levels of deposit depth to determine the effect of deposit depth on CaCO3, P, and Mn. The results show that there is a linear slope of 0.12, -0.16, and 0.13, for CaCO3, P, and Mn with deposit depth, respectively. Statistical analysis indicates that corn growing in soils with sediment over 10 cm requires a 31.8% increase in P rate to prevent yield decline. Additional notifications regarding cropping strategies in the near future are also discussed.

Human keratinocytes and melanoma can stick together to form clusters after eight days in co-culture. As in dynamic system concepts, one can consider cluster formation as the system attractor, cell seeding as the initial condition, and density change over time as a path within the basin of attraction. Herein, Cellular Automata, which is a class of Agent-Based Models, and Boolean Networks are discrete modeling methods used in population dynamics such that running the dynamics of cellular automata backward reveals an underlying network in terms of basin of attraction, also known as global dynamics. Thus, we hypothesize that one can estimate the local dynamic of an agent-based model from the basin of attraction of a boolean network. Here, we propose an approach to estimating these agent-based model rules, which consists of comparing the density states within each state transition and reaching a consensus among state transitions belonging to a basin of attraction of a boolean network. The objectives of this study are: (1) to infer a boolean network from the co-culture growth curve; (2) to estimate the rules of agent-based models; and (3) to implement spatial dynamics simulations. The binarization of the growth curve shows high population density after four days; the estimated agent-based model rules were compatible with cell proliferation and migration in agreement with literature, so we had to propose individual rules for survival and death. Spatial dynamics shows that (1) keratinocytes exhibit a higher density in neighborhoods where melanoma is present; (2) the chance of keratinocyte migration increases until the fourth day, then decreases, and the probability of survival increases substantially after four days; and (3) cells with low proliferation capacity die and free space for those with high ones. Our approach suggests that the attractor state of cell co-culture is induced mainly by an increase in keratinocyte migration and survival. Our approach has the potential to offer valuable clues about microenvironmental interactions or configurations that drive population dynamics.

Emotion recognition and social inference impairments are well-documented post-traumatic brain injury (TBI) yet the mechanisms underpinning these are not fully understood. We examined dynamic emotion recognition, social inference abilities, and eye fixation patterns between adults with and without TBI. Eighteen individuals with TBI and 18 matched non-TBI participants were recruited and underwent all three components of The Assessment of Social Inference Test (TASIT). The TBI group were less accurate in identifying emotions compared to the non-TBI group. Individuals with TBI also scored lower when distinguishing sincere and sarcastic conversations but scored similarly to those without TBI during lie vignettes. Finally, those with TBI also had difficulty understanding the actor’s intentions, feelings, and beliefs compared to participants without TBI. No group differences were found for eye fixation patterns and there were no associations between fixations and behavioural accuracy scores. This conflicts with previous studies and might be related to an important distinction between static and dynamic stimuli. Visual strategies appeared goal- and stimulus-driven, with attention being distributed to the most diagnostic area of the face for each emotion. These findings suggest that low-level visual deficits may not be modulating emotion recognition and social inference disturbances post-TBI.

Using a simple model for internal heat evolution and mass-internal heat relations found for rocky exo planetary objects in the inner solar system we have inferred the phases of volcanism at earth ( EA) or host star ages (SA) in 52 potentially habitable rocky exo planets. We have also calculated the internal tidal heat contributions and magnetic moments of these exo planets. Based on these results we have inferred the probability of existence of life favouring geophysical conditions in the above exo planets at EA and SA. In M star associated exo planets, occurrences of super flares and long night periods may pose problems for the development of advanced life

