Diffusion Probability Research Articles

Diffusion network with spatial channel attention infusion and frequency spatial attention for brain tumor segmentation.

Accurate segmentation of gliomas is crucial for diagnosis, treatment planning, and evaluating therapeutic efficacy. Physicians typically analyze and delineate tumor regions in brain magnetic resonance imaging (MRI) images based on personal experience, which is often time-consuming and subject to individual interpretation. Despite advancements in deep learning technology for image segmentation, current techniques still face challenges in clearly defining tumor boundary contours and enhancing segmentationaccuracy. To address these issues, this paper proposes a conditional diffusion network (SF-Diff) with a spatial channel attention infusion (SCAI) module and a frequency spatial attention (FSA) mechanism to achieve accurate segmentation of the whole tumor (WT) region in braintumors. SF-Diff initially extracts multiscale information from multimodal MRI images and subsequently employs a diffusion model to restore boundaries and details, thereby enabling accurate brain tumor segmentation (BraTS). Specifically, a SCAI module is developed to capture multiscale information within and between encoder layers. A dual-channel upsampling block (DUB) is designed to assist in detail recovery during upsampling. A FSA mechanism is introduced to better match the conditional features with the diffusion probability distribution information. Furthermore, a cross-model loss function has been implemented to supervise the feature extraction of the conditional model and the noise distribution of the diffusionmodel. The dataset used in this paper is publicly available and includes 369 patient cases from the Multimodal BraTS Challenge 2020 (BraTS2020). The conducted experiments on BraTS2020 demonstrate that SF-Diff performs better than other state-of-the-art models. The method achieved a Dice score of 91.87%, a Hausdorff 95 of 5.47 mm, an IoU of 84.96%, a sensitivity of 92.29%, and a specificity of 99.95% onBraTS2020. The proposed SF-Diff performs well in identifying the WT region of the brain tumors compared to other state-of-the-art models, especially in terms of boundary contours and non-contiguous lesion regions, which is clinically significant. In the future, we will further develop this method for brain tumor three-class segmentation task.

BP-Diff: a conditional diffusion model for cuffless continuous BP waveform estimation using U-Net.

Continuous monitoring of blood pressure (BP) is crucial for daily healthcare. Although invasive methods provide accurate continuous BP measurements, they are not suitable for routine use. Photoplethysmography (PPG), a non-invasive technique that detects changes in blood volume within the microcirculation using light, shows promise for BP measurement. The primary goal of this study is to develop a novel cuffless method based on PPG for accurately estimating continuous BP.
Approach. We introduce BP-Diff, an end-to-end method for cuffless continuous BP waveform estimation utilizing a conditional diffusion probability model combined with a U-Net architecture. This approach takes advantage of the stochastic properties of diffusion models and the strong feature representation capabilities of U-Net. It integrates the continuous BP waveform as the initial status and uses the PPG signal and its derivatives as conditions to guide the training and sampling process.
Main results. BP-Diff was evaluated using both uncalibrated and calibrated schemes. The results indicate that, when uncalibrated, BP-Diff can accurately track BP dynamics, including peak and valley positions, as well as timing. After calibration, BP-Diff achieved highly accurate BP estimations. The mean absolute error (MAE) of the estimated BP waveforms, along with the systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP) from the calibrated BP-Diff model, were 2.99 mmHg, 2.6 mmHg, 1.4 mmHg, and 1.44 mmHg, respectively. Consistency tests, including Bland-Altman analysis and Pearson correlation, confirmed its high reliability compared to reference BP. BP-Diff meets the American Association for Medical Instrumentation (AAMI) standards and has achieved a Grade A from the British Hypertension Society (BHS).
Significance. This study utilizes PPG signals to develop a novel cuffless continuous BP measurement method, demonstrating superiority over existing approaches. The method is suitable for integration into wearable devices, providing a practical solution for continuous BP monitoring in everyday healthcare.

Coupled awareness-epidemic spreading with the consideration of self-isolation behavior

Epidemic transmission and the associated awareness diffusion are fundamentally interactive. There has been a burgeoning interest in exploring the coupled epidemic-awareness dynamic. However, current research predominantly focuses on self-protection behavior stimulated by awareness, paying less attention to self-isolation behavior. Given the constraints of government-mandated quarantine measures, spontaneous self-isolation actions assume greater significance in the long-term response to epidemics. In response, we propose a coupled awareness-epidemic spreading model with the consideration of self-isolation behavior and subsequently employ a Micro Markov Chain Approach to analyze the model. Extensive experiments show that self-isolation behavior can effectively raise the epidemic threshold and reduce the final outbreak scale. Notably, in multiplex networks with positive inter-layer correlation, the inhibitory effect is the greatest. Moreover, there exists a metacritical point, only when the awareness diffusion probability exceeds the critical value of this point, the epidemic threshold will increase with the increase of awareness diffusion probability. In addition, the growth of the average degree of the virtual-contact layer can reduce the value of this metacritical point. This research emphasizes the significant role of self-isolation behavior in curbing epidemic transmission, providing valuable perspectives for epidemic prevention through the interplay of awareness and epidemic spreading.

