Implicit Model Research Articles

Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images.

Segmentation masks of pathological areas are useful in many medical applications, such as brain tumour and stroke management. Moreover, healthy counterfactuals of diseased images can be used to enhance radiologists' training files and to improve the interpretability of segmentation models. In this work, we present a weakly supervised method to generate a healthy version of a diseased image and then use it to obtain a pixel-wise anomaly map. To do so, we start by considering a saliency map that approximately covers the pathological areas, obtained with ACAT. Then, we propose a technique that allows to perform targeted modifications to these regions, while preserving the rest of the image. In particular, we employ a diffusion model trained on healthy samples and combine Denoising Diffusion Probabilistic Model (DDPM) and Denoising Diffusion Implicit Model (DDIM) at each step of the sampling process. DDPM is used to modify the areas affected by a lesion within the saliency map, while DDIM guarantees reconstruction of the normal anatomy outside of it. The two parts are also fused at each timestep, to guarantee the generation of a sample with a coherent appearance and a seamless transition between edited and unedited parts. We verify that when our method is applied to healthy samples, the input images are reconstructed without significant modifications. We compare our approach with alternative weakly supervised methods on the task of brain lesion segmentation, achieving the highest mean Dice and IoU scores among the models considered.

Toward Reliable Conformational Energies of Amino Acids and Dipeptides─The DipCONFS Benchmark and DipCONL Datasets.

Simulating peptides and proteins is becoming increasingly important, leading to a growing need for efficient computational methods. These are typically semiempirical quantum mechanical (SQM) methods, force fields (FFs), or machine-learned interatomic potentials (MLIPs), all of which require a large amount of accurate data for robust training and evaluation. To assess potential reference methods and complement the available data, we introduce two sets, DipCONFL and DipCONFS, which cover large parts of the conformational space of 17 amino acids and their 289 possible dipeptides in aqueous solution. The conformers were selected from the exhaustive PeptideCS dataset by Andris et al. [ J. Phys. Chem. B 2022, 126, 5949-5958]. The structures, originally generated with GFN2-xTB, were reoptimized using the accurate r2SCAN-3c density functional theory (DFT) composite method including the implicit CPCM water solvation model. The DipCONFS benchmark set contains 918 conformers and is one of the largest sets with highly accurate coupled cluster conformational energies so far. It is employed to evaluate various DFT and wave function theory (WFT) methods, especially regarding whether they are accurate enough to be used as reliable reference methods for larger datasets intended for training and testing more approximated SQM, FF, and MLIP methods. The results reveal that the originally provided BP86-D3(BJ)/DGauss-DZVP conformational energies are not sufficiently accurate. Among the DFT methods tested as an alternative reference level, the revDSD-PBEP86-D4 double hybrid performs best with a mean absolute error (MAD) of 0.2 kcal mol-1 compared with the PNO-LCCSD(T)-F12b reference. The very efficient r2SCAN-3c composite method also shows excellent results, with an MAD of 0.3 kcal mol-1, similar to the best-tested hybrid ωB97M-D4. With these findings, we compiled the large DipCONFL set, which includes over 29,000 realistic conformers in solution with reasonably accurate r2SCAN-3c reference conformational energies, gradients, and further properties potentially relevant for training MLIP methods. This set, also in comparison to DipCONFS, is used to assess the performance of various SQM, FF, and MLIP methods robustly and can complement training sets for those.

Identifying Artifacts from Large Library Docking.

While large library docking has discovered potent ligands for multiple targets, as the libraries have grown the hit lists can become dominated by rare artifacts that cheat our scoring functions. Here, we investigate rescoring top-ranked docked molecules with orthogonal methods to identify these artifacts, exploring implicit solvent models and absolute binding free energy perturbation as cross-filters. In retrospective studies, this approach deprioritized high-ranking nonbinders for nine targets while leaving true ligands relatively unaffected. We tested the method prospectively against hits from docking against AmpC β-lactamase. We prioritized 128 high-ranking molecules for synthesis and testing, a mixture of 39 molecules flagged as likely cheaters and 89 that were plausible inhibitors. None of the predicted cheating compounds inhibited AmpC detectably, while 57% of the 89 plausible compounds did so. As our libraries continue to grow, deprioritizing docking artifacts by rescoring with orthogonal methods may find wide use.