Three-Dimensional reconstruction of the corneal surface provides a powerful tool for managing corneal diseases. This study proposes a novel method for reconstructing the corneal surface from elevation point clouds, using modal schemes capable of reproducing corneal shapes using surface polynomial functions. The multivariable polynomial fitting was performed using a non-dominated sorting multivariable genetic algorithm (NS-MVGA). Standard reconstruction methods using least-squares discrete fitting (LSQ) and sequential quadratic programming (SQP) were compared with the evolutionary algorithm-based approach. The study included 49 eyes of 49 patients (ages 11-63) sorted in two groups: control (33 eyes) and keratoconus (KC) (16 eyes). Tomographic information (Sirius, Costruzione Strumenti Oftalmici, Italy) was processed using Matlab. The goodness of fit for each method was evaluated using mean squared error (MSE), measured at the same nodes where the elevation data were collected. Polynomial fitting based on NS-MVGA improves MSE values by 86% compared to LSQ-based methods in healthy patients. Moreover, this new method improves aberrated surface reconstruction by 43% for Amsler-Krumeich (AK) Grade 1 keratoconus patients. Finally, significant improvements were also found in morpho-geometric parameters, such as asphericity and corneal curvature radii.

The development and application of marine current energy are attracting more and more attention around the world. Due to the hardness of its working environment, it is important and difficult to study the fault diagnosis of a marine current generation system. In this paper, an underwater image is chosen as the fault-diagnosing signal, after different sensors are compared. This paper proposes a diagnosis method based on the sparse autoencoder (SA) and softmax regression (SR). The SA is used to extract the features and SR is used to classify them. Images are used to monitor whether the blade is attached by benthos and to determine its corresponding degree of attachment. Compared with other methods, the experiment results show that the proposed method can diagnose the blade attachment with higher accuracy.

Self-esteem, the evaluation of one's own worth or value, is a critical aspect of psychological well-being and mental health. In this paper, we propose an active inference account of self-esteem, casting it as a sociometer, or an inferential capacity to interpret one's standing within a social group. This approach allows us to explore the interaction between an individual's self-perception and the expectations of their social environment.When there's a mismatch between these perceptions and expectations, the individual needs to adjust their actions or update their self-perception to better align with their current experiences. We also consider this hypothesis in relation to recent research on affective inference, suggesting that self-esteem enables the individual to track and respond to this discrepancy through affective states such as anxiety or positive affect. By acting as an inferential sociometer, self-esteem allows individuals to navigate and adapt to their social environment, ultimately impacting their psychological well-being and mental health.

Deploying UAVs as aerial base stations is an exceptional approach to reinforce terrestrial infrastructure owing to their remarkable flexibility and superior agility. However, it is essential to design their flight trajectory effectively to make the most of UAV-assisted wireless communications. This paper presents a novel method for improving wireless connectivity between UAVs and terrestrial users through effective path planning. This is achieved by developing a goal-directed trajectory planning method using active inference. First, we create a global dictionary using TSPWP instances executed on various training examples. This dictionary contains letters representing available hotspots, tokens representing local paths, and words depicting complete trajectories and hotspot order. By using this world model, the UAV can understand the TSPWP’s decision-making grammar and how to use the available letters to form tokens and words at various levels of abstraction and time scales. With this knowledge, the UAV can assess encountered situations and deduce optimal routes based on the belief encoded in the world model. Our proposed method outperforms traditional Q-learning by providing fast, stable, and reliable solutions with good generalization ability.

Bayesian techniques for engineering problems, that rely on Gaussian process (GP) regression, are known for their ability to quantify epistemic and aleatory uncertainties and for being data efficient. The mathematical elegance of applying these methods usually comes at a high computational cost when compared to deterministic and empirical Bayesian methods. Furthermore, using these methods becomes practically infeasible in scenarios characterized by a large number of inputs and thousands of training data. The focus of this work is on enhancing Gaussian Process-based metamodeling and model calibration tasks, when the size of the training datasets is significantly large. To achieve this goal, we employ a stochastic variational inference algorithm that enables rapid statistical learning of the calibration parameters and hyperparameter tuning, while retaining the rigor of Bayesian inference. The numerical performance of the algorithm is demonstrated on multiple metamodeling and model calibration problems with thousands of training data.

