Size Of Set Research Articles

Self-supervised contrastive learning improves machine learning discrimination of full thickness macular holes from epiretinal membranes in retinal OCT scans.

There is a growing interest in using computer-assisted models for the detection of macular conditions using optical coherence tomography (OCT) data. As the quantity of clinical scan data of specific conditions is limited, these models are typically developed by fine-tuning a generalized network to classify specific macular conditions of interest. Full thickness macular holes (FTMH) present a condition requiring urgent surgical repair to prevent vision loss. Other works on automated FTMH classification have tended to use supervised ImageNet pre-trained networks with good results but leave room for improvement. In this paper, we develop a model for FTMH classification using OCT B-scans around the central foveal region to pre-train a naïve network using contrastive self-supervised learning. We found that self-supervised pre-trained networks outperform ImageNet pre-trained networks despite a small training set size (284 eyes total, 51 FTMH+ eyes, 3 B-scans from each eye). On three replicate data splits, 3D spatial contrast pre-training yields a model with an average F1-score of 1.0 on holdout data (50 eyes total, 10 FTMH+), compared to an average F1-score of 0.831 for FTMH detection by ImageNet pre-trained models. These results demonstrate that even limited data may be applied toward self-supervised pre-training to substantially improve performance for FTMH classification, indicating applicability toward other OCT-based problems.

Accuracy of vestibular schwannoma segmentation using deep learning models - a systematic review & meta-analysis.

Following 2020 PRISMA guidelines, a search across four databases was conducted. Inclusion criteria focused on articles using DL for VS MR image segmentation. The primary metric was the Dice score, supplemented by relative volume error (RVE) and average symmetric surface distance (ASSD). The search process identified 752 articles, leading to 11 studies for meta-analysis. A QUADAS- 2 analysis revealed varying biases. The overall Dice score for 56 models was 0.89 (CI: 0.88-0.90), with high heterogeneity (I2 = 95.9%). Subgroup analyses based on DL architecture, MRI inputs, and testing set sizes revealed performance variations. 2.5D DL networks demonstrated comparable efficacy to 3D networks. Imaging input analyses highlighted the superiority of contrast-enhanced T1-weighted imaging and mixed MRI inputs. This study fills a gap in systematic review in the automated segmentation of VS using DL techniques. Despite promising results, limitations include publication bias and high heterogeneity. Future research should focus on standardized designs, larger testing sets, and addressing biases for more reliable results. DL have promising efficacy in VS diagnosis, however further validation and standardization is needed. In conclusion, this meta-analysis provides comprehensive review into the current landscape of automated VS segmentation using DL. The high Dice score indicates promising agreement in segmentation, yet challenges like bias and heterogeneity must be addressed in the future research.

Affordance norms for 2825 concrete nouns.

Objects are commonly described based on their relations to other objects (e.g., associations, semantic similarity, etc.) or their physical features (e.g., birds have wings, feathers, etc.). However, objects can also be described in terms of their actionable properties (i.e., affordances), which reflect interactive relations between actors and objects. While several normed datasets have been developed to categorize various aspects of meaning (e.g., semantic features, cue-target associations, etc.), to date, norms for affordances have not been generated. We address this limitation by developing a set of affordance norms for 2825 concrete nouns. Using an open-response format, we computed affordance strength (AFS; i.e., the probability of an item eliciting a particular action response), affordance proportion (AFP; i.e., the proportion of participants who provided a specific action response), and affordance set size (AFSS; i.e., the total number of unique action responses) for each item. Because our stimuli overlapped with Pexman et al.'s, Behavior Research Methods, 51, 453-466, (2019) body-object interaction norms (BOI), we tested whether AFS, AFP, and AFSS were related to BOI, as objects with more perceived action properties may be viewed as being more interactive. Additionally, we tested the relationship between AFS and AFP and two separate measures of relatedness: cosine similarity (Buchanan et al., Behavior Research Methods, 51, 1849-1863, 2019a, Behavior Research Methods, 51, 1878-1888, 2019b) and forward associative strength (Nelson et al., Behavior Research Methods, Instruments, & Computers, 36(3), 402-407, 2004). All analyses, however, revealed weak relationships between affordance measures and existing semantic norms, suggesting that affordance properties reflect a separate construct.