Thermal radiation, Soret and Dufour effects on MHD mixed convective Maxwell hybrid nanofluid flow under porous medium: a numerical study

PurposeScientists have been conducting trials to find ways to reduce fuel consumption and enhance heat transfer rates to make heating systems more efficient and cheaper. Adding solid nanoparticles to conventional liquids may greatly improve their thermal conductivity, according to the available evidence. This study aims to examine the influence of external magnetic flux on the flow of a mixed convective Maxwell hybrid non-Newtonian nanofluid over a linearly extending porous flat plate. The investigation considers the effects of thermal radiation, Dufour and Soret.Design/methodology/approachThe mathematical model is formulated based on the fundamental assumptions of mass, energy and momentum conservation. The implicit models are epitomized by a set of interconnected nonlinear partial differential equations, which include a suitable and comparable adjustment. The numerical solution to these equations is assessed for approximate convergence by the Runge−Kutta−Fehlberg method based on the shooting technique embedded with the MATLAB software.FindingsThe findings are presented through graphical representations, offering a visual exploration of the effects of various dynamic parameters on the flow field. These parameters encompass a wide range of factors, including radiation, thermal and Brownian diffusion parameters, Eckert, Lewis and Soret numbers, magnetic parameters, Maxwell fluid parameters, Darcy numbers, thermal and solutal buoyancy factors, Dufour and Prandtl numbers. Notably, the authors observed that nanoparticles with a spherical shape exerted a significant influence on the stream function, highlighting the importance of nanoparticle geometry in fluid dynamics. Furthermore, the analysis revealed that temperature profiles of nanomaterials were notably affected by their shape factor, while concentration profiles exhibited an opposite trend, providing valuable insights into the behavior of nanofluids in porous media.Originality/valueA distinctive aspect of the research lies in its novel exploration of the impact of external magnetic flux on the flow of a mixed convective Maxwell hybrid non-Newtonian nanofluid over a linearly extending porous flat plate. By considering variables such as solar radiation, external magnetic flux, thermal and Brownian diffusion parameters and nanoparticle shape factor, the authors ventured into uncharted territory within the realm of fluid dynamics. These variables, despite their significant relevance, have not been extensively studied in previous research, thus underscoring the originality and value of the authors’ contribution to the field.

Financial Socialization in Christian Premarital Counseling With Emerging Adults

Research on financial socialization among emerging adults has retrospectively examined what they have learned from their parents growing up. Building on this work, this article explores how these lessons are not static but can become reexamined through interpersonal relationships. It reports on findings from a qualitative study of four Christian premarital programs (two evangelical Protestants and two Catholics) and 70 interviews with participating couples and leaders of these and other programs. By contributing observational data on how the methods of socialization operate, it analyzes both explicit lessons on money and implicit models for how premarital counselors construct normative frameworks on how to interrogate emerging adult’s past and plan for their financial future. Specifically, it documents how financial advice was often relegated to supplemental materials due to leaders’ lack of confidence on money matters but also how the broader programming provided young couples with opportunities to identify and reflect on their family financial socialization. Implications for professionals interested in improving premarital and financial counseling are discussed.

Diffusion models for multidimensional seismic noise attenuation and superresolution

Seismic data quality proves pivotal to its interpretation, necessitating the reduction of noise and enhancement of resolution. Traditional and deep-learning-based solutions have achieved varying degrees of success on low-dimensional seismic data. We develop a deep generative solution for high-dimensional seismic data denoising and superresolution through the innovative application of denoising diffusion probabilistic models (DDPMs), which we refer to as MD Diffusion. MD Diffusion treats degraded seismic data as a conditional prior that guides the generative process, enhancing the capability to recover data from complex noise. By iteratively training an implicit probability model, we achieve a sampling speed 10 times faster than the original DDPM. Extensive training allows us to explicitly model complex seismic data distributions in synthetic data sets to transfer this knowledge to the process of recovering field data with unknown noise levels, thereby attenuating the noise and enhancing the resolution in an unsupervised manner. Quantitative metrics and qualitative results for 3D synthetic and field data demonstrate that MD Diffusion exhibits superior performance in high-dimensional seismic data denoising and superresolution compared with the UNet and seismic superresolution methods, especially in enhancing thin-layer structures and preserving fault features, and indicates the potential for application to higher-dimensional data.