The success of a software product depends on several factors. Given that different organizations and institutions use software products, the need to have a quality and desirable software according to the goals and needs of the organization makes measuring the quality of software products an important issue for most organizations and institutions. To be sure of having the right software. It is necessary to use a standard quality model to examine the features and sub-features for a detailed and principled study in the quality discussion. In this study, the quality of Word software was measured. Considering the importance of software quality and to have a good and usable software in terms of quality and measuring the quality of software during the study, experts and skilled in this field were used and the impact of each factor and quality characteristics. It was applied at different levels according to their opinion to make the result of measuring the quality of Word software more accurate and closer to reality. In this research, the quality of the software product is measured based on the fuzzy inference system in ISO standard. According to the results obtained in this study, it is understood that quality is a continuous and hierarchical concept and the quality of each part of the software at any stage of production can lead to high quality products.

Most existing flexible count regression models allow only approximate inference. Balanced discretization is a simple method to produce a mean-parametrizable flexible count distribution starting from a continuous probability distribution. This makes easy the definition of flexible count regression models allowing exact inference under various types of dispersion (equi-, under- and overdispersion). This study describes maximum likelihood (ML) estimation and inference in count regression based on balanced discrete gamma (BDG) distribution and introduces a likelihood ratio based latent equidispersion (LE) test to identify the parsimonious dispersion model for a particular dataset. A series of Monte Carlo experiments were carried out to assess the performance of ML estimates and the LE test in the BDG regression model, as compared to the popular Conway-Maxwell-Poisson model (CMP). The results show that the two evaluated models recover population effects even under misspecification of dispersion related covariates, with coverage rates of asymptotic 95% confidence interval approaching the nominal level as the sample size increases. The BDG regression approach, nevertheless, outperforms CMP regression in very small samples (n = 15 − 30), mostly in overdispersed data. The LE test proves appropriate to detect latent equidispersion, with rejection rates converging to the nominal level as the sample size increases. Two applications on real data are given to illustrate the use of the proposed approach to count regression analysis.

Demographic processes directly affect patterns of genetic variation within contemporary populations as well as future generations, allowing for demographic inference from patterns of both present day and past genetic variation. Advances in laboratory procedures and sequencing and genotyping technologies in the last decades have resulted in massive increases in high quality genome-wide genetic data from present day populations and allowed retrieving genetic data from archaeological material, also known as ancient DNA. This has resulted in an explosion of work exploring past changes in population size, structure, continuity and movement. However, as genetic processes are highly stochastic, patterns of genetic variation only indirectly reflect demographic histories. As a result, past demographic processes need to be reconstructed using an inferential approach. This usually involves comparing observed patterns of variation with model expectations from theoretical population genetics. A large number of approaches have been developed based on different population genetic models that each come with assumptions about the data and underlying demography. In this article I review some of the key models and assumptions underlying the most commonly used approaches for past demographic inference and their consequences for our ability to link the inferred demographic processes to the archaeological and climate records.

In this effort we propose a data-driven learning framework for reduced order modeling of fluid dynamics. Designing accurate and efficient reduced order models for nonlinear fluid dynamic problems is challenging for many practical engineering applications. Classical projection-based model reduction methods generate reduced systems by projecting full-order differential operators into low-dimensional subspaces. However, these techniques usually lead to severe instabilities in the presence of highly nonlinear dynamics, which dramatically deteriorates the accuracy of the reduced-order models. In contrast, our new framework exploits linear multistep networks, based on implicit Adams-Moulton schemes, to construct the reduced system. The advantage is that the method optimally approximates the full order model in the low-dimensional space with a given supervised learning task. Moreover, our approach is non-intrusive, such that it can be applied to other complex nonlinear dynamical systems with sophisticated legacy codes. We demonstrate the performance of our method through the numerical simulation of a two-dimensional flow past a circular cylinder with Reynolds number Re = 100. The results reveal that the new data-driven model is significantly more accurate than standard projection-based approaches