Learning the structure of multivariate regression chain graphs by testing complete separators in prime blocks

This paper introduces an algorithm to construct a bidirectional causal graph using an augmented graph. The algorithm decomposes the augmented graph, significantly reducing the size of the variable set required for conditional independence testing. Simultaneously, it preserves the fundamental structure of the augmented graph after decomposition, saving time and cost in constructing a global skeleton graph. Through experiments on discrete and continuous datasets, the algorithm demonstrates a clear advantage in runtime compared to traditional methods. In large-scale sparse networks, the training time is only about one-tenth of traditional methods. Additionally, the algorithm shows improvement in terms of construction error. Since the input to the algorithm is an augmented graph, this paper also discusses the impact on construction error when using both real and generated augmented graphs as input. Furthermore, the concept of markov blanket is extended to multivariate regression chain graphs, providing a method for rapidly constructing augmented graphs given certain prior knowledge.

Representing Matroids over the Reals is $\exists \mathbb R$-complete

A matroid $M$ is an ordered pair $(E,I)$, where $E$ is a finite set called the ground set and a collection $I\subset 2^{E}$ called the independent sets which satisfy the conditions: (i) $\emptyset \in I$, (ii) $I'\subset I \in I$ implies $I'\in I$, and (iii) $I_1,I_2 \in I$ and $|I_1| < |I_2|$ implies that there is an $e\in I_2$ such that $I_1\cup \{e\} \in I$. The rank $rank(M)$ of a matroid $M$ is the maximum size of an independent set. We say that a matroid $M=(E,I)$ is representable over the reals if there is a map $\varphi \colon E \rightarrow \mathbb{R}^{rank(M)}$ such that $I\in I$ if and only if $\varphi(I)$ forms a linearly independent set. We study the problem of matroid realizability over the reals. Given a matroid $M$, we ask whether there is a set of points in the Euclidean space representing $M$. We show that matroid realizability is $\exists \mathbb R$-complete, already for matroids of rank 3. The complexity class $\exists \mathbb R$ can be defined as the family of algorithmic problems that is polynomial-time is equivalent to determining if a multivariate polynomial with integers coefficients has a real root. Our methods are similar to previous methods from the literature. Yet, the result itself was never pointed out and there is no proof readily available in the language of computer science.

Efficient First-Order Algorithms for Large-Scale, Non-Smooth Maximum Entropy Models with Application to Wildfire Science.

Maximum entropy (MaxEnt) models are a class of statistical models that use the maximum entropy principle to estimate probability distributions from data. Due to the size of modern data sets, MaxEnt models need efficient optimization algorithms to scale well for big data applications. State-of-the-art algorithms for MaxEnt models, however, were not originally designed to handle big data sets; these algorithms either rely on technical devices that may yield unreliable numerical results, scale poorly, or require smoothness assumptions that many practical MaxEnt models lack. In this paper, we present novel optimization algorithms that overcome the shortcomings of state-of-the-art algorithms for training large-scale, non-smooth MaxEnt models. Our proposed first-order algorithms leverage the Kullback-Leibler divergence to train large-scale and non-smooth MaxEnt models efficiently. For MaxEnt models with discrete probability distribution of n elements built from samples, each containing m features, the stepsize parameter estimation and iterations in our algorithms scale on the order of O(mn) operations and can be trivially parallelized. Moreover, the strong ℓ1 convexity of the Kullback-Leibler divergence allows for larger stepsize parameters, thereby speeding up the convergence rate of our algorithms. To illustrate the efficiency of our novel algorithms, we consider the problem of estimating probabilities of fire occurrences as a function of ecological features in the Western US MTBS-Interagency wildfire data set. Our numerical results show that our algorithms outperform the state of the art by one order of magnitude and yield results that agree with physical models of wildfire occurrence and previous statistical analyses of wildfire drivers.