A fault diagnosis method based on an improved diffusion model under limited sample conditions.

As a critical component in mechanical systems, the operational status of rolling bearings plays a pivotal role in ensuring the stability and safety of the entire system. However, in practical applications, the fault diagnosis of rolling bearings often encounters limitations due to the constraint of sample size, leading to suboptimal diagnostic accuracy. This article proposes a rolling bearing fault diagnosis method based on an improved denoising diffusion probability model (DDPM) to address this issue. The practical value of this research lies in its ability to address the limitation of small sample sizes in rolling bearing fault diagnosis. By leveraging DDPM to generate one-dimensional vibration data, the proposed method significantly enriches the datasets and consequently enhances the generalization capability of the diagnostic model. During the model training process, we innovatively introduce the feature differences between the original vibration data and the predicted vibration data generated based on prediction noise into the loss function, making the generated data more directional and targeted. In addition, this article adopts a one-dimensional convolutional neural network (1D-CNN) to construct a fault diagnosis model to more accurately extract and focus on key feature information related to faults. The experimental results show that this method can effectively improve the accuracy and reliability of rolling bearing fault diagnosis, providing new ideas and methods for fault detection and prevention in industrial applications. This advancement in diagnostic technology has the potential to significantly reduce the risk of system failures, enhance operational efficiency, and lower maintenance costs, thus contributing significantly to the safety and efficiency of mechanical systems.

The coupled awareness-epidemic dynamics with individualized self-initiated awareness in multiplex networks

The outbreak of an epidemic often stimulates the generation of public awareness about epidemic prevention. This heightened awareness encourages individuals to take proactive protective measures, thereby curbing the transmission of the epidemic. Previous research commonly adopts an assumption that each individual has the same probability of awakening self-protection awareness after infection. However, in the real-world process, different individuals may generate varying awareness responses due to the differences in the amount of information received. Therefore, in this study, we first propose a coupled awareness-epidemic spreading model, where the self-initiated awareness of each individual can be influenced by the number of aware neighbors. Subsequently, we develop a Micro Markov Chain Approach to analyze the proposed model and explore the effects of different dynamic and structural parameters on the coupled dynamics. Findings indicate that individual awareness awakening can effectively promote awareness diffusion within the proposed coupled dynamics and inhibit epidemic transmission. Moreover, the influence of awareness diffusion on epidemic transmission exhibits a metacritical point, from which the epidemic threshold increases with the increase in the awareness diffusion probability. The research findings also suggest that the increase in the average degree of virtual-contact networks can reduce the value of the metacritical point, while the change in the average degree of the physical-contact networks does not affect the metacritical point. Finally, we conduct extensive experiments on four real networks and obtain results consistent with the above conclusions. The systematic research findings of this study provide new insights for exploring the interaction between individual awareness and epidemic transmission in the real world.

ReF-DDPM: A novel DDPM-based data augmentation method for imbalanced rolling bearing fault diagnosis

Effective bearing fault diagnosis is crucial to ensure the safety and reliability of mechanical systems. Due to the complex and harsh working environment, mechanical data often comes from imbalanced datasets, which is a pressing problem in diagnosis applications. However, currently proposed data augmentation methods mainly based on generative adversarial networks, remain challenging in balancing the quality and diversity of the generation samples. To solve it, this paper proposes a new data enhancement method called the reparameterized residual denoising diffusion probability model (ReF-DDPM) and applies it to fault diagnosis. The proposed architecture includes a forward diffusion process and a reverse denoising process, where Gaussian noise and original samples are transformed by Markov chains. To improve the quality of generation samples, the noise prediction network is modified for better feature representation by enhancing intra-level and inter-level features. Furthermore, signal labels are added to the model as conditional information to direct the generation of relevant category samples during the sampling process. The study provides a new data augmentation method for bearing imbalanced data, and generation data can be further used for fault diagnosis tasks. Verification experiments demonstrate the effectiveness and good generalization of the method, and improve the accuracy of imbalance fault diagnosis.

Enhancing Hi-C contact matrices for loop detection with Capricorn: a multiview diffusion model.