One of the frequently used classes of the sparse reconstruction algorithms is based on the iterative shrinkage/thresholding procedure, where the thresholding parameter controls a trade-off between the algorithm accuracy and the execution time. In order to avoid this trade-off, we propose using a fast intersection of confidence interval method in order to adaptively control the threshold value through the reconstruction algorithm iterations. We have upgraded the two-step iterative shrinkage thresholding algorithm with a such procedure, improving its performance. The proposed algorithm, denoted as the FICI-TwIST, along with a few selected state-of-the-art sparse reconstruction algorithms have been tested on the classical problem of image recovery by emphasizing the image sparsity in the discrete cosine and the discrete wavelet domain. Furthermore, we have derived a single wavelet transformation matrix which avoids wrapping effects achieving significantly faster execution times when compared to more traditional function based transformation. The obtained results indicate competitive performance of the proposed algorithm, even in cases where all algorithm parameters have been individually fine-tuned for best performances.

Groundwater modeling is a useful tool for assessing sustainability in water resources planning. However, groundwater models are difficult to construct in regions with limited data availability. We illustrated how remote sensing data can be used leverage limited in situ data to build and calibrate a regional groundwater model in the Goulbi Maradi alluvial aquifer in Southern Niger in Western Africa. We used data from the NASA Gravity Recovery and Climate Experiment (GRACE) satellite mission to estimate recharge rates, the primary source of water to the aquifer. Additionally, we incorporated groundwater storage changes obtained from GRACE data from 2009 to 2021 to establish an overall water budget from which we could back-calculate groundwater withdrawals from pumping in the region. This approach allowed us to calibrate the model and then convert it to a predictive tool to analyze the impact of various assumptions about future recharge and groundwater extraction patterns associated with the development of groundwater infrastruction in the region. The results indicate that the Goulbi Maradi alluvial aquifer is sustainable, even an increase of groundwater extraction up to 28%.

Purposes: To provide abdominal contrast-enhanced MR image synthesis, we developed an image gradient regularized multi-modal multi-discrimination sparse-attention fusion generative adversarial network (GRMM-GAN) to avoid repeated contrast injections to patients and facilitate adaptive monitoring. Methods: With IRB approval, 165 abdominal MR studies from 61 liver cancer patients were retrospectively solicited from our institutional database. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast-enhanced (T1ce) images. The GRMM-GAN synthesis pipeline consists of a sparse attention fusion network, an image gradient regularizer (GR), and a generative adversarial network with multi-discrimination. The studies were randomly divided into 115 for training, 20 for validation, and 30 for testing. The two pre-contrast MR modalities, T2 and T1pre images, were adopted as inputs in the training phase. The T1ce image at the portal venous phase was used as an output. The synthesized T1ce images were compared with the ground truth T1ce images. The evaluation metrics include peak signal-to-noise ratio (PSNR), structural-similarity-index (SSIM), and mean-squared-error (MSE). A Turing test and experts’ contours evaluated the image synthesis quality. Results: The proposed GRMM-GAN model achieved a PSNR of 28.56, an SSIM of 0.869, and an MSE of 83.27. The proposed model showed statistically significant improvements in all metrics tested with p-values <0.05 over the state-of-the-art model comparisons. The average Turing test score was 52.33%, close to random guessing, supporting the model's effectiveness for clinical application. In the tumor-specific region analysis, the average tumor contrast-to-noise ratio (CNR) of the synthesized MR images was not statistically significant from the real MR images. The average DICE from real vs. synthetic images was 0.90, compared to the inter-operator DICE of 0.91. Conclusion: We demonstrated the function of a novel multi-modal MR image synthesis neural network, GRMM-GAN, for T1ce MR synthesis based on pre-contrast T1 and T2 MR images. GRMM-GAN shows promise for avoiding repeated contrast injections during radiation therapy treatment.