Design framework based on implicit modeling for a compact heat exchanger with triply periodic minimal surface structures

Design framework based on implicit modeling for a compact heat exchanger with triply periodic minimal surface structures

DC-Link Utilization Enhanced Implicit Model Predictive Control for Dual Three-Phase PMSMs

DC-Link Utilization Enhanced Implicit Model Predictive Control for Dual Three-Phase PMSMs

Digital bead modeling for wire-arc directed energy deposition

Prediction of 2D cross-section and full 3D geometry for stacked weld beads is critical for the outcome of wire-arc directed energy deposition (DED) parts; however, most additive path planning software packages model beads as extrusions of a rectangle. Weld beads are not rectangular, and the resulting shape is dependent upon physics effects at the moment of deposition. Physics phenomena such as the geometry of the underlying surface, the heat input of the welding mode, and the direction of gravity contribute to bead shape. This paper presents a novel implicit modeling method that discretizes a 2D area or 3D volume of space into pixels or voxels and constructs fields based on these physics phenomena. The fields are combined using a weighting scheme trained on 3D scan measurements of welds and wire-arc DED prints. Pixels or voxels are added until the known amount of deposited volume has been achieved. Thereby, a strong conservation of mass principle is applied to the process. Utilizing machine learning techniques, the present model can be trained on a database of scans allowing for the representation of a wide variety of prints. Results show that this method can produce predictions with realistic bead morphology and sub-millimeter form error.

Identifying alternately poisoning attacks in federated learning online using trajectory anomaly detection method

Implicit poisoning in federated learning is a significant threat, with malicious nodes subtly altering gradient parameters each round, making detection difficult. This study investigates this problem, revealing that temporal analysis alone struggles to identify such covert attacks, which can bypass online methods like cosine similarity and clustering. Common detection methods rely on offline analysis, resulting in delayed responses. However, recalculating gradient updates reveals distinct characteristics of malicious clients. Based on this finding, we designed a privacy-preserving detection algorithm using trajectory anomaly detection. Singular values of matrices are used as features, and an improved Isolation Forest algorithm processes these to detect malicious behavior. Experiments on MNIST, FashionMNIST, and CIFAR-10 datasets show our method achieves 94.3% detection accuracy and a false positive rate below 1.2%, indicating its high accuracy and effectiveness in detecting implicit model poisoning attacks.

Molecular spectroscopy, solvent effect, and DFT studies of azithromycin solvate

Azithromycin ethanol solvate monohydrate [C38H72N2O120.5(C2H6O)H2O], abbreviated by AZM-MH-EtOH, was synthesized by slow evaporation method and investigated by powder X-ray diffraction, Raman and infrared (IR) spectroscopy combined with density functional theory (DFT) studies. Electronic and vibrational properties were properly investigated based on a theoretical study of solvation effects, using implicit solvation and solute electron density models. The electronic and vibrational studies were evaluated under aqueous, ethanolic, and vacuum conditions. The electronic structure calculations indicated that the AZM-MH-EtOH is chemically more stable in solvents compared to vacuum condition. Ultraviolet–visible (UV–vis) measurements confirmed the stability of the material in ethanolic medium, due to higher absorbance values compared to the aqueous medium. Vibrational changes were observed in the Raman and IR bands, which have connection with hydrogen bonds. The experimental vibration modes showed better accordance with the predicted modes’ values under solvation effects, but a slight divergence is noticed when we compared to vibration modes obtained in vacuum. Furthermore, the results have revealed a greater affinity profile of AZM-MH-EtOH for water and ethanol solvents compared to theoretical data under vacuum condition.