On the sample complexity of quantum Boltzmann machine learning

Quantum Boltzmann machines (QBMs) are machine-learning models for both classical and quantum data. We give an operational definition of QBM learning in terms of the difference in expectation values between the model and target, taking into account the polynomial size of the data set. By using the relative entropy as a loss function, this problem can be solved without encountering barren plateaus. We prove that a solution can be obtained with stochastic gradient descent using at most a polynomial number of Gibbs states. We also prove that pre-training on a subset of the QBM parameters can only lower the sample complexity bounds. In particular, we give pre-training strategies based on mean-field, Gaussian Fermionic, and geometrically local Hamiltonians. We verify these models and our theoretical findings numerically on a quantum and a classical data set. Our results establish that QBMs are promising machine learning models.

Full wave function cloning for improving convergence of the multiconfigurational Ehrenfest method: Tests in the zero-temperature spin-boson model regime.

In this paper, we report a new algorithm for creating an adaptive basis set in the Multiconfigurational Ehrenfest (MCE) method, which is termed Full Cloning (FC), and test it together with the existing Multiple Cloning (MC) using the spin-boson model at zero-temperature as a benchmark. The zero-temperature spin-boson regime is a common hurdle in the development of methods that seek to model quantum dynamics. Two versions of MCE exist. We demonstrate that MC is vital for the convergence of MCE version 2 (MCEv2). The first version (MCEv1) converges much better than MCEv2, but FC improves its convergence in a few cases where it is hard to converge it with the help of a reasonably small size of the basis set.

On the maximum field of linearity of linear sets

AbstractLet denote an ‐dimensional ‐vector space. For an ‐dimensional ‐subspace of , assume that for each nonzero vector . If , then we prove the existence of an integer such that the set of one‐dimensional ‐subspaces generated by nonzero vectors of is the same as the set of one‐dimensional ‐subspaces generated by nonzero vectors of . If we view as a point set of , it means that and determine the same set of directions. We prove a stronger statement when . In terms of linear sets, it means that an ‐linear set of has maximum field of linearity only if it has a point of weight one. We also present some consequences regarding the size of a linear set.

General weighted extropy of minimum and maximum ranked set sampling with unequal samples

. In industrial, environmental, and ecological investigations, ranked set sampling is a sample method that enables the experimenter to use the whole range of population values. The ranked set sampling process can be modified in two extremely helpful ways: maximum ranked set sampling with unequal samples and minimum ranked set sampling with unequal samples. They permit an increase in set size without too many ranking errors being introduced. In this article, we are defining general weighted extropy (GWJ) of minimum and maximum ranked set samples when samples are of unequal size (minRSSU and maxRSSU, respectively). Stochastic comparison and monotone properties have been studied under different situations. Additionally, we compare the extropy of these two sampling data with that of ranked set sampling data and simple random sampling data. Bounds of GWJ of minRSSU and maxRSSU have been obtained. Finally, we investigate the weighted discrimination information between simple random sampling, ranked set sampling, and minimum and maximum ranked set sampling with unequal sample sizes. Some results for equality of GWJ of minRSSU and maxRSSU under symmetric assumption are also obtained.

Balancing the efforts of chart review and gains in PRS prediction accuracy: An empirical study