Deep Neural Network (DNN) inference demands substantial computing power, resulting in significant energy consumption. A large number of negative output activations in convolution layers are rendered zero due to the invocation of the ReLU activation function. This results in a substantial number of unnecessary computations that consume significant amounts of energy. This paper presents ECHO: Energy-efficient Computation Harnessing Onilne Arithmetic - A MSDF-based accelerator for DNN inference, designed for computation pruning, utilizing an unconventional arithmetic paradigm known as online/ most-significant digit first (MSDF) arithmetic which performs computations in a digit-serial manner. The MSDF digital serial computation of online arithmetic enables overlapped computation of successive operations leading to substantial performance improvements. The online arithmetic, coupled with a negative output detection scheme, facilitates early and precise recognition of negative outputs. This, in turn, allows for the timely termination of unnecessary computations, resulting in a reduction of energy consumption. The implemented design has been realized on the Xilinx Virtex-7 VU3P FPGA and subjected to a comprehensive evaluation through a rigorous comparative analysis involving widely used performance metrics. Experimental results demonstrate promising power and throughput improvements compared to contemporary methods. In particular, the proposed design achieved an average improvement in power consumption of up to 81%, 82.9%, and 40.6% for VGG-16, ResNet-18, and ResNet-50 workloads compared to the conventional bit-serial design, respectively. Furthermore, significant average speedups of 2.39×, 2.6×, and 2.42 were observed when comparing the proposed design to conventional bit-serial designs for VGG-16, ResNet-18, and ResNet-50 models respectively.

Equipping autonomous agents for dynamic interaction and navigation is a significant challenge in intelligent transportation systems. This study aims to address this by implementing a brain-inspired model for decision-making in autonomous vehicles. We employ active inference, a Bayesian approach that models decision-making processes similar to the human brain, focusing on the agent's preferences and the principle of free energy. This approach is combined with imitation learning to enhance the vehicle's ability to adapt to new observations and make human-like decisions. The research involved developing a multi-modal self-awareness architecture for autonomous driving systems and testing this model in driving scenarios, including abnormal observations. The results demonstrated the model's effectiveness in enabling the vehicle to make safe decisions, particularly in unobserved or dynamic environments. The study concludes that the integration of active inference with imitation learning significantly improves the performance of autonomous vehicles, offering a promising direction for future developments in intelligent transportation systems.

For Convolutional Neural Network (CNN), Depthwise Separable CNN (DSCNN) is a preferred architecture for Application Specific Integrated Circuit (ASIC) implementation on edge devices. It can benefit from a multi-mode approximate multiplier proposed in this work. The proposed approximate multiplier uses two 4-bit multiplication operations to implement a 12-bit multiplication operation by reusing the same multiplier array. With this approximate multiplier, sequential multiplication operations are pipelined in a modified DSCNN to fully utilize the PE array in the convolutional layer. This Approximate (A-DSCNN) was implemented on TSMC 40-nm CMOS process with a supply voltage of 0.9 V. At the clock frequency of 200 MHz, the design achieves 4.78 GOPs/mW while occupying 1.24 mm x 1.24 mm silicon area. Compared to conventional DSCNN implemented in a similar process node, the chip area and power consumption were reduced by 53% and 25%, while the throughput was improved by 17%.

The giant challenge breeding flood-irrigated rice is to identify superior genotypes that present high-yielding with specific grain qualities, resistance to abiotic and biotic stresses, excellent adaptation to the target environment. Thus, the objectives of this study were to propose a bayesian multi-trait model, estimate genetic parameters, and select flood-irrigated rice genotypes with better genetic potentials in different evaluation environments. For this, twenty-five rice genotypes belonging to the flood-irrigated rice improvement program were evaluated. The grain yields, grain length, width and thickness, grain length, and grain width and weight of 100 grains in the agricultural year 2016/2017. The experimental design used in all experiments was a randomized block design with three replications. The Monte Carlo Markov Chain algorithm estimated genetic parameters and genetic values. The grain thickness trait was considered highly heritable, with a credibility interval ranging from: h^2: 0.9480; 0.9440; 0.8610, in environments 1, 2, and 3, respectively. The grain yields showed a low correlation estimate between grain thickness and 100-grain weight, in all environments, with a credibility interval ranging from (ρ= 0.5477; 0.5762; 0.5618 and 0.5973; 0.5247; 0.5632, grain thickness and 100-grain weight, in environments 1, 2, and 3, respectively). The Bayesian multi-trait model proved to be an adequate strategy for the genetic improvement of flood-irrigated. Genotypes 2 and 15 had similar potential in the three environments, they should be selected as high-performance multi-trait genotypes for the genetic breeding of flood-irrigated rice in the program.