QM-CSA: A Novel Quantum Mechanics-Based Protocol for Evaluation of the Carcinogen-Scavenging Activity of Polyphenolic Compounds.

In this study, a novel quantum mechanics-based protocol for the evaluation of carcinogen-scavenging activity (QM-CSA) is developed. The QM-CSA protocol represents a universal and quantitative approach to evaluate and compare the activation-free energies for alkylation reactions between individual polyphenolic compounds and chemical carcinogens of the epoxy type at physiological conditions by applying two scales: the absolute scale allowing for the comparison with guanine and the relative scale allowing the comparison with glutathione as a reference compound. The devised quantum mechanical methodology was validated by comparing the activation-free energies calculated with 14 DFT functionals in conjunction with two implicit solvation models (SMD and CPCM) and the experimental activation-free energies for reactions between nine investigated chemical carcinogens and guanine. According to the obtained results, the best agreement with experimental data was achieved by applying DFT functionals M11-L and MN12-L in conjunction with the flexible 6-311++G(d,p) basis set and implicit solvation model SMD, and the obtained uncertainties were proven to be similar to the experimental ones. To demonstrate the applicability of the QM-CSA protocol, functionals M11-L, and MN12-L in conjunction with the SMD implicit solvation model were applied to calculate activation-free energies for the reactions of nine investigated chemical carcinogens of the epoxy type with three catechins, namely EGCG, EGC, and (+)-catechin. The order of CSA in this series of catechins in comparison to guanine and glutathione was determined as (+)-catechin > EGC > EGCG. The obtained results, for the first time, demonstrated the evaluation and comparison of CSA in a series of selected catechins with respect to glutathione and guanine. Moreover, the presented results provide valuable insights into the reaction mechanisms and configurations of the corresponding transition states. The novel QM-CSA protocol is also expected to expand the kinetic data for alkylation reactions between various polyphenolic compounds and chemical carcinogens of the epoxy type, which is currently lacking in the scientific literature.

A CAD-oriented parallel-computing design framework for shape and topology optimization of arbitrary structures using parametric level set

Recently, the high-resolution topology optimization to promote engineering applicability has gained much more attentions. However, an accurate and highly-efficient design framework for implementing shape and topology optimization of engineering structures with integration of CAD model is still in demand. In the current work, the critical intention is to develop a CAD-oriented parallel-computing design framework for arbitrary structures, where the Parametric Level Set Method (PLSM) is employed for shape and topology optimization. Firstly, an implicit identification model is constructed for generating a signed distance field using the vertex and normal information from the ‘STL’ file of engineering structures. The signed distance field is combined with the compactly supported radial basis functions (CSRBFs) to solve the initial level set function with a parametrization. This method is applied to present all domains, including design domains, Neumann boundary domains, Dirichlet boundary domains, and non-design domains. Secondly, the CPU parallel strategy is considered for allocating partitions of structural stiffness matrix in finite element analysis to different CPU cores for the parallel-computing to save computation costs. Thirdly, a parallel-computing design formulation is developed for performing shape and topology optimization of arbitrary structures, in which the partitioned terms of all design variables and stiffness matrix are concurrently computed on each CPU core. Finally, several classic benchmarks and the critical engineering structure of Virtual Reality (VR) glass part with extremely complex geometries, are discussed to demonstrate the effectiveness and efficiency of the proposed design framework.

Integrating word embedding and topic modeling for sentiment analysis: A case study on the social mood on economy

In recent years, textual analysis and embedding spaces have become essential and complementary tools for sentiment analysis in National Statistics Institutes’ research, owing to their ability to summarize discussed topics effectively. Istat has developed an innovative tool, wordembox, which allows external users to explore the outputs of popular word embedding algorithms, such as Word2Vec and FastText. This tool enriches the analysis with a novel graph functionality, enabling users to discover clusters of words and facilitating implicit topic modeling. This article focuses on Social Mood on Economy (SME) posts over a period in which the index recorded a strong downward trend: the first month of the Russia-Ukraine conflict at the beginning of 2022. We compare findings from wordembox with standard topic modeling techniques, including Bayesian Latent Dirichlet Allocation (LDA), Top2Vec, and BERTopic, recent methods that extract clusters from word embedding spaces. These techniques show coherent results, and their combined use in textual analysis may create a synergy that enhances the informative content of synthetic indexes such as ‘Social Mood on Economy Index (SMEI)’.