ObjectivePhenotypic misclassification in genetic association analyses can impact the accuracy of PRS-based prediction models. The bias reduction method proposed by Tong et al. (2019) has demonstrated its efficacy in reducing the effects of bias on the estimation of association parameters between genotype and phenotype while minimizing variance by employing chart reviews on a subset of the data for validating phenotypes, however its improvement of subsequent PRS prediction accuracy remains unclear. Our study aims to fill this gap by assessing the performance of simulated PRS models and estimating the optimal number of chart reviews needed for validation. MethodsTo comprehensively assess the efficacy of the bias reduction method proposed by Tong et al. in enhancing the accuracy of PRS-based prediction models, we simulated each phenotype under different correlation structures (an independent model, a weakly correlated model, a strongly correlated model) and introduced error-prone phenotypes using two distinct error mechanisms (differential and non-differential phenotyping errors). To facilitate this, we used genotype and phenotype data from 12 case-control datasets in the Alzheimer’s Disease Genetics Consortium (ADGC) to produce simulated phenotypes. The evaluation included analyses across various misclassification rates of original phenotypes as well as quantities of validation set. Additionally, we determined the median threshold, identifying the minimal validation size required for a meaningful improvement in the accuracy of PRS-based predictions across a broad spectrum. ResultsThis simulation study demonstrated that incorporating chart review does not universally guarantee enhanced performance of PRS-based prediction models. Specifically, in scenarios with minimal misclassification rates and limited validation sizes, PRS models utilizing debiased regression coefficients demonstrated inferior predictive capabilities compared to models using error-prone phenotypes. Put differently, the effectiveness of the bias reduction method is contingent upon the misclassification rates of phenotypes and the size of the validation set employed during chart reviews. Notably, when dealing with datasets featuring higher misclassification rates, the advantages of utilizing this bias reduction method become more evident, requiring a smaller validation set to achieve better performance. ConclusionThis study highlights the importance of choosing an appropriate validation set size to balance between the efforts of chart review and the gain in PRS prediction accuracy. Consequently, our study establishes a valuable guidance for validation planning, across a diverse array of sensitivity and specificity combinations.

The Structure of Large SUM-Free Sets in 𝔽n p

ABSTRACT A set $A\subset \mathbb{F}_p^n$ is sum-free if A + A does not intersect A. If $p\equiv 2 \;\mathrm{mod}\; 3$, the maximal size of a sum-free set in $\mathbb{F}_p^n$ is known to be $(p^n+p^{n-1})/3$. We show that if a sum-free set $A\subset \mathbb{F}_p^n$ has size at least $p^n/3-p^{n-1}/6+p^{n-2}$, then there exists subspace $V\lt\mathbb{F}_p^n$ of codimension 1 such that A is contained in $(p+1)/3$ cosets of V. For p = 5 specifically, we show the stronger result that every sum-free set of size larger than $1.2\cdot 5^{n-1}$ has this property, thus improving on a recent theorem of Lev.

Exploring the Interplay of Dataset Size and Imbalance on CNN Performance in Healthcare: Using X-rays to Identify COVID-19 Patients.

Convolutional Neural Network (CNN) systems in healthcare are influenced by unbalanced datasets and varying sizes. This article delves into the impact of dataset size, class imbalance, and their interplay on CNN systems, focusing on the size of the training set versus imbalance-a unique perspective compared to the prevailing literature. Furthermore, it addresses scenarios with more than two classification groups, often overlooked but prevalent in practical settings. Initially, a CNN was developed to classify lung diseases using X-ray images, distinguishing between healthy individuals and COVID-19 patients. Later, the model was expanded to include pneumonia patients. To evaluate performance, numerous experiments were conducted with varied data sizes and imbalance ratios for both binary and ternary classifications, measuring various indices to validate the model's efficacy. The study revealed that increasing dataset size positively impacts CNN performance, but this improvement saturates beyond a certain size. A novel finding is that the data balance ratio influences performance more significantly than dataset size. The behavior of three-class classification mirrored that of binary classification, underscoring the importance of balanced datasets for accurate classification. This study emphasizes the fact that achieving balanced representation in datasets is crucial for optimal CNN performance in healthcare, challenging the conventional focus on dataset size. Balanced datasets improve classification accuracy, both in two-class and three-class scenarios, highlighting the need for data-balancing techniques to improve model reliability and effectiveness. Our study is motivated by a scenario with 100 patient samples, offering two options: a balanced dataset with 200 samples and an unbalanced dataset with 500 samples (400 healthy individuals). We aim to provide insights into the optimal choice based on the interplay between dataset size and imbalance, enriching the discourse for stakeholders interested in achieving optimal model performance. Recognizing a single model's generalizability limitations, we assert that further studies on diverse datasets are needed.

Analytic Gradients for Density Fitting MP2 Using Natural Auxiliary Functions.