Climate change impacts and adaptations is subject to ongoing issues that attract the attention of many researchers. Insight into the wind power potential in an area and its probable variation due to climate change impacts can provide useful information for energy policymakers and strategists for sustainable development and management of the energy. In this study, spatial variation of wind power density at the turbine hub-height and its variability under future climatic scenarios are taken under consideration. An ANFIS based post-processing technique was employed to match the power outputs of the regional climate model with those obtained from the reference data. The near-surface wind data obtained from a regional climate model are employed to investigate climate change impacts on the wind power resources in the Caspian Sea. Subsequent to converting near-surface wind speed to turbine hub-height speed and computation of wind power density, the results have been investigated to reveal mean annual power, seasonal, and monthly variability for a 20-year period in the present (1981-2000) and in the future (2081-2100). The results of this study revealed that climate change does not affect the wind climate over the study area, remarkably. However, a small decrease was projected for future simulation revealing a slightly decrease in mean annual wind power in the future compared to historical simulations. Moreover, the results demonstrated strong variation in wind power in terms of temporal and spatial distribution when winter and summer have the highest values of power. The findings of this study indicated that the middle and northern parts of the Caspian Sea are placed with the highest values of wind power. However, the results of the post-processing technique using adaptive neuro-fuzzy inference system (ANFIS) model showed that the real potential of the wind power in the area is lower than those of projected from the regional climate model.

This paper presents a novel method of restoring the electron beam (EB) measurements that are degraded by linear motion blur. This is based on a Fuzzy Inference System (FIS) and Wiener inverse filter, together providing autonomy, reliability, flexibility and real-time execution. This system is capable of restoring highly degraded signals without requiring the exact knowledge of EB probe size. The FIS is formed of three inputs, eight fuzzy rules and one output. The FIS is responsible to monitor the restoration results, grade their validity and choose the one that yields to a better grade. These grades are produced autonomously by analyzing results of Wiener inverse filter. To benchmark the performance of the system, ground truth signals obtained using an 18 um wire probe are compared with the restorations. Main aims are therefore a) Provide unsupervised deblurring for device independent EB measurement; b) Improve the reliability of the process; c) Apply deblurring without knowing the probe size. These, further facilitates the deployment and manufacturing of EB probes and probe independent and accurate EB characterization. It also makes restoration of previously collected EB measurements easier, where the probe sizes are not known or recorded.

Input noise causes inescapable bias to the weight vectors of the adaptive filters during the adaptation processes. Moreover, the impulse noise at the output of the unknown systems can prevent bias compensation from converging. This paper presents a robust bias compensation method for a sparse normalized quasi-Newton least-mean (BC-SNQNLM) adaptive filtering algorithm to address this issue. We have mathematically derived the biased-compensation terms in an impulse noisy environment. Inspired by the convex combination of adaptive filters' step sizes, we propose a novel variable-mixing-norm method to accelerate the convergence for our BC-SNQNLM algorithm, which is referred to as BC-SNQNLM-VMN. Simulation results confirm that the proposed method significantly outperforms other comparative works regarding normalized mean-squared deviation (NMSD) in the steady state.

Genomics involving tens of thousands of genes is a complex system determining phenotype. An interesting and vital issue is that how to integrate highly sparse genetic genomics data with a mass of minor effects into prediction model for improving prediction power. We find that deep learning method can work well to extract features by transforming highly sparse dichotomous data to lower dimensional continuous data in a non-linear way. This idea may provide benefits in risk prediction based on genome-wide data associated e.g. integrating most of the information in the genotype data. Hence, we developed a multi-stage strategy to extract information from highly sparse binary genotype data and applied it for risk prediction. Specifically, we first reduced the number of biomarkers via a univariable regression model to a moderate size. Then a trainable auto-encoder was used to extract compact representations from the reduced data. Next, we performed a LASSO problem process over a grid of tuning parameter values to select the optimal combination of extracted features. Finally, we applied such feature combination to two prognostic models, and evaluated predictive effect of the models. The results of simulation studies and real data applying indicated that these highly compressed transformation features could better improve predictive performance and did not easily lead to over-fitting.