Comparison of post-impact residual strength ratio between hybrid filament-wound cylinder and hybrid plate specimen

The filament-wound (FW) cylinders possess numerous benefits as a high-pressure storage device but are susceptible to impact loads. The presence of post-impact residual strength in an operating FW cylinder has the potential to accelerate the onset of failure. Ensuring the structural integrity and safety of the equipment requires thorough impact testing, which can be expensive and time-consuming, resulting in limited use. This article presents an innovative and cost-effective approach for conducting low-velocity impact testing on a hybrid Al/CFRP filament-wound cylinder by utilizing a simple hybrid Al/CFRP plate specimen. The main focus is to conduct low-velocity impact testing on both types of specimens, followed by post-damage testing that includes tensile tests on the hybrid plate specimen and burst tests on the FW cylinder. The results of laboratory experiments were compared to explicit and implicit numerical models conducted in a broad spectrum of impact energy range and found to be consistent. Using a parameter known as the post-impact residual strength ratio, it is possible to determine the expected impact loading conditions on the hybrid plate specimen that are equivalent to those experienced by the FW-cylinder. This low-cost impact testing method offers a practical and feasible solution to ensure the dependability and safety of FW cylinders throughout their operational lifespan.

Learning facial structural dependency in 3D aligned space for face alignment

Facial structure's statistical characteristics offer pivotal prior information in facial landmark prediction, forming inter-dependencies among different landmarks. Such inter-dependencies ensure that predictions adhere to the shape distribution typical of natural faces. In challenging scenarios like occlusions or extreme facial poses, this structure becomes indispensable, which can help to predict elusive landmarks based on more discernible ones. While current deep learning methods do capture these landmark dependencies, it's often an implicit process heavily reliant on vast training datasets. We contest that such implicit modeling approaches fail to manage more challenging situations. In this paper, we propose a new method that harnesses the facial structure and explicitly explores inter-dependencies among facial landmarks in an end-to-end fashion. We propose a Structural Dependency Learning Module (SDLM). It uses 3D face information to map facial features into a canonical UV space, in which the facial structure is explicitly 3D semantically aligned. Besides, to explore the global relationships between facial landmarks, we take advantage of the self-attention mechanism in the image and UV spaces. We name the proposed method Facial Structure-based Face Alignment (FSFA). FSFA reinforces the landmark structure, especially under challenging conditions. Extensive experiments demonstrate that FSFA achieves state-of-the-art performance on the WFLW, 300W, AFLW, and COFW68 datasets.

Separating the predictable part of returns with CNN-GRU-attention from inputs to predict stock returns

The noise and high randomness of the stock market are primary obstacles to profitability. These factors cause stock returns to consist of short-term predictable and stock-specific residual parts. Therefore, it is beneficial to separate and model the two items for forecasting returns in the randomness environment. On this basis, we propose a novel Temporal Return Separation and Restore Forecasting (TRSRF) method. TRSRF first extracts price- and relation-based features from historical stock inputs and uses them to decompose and restore predictable and residual elements of historical returns , respectively. Then it forecasts these components based on historical values. We conducted experiments on the Chinese small and mid-cap, blue-chip, and large-cap indexes over ten years to compare with seven proposed baselines. On the three Chinese indexes our method separately exceeds 6%, 16%, and 22% absolute annualized returns than our baseline. The ablation study also proves the necessity of return decomposition and inter-stock relation modeling. We find that modeling inter-stock relations on small-cap stocks works better than on large-cap stocks. Furthermore, we prove our method might be an implicit ensemble model of the predictable and residual parts, which is why it works stability under various market conditions.