The natural auxiliary function (NAF) approach is an approximation to decrease the size of the auxiliary basis set required for quantum chemical calculations utilizing the density fitting technique. It has been proven efficient to speed up various correlation models, such as second-order Møller-Plesset (MP2) theory and coupled-cluster methods. Here, for the first time, we discuss the theory of analytic derivatives for correlation methods employing the NAF approximation on the example of MP2. A detailed algorithm for the gradient calculation with the NAF approximation is proposed in the framework of the method of Lagrange multipliers. To assess the effect of the NAF approximation on gradients and optimized geometric parameters, a series of benchmark calculations on small and medium-sized systems was performed. Our results demonstrate that, for MP2, sufficiently accurate gradients and geometries can be achieved with a moderate time reduction of 15-20% for both small and medium-sized molecules.

Relativistic Coupled Cluster with Completely Renormalized and Perturbative Triples Corrections.

We have implemented noniterative triples corrections to the energy from coupled-cluster with single and double excitations (CCSD) within the 1-electron exact two-component (1eX2C) relativistic framework. The effectiveness of both the CCSD(T) and the completely renormalized (CR) CC(2,3) approaches are demonstrated by performing all-electron computations of the potential energy curves and spectroscopic constants of copper, silver, and gold dimers in their ground electronic states. Spin-orbit coupling effects captured via the 1eX2C framework are shown to be crucial for recovering the correct shape of the potential energy curves, and the correlation effects due to triples in these systems change the dissociation energies by about 0.1-0.2 eV or about 4-7%. We also demonstrate that relativistic effects and basis set size and contraction scheme are significantly more important in Au2 than in Ag2 or Cu2.

Anomaly detection combining bidirectional gated recurrent unit and autoencoder in the context of e-commerce

E-commerce platforms store a large amount of user personal information, transaction data, and financial information, which have extremely high value for hackers and criminals. Therefore, protecting the security of e-commerce platforms is particularly important, and intrusion detection is a technical means used to discover and respond to possible security threats and attacks. But with the development of Internet technology, there are more and more types of intrusion attacks and more sophisticated means. Traditional intrusion detection systems are difficult to cope with. This study proposes an anomaly detection model based on bidirectional gated loop units and autoencoders. The model learns HTTP text data, trains the model, and uses bidirectional gated loop units to convert text sequences from characters to numbers. The experimental results show that when the training set size is 1000, the false alarm rates of Analytic Hierarchy Process, Support Vector Machine, Long Short Term Recurrent Memory Network, and Improved end-to-end algorithm models are 0.30, 0.27, 0.23, and 0.10, respectively. The loss function values are 0.35, 0.28, 0.17, and 0.13, respectively. The F1 values are 0.78, 0.88, 0.91, and 0.99, and the accuracy rates are 0.88, 0.91, 0.95, and 0.99, respectively. The research results indicate that the proposed method model has excellent performance.

Multi-trait multi-environment genomic prediction of preliminary yield trial in pulse crop.

Phenotypic selection of complex traits such as seed yield and protein in the preliminary yield trial (PYT) is often constrained by limited seed availability, resulting in trials with few environments and minimal to no replications. Multi-trait multi-environment enabled genomic prediction (MTME-GP) offers a valuable alternative to predict missing phenotypes of selection candidates for multiple traits and diverse environments. In this study, we assessed the efficiency of MTME-GP for improving seed protein and seed yield in field pea, the top two breeding targets but highly antagonistic traits in pulse crop. We utilized a set of 300 selection candidates in the PYT that virtually represented all possible families of the North Dakota State University field pea breeding program. Selection candidates were evaluated in three diverse, contrasting environments, as indicated by a range of heritability. Using whole- and split-environment cross validation schemes, MTME-GP had higher predictive ability than a standard additive G-BLUP model. Integrating a range of overlapping genotypes in between environments showed improvement on the predictive ability of the MTME-GP model but tends to plateau at 50%-80% training set size. Regardless of the cross-validation scheme, accuracy was among the lowest in stressed environments, presumably due to low heritability for seed protein and yield. This study provided insights into the potential of MTME-GP in a public pulse crop breeding program. The MTME-GP framework can be further improved with more testing environments and integration of additional orthogonal information in the early stages of the breeding pipeline.