This paper presents a method to detect and classify the high impedance fault that occur in the medium voltage distribution network using discrete wavelet transform (DWT) and adaptive neuro-fuzzy inference system (ANFIS). The network is designed using Matlab software and various faults such as high impedance, symmetrical and unsymmetrical fault have been applied to study the effectiveness of the proposed ANFIS classifier method. This is achieved by training the ANFIS classifier using the features (standard deviation values) extracted from the three phase fault current signal by DWT technique for various cases of fault with different values of fault resistance in the system. The success and discrimination rate obtained for identifying and classifying the high impedance fault from the proffered method is 100% whereas the values are 66.7% and 85% respectively for conventional fuzzy based approach. The results indicate that the proposed method is more efficient to identify and discriminate the high impedance fault accurately from other power system faults in the system.

Often, when solving forward, inverse or data assimilation problems, only a part of the solution is needed. As a model, we consider the stationary diffusion problem. We demonstrate an algorithm that can compute only a part or a functional of the solution, without calculating the full inversion operator and the complete solution. It is a well-known fact about partial differential equations that the solution at each discretisation point depends on the solutions at all other discretisation points. Therefore, it is impossible to compute the solution only at one point, without calculating the solution at all other points. The standard numerical methods like a conjugate gradient or Gauss elimination compute the whole solution and/or the complete inverse operator. We suggest a method which can compute the solution of the given partial differential equation 1) at a point; 2) at few points; 3) on an interface; or a functional of the solution, without computing the solution at all points. The required storage cost and computational resources will be lower as in the standard approach. With this new method, we can speed up, for instance, computation of the innovation in filtering or the likelihood distribution, which measures the data misfit (mismatch). Further, we can speed up the solution of the regression, Bayesian inversion, data assimilation, and Kalman filter update problems. Applying additionally the hierarchical matrix approximation, we reduce the cubic computational cost to almost linear $\mathcal{O}(k^2n \log^2 n)$, where $k\ll n$ and $n$ is the number of degrees of freedom. Up to the hierarchical matrix approximation error, the computed solution is exact. One of the disadvantages of this method is the need to modify the existing deterministic solver.

Grading of rice grains has gain attentions due its requirement of quality assessment during import or export. Rice grain quality depends on milling operation, where rice hull is removed with a huller system followed by whitening operation. In such process, adjustment of rollers, control, and operation is important in terms of quality of milled rice. Especially, the basmati rice needed more quality assurance as it is not parboiled rice and exported globally with a high product value. In this present work, the basic problem of quality assessment in rice industry is addressed with digital image processing based technique. Machine vision and digital image processing provide an alternative with the automated, nondestructive, cost-effective, and fast approach as compared with traditional method which is done manually by human inspectors. A model of quality grade testing and identification is built based on morphological features using digital image processing and knowledge based adaptive neuro-fuzzy inference system (ANFIS). The qualities of rice kernels are determined with the help of shape descriptors and geometric features using the sample images of milled rice. The adopted technique has been tested on a sufficient number of training images of basmati rice grain. The proposed method gives a promising result in an evaluation of rice quality with 100% classification accuracy for broken and whole grain. The milling efficiency is also assessed using the ratio between head rice and broken rice percentage and it is 77.27% for the test sample. The overall results of the adopted methodology are promising in terms of classification accuracy and efficiency.