A modified physics-informed neural network to fatigue life prediction of deck-rib double-side welded joints

Deck-rib welded joint is an important part of orthotropic steel decks, which are susceptible to fatigue cracks under various load cycles. Therefore, it is essential to use efficient predicting methods to assess the fatigue performance of deck-rib welded joints with new geometry and form in order to ensure a reliable operation of the bridge. A modified physics-informed neural network (PINN) is proposed for the fatigue life prediction of the novel deck-rib double-side welded joints. The modified PINN incorporates implicit physical model as an activation function into the hidden neurons, and explicit physical constraints into the loss function. Additionally, the influence of deck thickness is integrated using limited test sample data based on the observational approach. The 62 experimental data were taken from the literature to compare the performance of the artificial neural network (ANN), traditional PINN and the modified PINN. The results demonstrate that the modified PINN enhances the learning process of the neural network through the joint learning of physical knowledge by activation function and loss function. Furthermore, the fatigue life prediction of the deck-rib double-side welded joints under the modified PINN exhibits physical consistency and accuracy when compared with the traditional ANN and PINN.

RobotSDF: Implicit Morphology Modeling for the Robotic Arm.

The expression of robot arm morphology is a critical foundation for achieving effective motion planning and collision avoidance in robotic systems. Traditional geometry-based approaches usually suffer from the contradiction between the high demand for computing resources for fine expression and the insufficient detail expression caused by the pursuit of efficiency. The signed distance function addresses these drawbacks due to its ability to handle complex and arbitrary shapes and lower computational requirements. However, conventional robotic morphology methods based on the signed distance function often face challenges when the robot moves dynamically, since robots with different postures are modeled as independent individuals but the postures of robots are infinite. In this paper, we introduce RobotSDF, an implicit morphology modeling approach that can express the robot shape of arbitrary posture precisely. Instead of depicting a whole model of the robot arm, RobotSDF models the robot morphology as integrated implicit joint models driven by joint configurations. In this approach, the dynamic shape change process of the robot is converted into the coordinate transformations of query points within each joint's coordinate system. Experimental results with the Elfin robot demonstrate that RobotSDF can accurately depict robot shapes across different postures up to the millimeter level, which exhibits 38.65% and 66.24% improvement over the Neural-JSDF and configuration space distance field algorithms, respectively, in representing robot morphology. We further verified the efficiency of RobotSDF through collision avoidance in both simulation and actual human-robot collaboration experiments.

PW-SMD: A Plane-Wave Implicit Solvation Model Based on Electron Density for Surface Chemistry and Crystalline Systems in Aqueous Solution.

Electron density-based implicit solvation models are a class of techniques for quantifying solvation effects and calculating free energies of solvation without an explicit representation of solvent molecules. Integral to the accuracy of solvation modeling is the proper definition of the solvation shell separating the solute molecule from the solvent environment, allowing for a physical partitioning of the free energies of solvation. Unlike state-of-the-art implicit solvation models for molecular quantum chemistry calculations, e.g., the solvation model based on solute electron density (SMD), solvation models for systems under periodic boundary conditions with plane-wave (PW) basis sets have been limited in their accuracy. Furthermore, a unified implicit solvation model with both homogeneous solution-phase and heterogeneous interfacial structures treated on equal footing is needed. In order to address this challenge, we developed a high-accuracy solvation model for periodic PW calculations that is applicable to molecular, ionic, interfacial, and bulk-phase chemistry. Our model, PW-SMD, is an extension of the SMD molecular solvation model to periodic systems in water. The free energy of solvation is partitioned into the electrostatic and cavity-dispersion-solvent structure (CDS) contributions. The electrostatic contributions of the solvation shell surrounding solute structures are parametrized based on their geometric and physical properties. In addition, the nonelectrostatic contribution to the solvation energy is accounted for by extending the CDS formalism of SMD to incorporate periodic boundary conditions. We validate the accuracy and robustness of our solvation model by comparing predicted solvation free energies against experimental data for molecular and ionic systems, carved-cluster composite energetic models of solvated reaction energies and barriers on surface systems, and deep-learning-accelerated ab initio molecular dynamics (AIMD). Our developed periodic implicit solvation model shows significantly improved accuracy compared to previous work (namely, solvation models in aqueous solution) and can be applied to simulate solvent effects in a wide range of surface and crystalline materials.