A fine‐tuning workflow for automatic first‐break picking with deep learning

AbstractFirst‐break picking is an essential step in seismic data processing. For reliable results, first arrivals should be picked by an expert. This is a time‐consuming procedure and subjective to a certain degree, leading to different results for different operators. In this study, we have used a U‐Net architecture with residual blocks to perform automatic first‐break picking based on deep learning. Focusing on the effects of weight initialization on first‐break picking, we conduct this research by using the weights of a pre‐trained network that is used for object detection on the ImageNet dataset. The efficiency of the proposed method is tested on two real datasets. For both datasets, we pick manually the first breaks for less than 10 of the seismic shots. The pre‐trained network is fine‐tuned on the picked shots, and the rest of the shots are automatically picked by the neural network. It is shown that this strategy allows to reduce the size of the training set, requiring fine‐tuning with only a few picked shots per survey. Using random weights and more training epochs can lead to a lower training loss, but such a strategy leads to overfitting as the test error is higher than the one of the pre‐trained network. We also assess the possibility of using a general dataset by training a network with data from three different projects that are acquired with different equipment and at different locations. This study shows that if the general dataset is created carefully it can lead to more accurate first‐break picking; otherwise, the general dataset can decrease the accuracy. Focusing on near‐surface geophysics, we perform traveltime tomography and compare the inverted velocity models based on different first‐break picking methodologies. The results of the inversion show that the first breaks obtained by the pre‐trained network lead to a velocity model that is closer to the one obtained from the inversion of expert‐picked first breaks.

Electric Field Gradient Calculations for Ice VIII and IX Using Polarizable Embedding: A Comparative Study on Classical Computers and Quantum Simulators.

We test the performance of the polarizable embedding variational quantum eigensolver self-consistent field (PE-VQE-SCF) model for computing electric field gradients with comparisons to conventional complete active space self-consistent-field (CASSCF) calculations and experimental results. We compute quadrupole coupling constants for ice VIII and ice IX. We find close agreement of the quantum-computing PE-VQE-SCF results with the results from the classical PE-CASSCF calculations and with experiment. Furthermore, we observe that the inclusion of the environment is crucial for obtaining results that match the experimental data. The calculations for ice VIII are within the experimental uncertainty for both CASSCF and VQE-SCF for oxygen and lie close to the experimental value for ice IX as well. With the VQE-SCF, which is based on an adaptive derivative-assembled problem-tailored (ADAPT) ansatz, we find that the inclusion of the environment and the size of the different basis sets do not directly affect the gate counts. However, by including an explicit environment, the wavefunction and therefore the optimization problem become more complicated, which usually results in the need to include more operators from the operator pool, thereby increasing the depth of the circuit.

Deep learning-based automated liver contouring using a small sample of radiotherapy planning computed tomography images

IntroductionNo study has yet investigated the minimum amount of data required for deep learning-based liver contouring. Therefore, this study aimed to investigate the feasibility of automated liver contouring using limited data. MethodsRadiotherapy planning Computed tomography (CT) images were subjected to various preprocessing methods, such as denoising and windowing. Segmentation was conducted using the modified Attention U-Net and Residual U-Net networks. Two different modified networks were trained separately for different training sizes. For each architecture, the model trained with the training set size that achieved the highest dice similarity coefficient (DSC) score was selected for further evaluation. Two unseen external datasets with different distributions from the training set were also used to examine the generalizability of the proposed method. ResultsThe modified Residual U-Net and Attention U-Net networks achieved average DSCs of 97.62% and 96.48%, respectively, on the test set, using 62 training cases. The average Hausdorff distances (AHDs) for the modified Residual U-Net and Attention U-Net networks were 0.57 mm and 0.71 mm, respectively. Also, the modified Residual U-Net and Attention U-Net networks were tested on two unseen external datasets, achieving DSCs of 95.35% and 95.82% for data from another center and 95.16% and 94.93% for the AbdomenCT-1K dataset, respectively. ConclusionThis study demonstrates that deep learning models can accurately segment livers using a small training set. The method, utilizing simple preprocessing and modified network architectures, shows strong performance on unseen datasets, indicating its generalizability. Implications for practiceThis promising result suggests its potential for automated liver contouring in radiotherapy planning.