This paper develops Bayesian inference in reliability of a class of scale mixtures of log-normal failure time (SMLNFT) models with stochastic (or uncertain) constraint in their reliability measures. The class is comprehensive and includes existing failure time (FT) models (such as log-normal, log-Cauchy, and log-logistic FT models) as well as new models that are robust in terms of heavy-tailed FT observations. Since classical frequency approaches to reliability analysis based on the SMLNFT model with stochastic constraint are intractable, the Bayesian method is pursued utilizing a Markov chain Monte Carlo (MCMC) sampling based approach. This paper introduces a two-stage maximum entropy (MaxEnt) prior, which elicits a priori uncertain constraint and develops Bayesian hierarchical SMLNFT model by using the prior. The paper also proposes an MCMC method for Bayesian inference in the SMLNFT model reliability and calls attention to properties of the MaxEnt prior that are useful for method development. Finally, two data sets are used to illustrate how the proposed methodology works.

With end-to-end encryption for video streaming services becoming more popular, network administrators face new challenges in preserving network performance and user experience. Video ads may cause traffic congestion and poor Quality of Experience. Because of the natural variation in user interests and network situations, traditional algorithms for increasing QoE may face limitations. To solve this problem, we suggest a novel method that uses user facial emotion recognition to deduce QoE and study the effect of ads. We use open-access Face Emotion Recognition (FER) datasets and extract facial emotion information from actual observers to train machine learning models. Participants were requested to watch ad videos and provide feedback, which will be used for comparison, training, testing, and validation of our suggested technique. Our tests show that our approach beats the ITU-T P.1203 standard in terms of accuracy by 37.1%. Our method provides a hopeful answer to the problem of increasing user engagement and experience in video streaming services.

The accurate prediction of the solar Diffuse Fraction (DF), sometimes called the Diffuse Ratio, is an important topic for solar energy research. In the present study, the current state of Diffuse Irradiance research is discussed and then three robust, Machine Learning (ML) models, are examined using a large dataset (almost 8 years) of hourly readings from Almeria, Spain. The ML models used herein, are a hybrid Adaptive Network-based Fuzzy Inference System (ANFIS), a single Multi-Layer Perceptron (MLP) and a hybrid Multi-Layer Perceptron-Grey Wolf Optimizer (MLP-GWO). These models were evaluated for their predictive precision, using various Solar and Diffuse Fraction (DF) irradiance data, from Spain. The results were then evaluated using two frequently used evaluation criteria, the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE). The results showed that the MLP-GWO model, followed by the ANFIS model, provided a higher performance, in both the training and the testing procedures.

This paper presents a novel approach for individual design perception modeling using the YUKI-trained Fuzzy Inference System. The study focuses on understanding how individuals perceive design based on personality traits, particularly openness to experience. The proposed YUKI algorithm optimizes the FCM clustering algorithm, enhancing its ability to handle uncertain and imprecise data. The YUKI-trained FIS generates several Sugeno-type FIS models to predict design perception, to minimize the Root Mean Squared Error between the model prediction and the actual design perception of participants. The results demonstrate that the YUKI-trained FIS offers more accurate predictions compared to the traditional FCM-trained FIS, and the RMSE values for individual design perceptions fall within a satisfactory range of 0.84 to 1.32. The YUKI-trained FIS proves effective in clustering individuals based on their level of openness, providing insights into how personality traits influence design perception.

Several studies have analyzed human gait data obtained from inertial gyroscope and accelerometer sensors mounted on different parts of the body. In this article, we take a step further in gait analysis and provide a methodology for predicting the movements of the missing parts of the legs. In particular, we propose a method, called GaIn, to control non-invasive, robotic, prosthetic legs. GaIn can infer the movements of both missing shanks and feet for humans suffering from double trans-femoral amputation using biologically inspired recurrent neural networks. Predictions are performed for casual walking related activities such as walking, taking stairs, and running based on thigh movement. In our experimental tests, GaIn achieved a 4.55 degree prediction error for shank movements on average. However, a patient's intention to stand up and sit down cannot be inferred from thigh movements. In fact, intention causes thigh movements while the shanks and feet remain roughly still. The GaIn system can be triggered by thigh muscle activities measured with electromyography (EMG) sensors to make robotic prosthetic legs perform standing up and sitting down actions. The GaIn system has low prediction latency and is fast and computationally inexpensive to be deployed on mobile platforms and portable devices.