High-resolution Hi-C contact matrices reveal the detailed three-dimensional architecture of the genome, but high-coverage experimental Hi-C data are expensive to generate. Simultaneously, chromatin structure analyses struggle with extremely sparse contact matrices. To address this problem, computational methods to enhance low-coverage contact matrices have been developed, but existing methods are largely based on resolution enhancement methods for natural images and hence often employ models that do not distinguish between biologically meaningful contacts, such as loops and other stochastic contacts. We present Capricorn, a machine learning model for Hi-C resolution enhancement that incorporates small-scale chromatin features as additional views of the input Hi-C contact matrix and leverages a diffusion probability model backbone to generate a high-coverage matrix. We show that Capricorn outperforms the state of the art in a cross-cell-line setting, improving on existing methods by 17% in mean squared error and 26% in F1 score for chromatin loop identification from the generated high-coverage data. We also demonstrate that Capricorn performs well in the cross-chromosome setting and cross-chromosome, cross-cell-line setting, improving the downstream loop F1 score by 14% relative to existing methods. We further show that our multiview idea can also be used to improve several existing methods, HiCARN and HiCNN, indicating the wide applicability of this approach. Finally, we use DNA sequence to validate discovered loops and find that the fraction of CTCF-supported loops from Capricorn is similar to those identified from the high-coverage data. Capricorn is a powerful Hi-C resolution enhancement method that enables scientists to find chromatin features that cannot be identified in the low-coverage contact matrix. Implementation of Capricorn and source code for reproducing all figures in this paper are available at https://github.com/CHNFTQ/Capricorn.

Enhanced Image Denoising with Diffusion Probability and Dictionary Learning Adaptation

Enhanced Image Denoising with Diffusion Probability and Dictionary Learning Adaptation

Super-resolution reconstruction of single image for latent features

Single-image super-resolution (SISR) typically focuses on restoring various degraded low-resolution (LR) images to a single high-resolution (HR) image. However, during SISR tasks, it is often challenging for models to simultaneously maintain high quality and rapid sampling while preserving diversity in details and texture features. This challenge can lead to issues such as model collapse, lack of rich details and texture features in the reconstructed HR images, and excessive time consumption for model sampling. To address these problems, this paper proposes a Latent Feature-oriented Diffusion Probability Model (LDDPM). First, we designed a conditional encoder capable of effectively encoding LR images, reducing the solution space for model image reconstruction and thereby improving the quality of the reconstructed images. We then employed a normalized flow and multimodal adversarial training, learning from complex multimodal distributions, to model the denoising distribution. Doing so boosts the generative modeling capabilities within a minimal number of sampling steps. Experimental comparisons of our proposed model with existing SISR methods on mainstream datasets demonstrate that our model reconstructs more realistic HR images and achieves better performance on multiple evaluation metrics, providing a fresh perspective for tackling SISR tasks.

Coulomb effect on elastic electron scattering by hydrogen atom and hydrogen-like ions in their metastable 2s state in the 511–770 KeV energy range

This paper reports on a study investigating the elastic scattering of hydrogen atoms in their metastable state (2S-2S) when subjected to electron impact, with a focus on the Coulomb effect within an energy range spanning from 511 keV to 770 keV . The analysis employs semi-relativistic wave functions to depict the hydrogen states. The validity of using Darwin wave functions is confirmed by ensuring that the condition Zα << 1 is met, where α represents the structure constant. Both incident and scattered free electrons are described using Dirac spinors. Notably, the semi-relativistic calculations converge with those of the non-relativistic case at low electron velocities. Additionally, in the presence of the Coulomb effect, the electron wave function is approximated by a Dirac function modulated by the confluent hypergeometric function. The paper presents the relativistic differential cross-section (RDCS) as a function of the final scattering angle for various energies of the incident electron, revealing intriguing insights into diffusion probabilities in specific directions. Moreover, the impact of the atomic number Z on the elastic scattering of hydrogen atoms and hydrogen-like ions by electron impact under the influence of the Coulomb effect is thoroughly examined.

Sample-imbalanced wafer map defects classification based on auxiliary classifier denoising diffusion probability model

This paper research on the classification task of wafer map defects under imbalanced sample. To improve the number of imbalanced wafer maps, a denoising diffusion probabilistic model with auxiliary classifier is proposed to generate new wafer maps. The developed model has an U-net structure with multiple inputs and outputs, taking wafer images, noise degree and category features as inputs, and outputs predicted noise and prediction category. When performing data augmentation, the trained model gradually removes prediction noise from the initial random noise and obtains new wafers. Finally, the balanced wafer defect maps are classified using a residual neural network. The proposed auxiliary classifier denoising diffusion probabilistic model and residual neural networks (ACDDPM-ResNet) method has validated on the MIR-WM811K dataset and MixedWM38 dataset, and the defect classification results of the imbalanced wafer map are remarkable improved after data augmentation. In addition, the paper also discusses and analyzes the influence of the maximum noise addition steps and the data augmentation size on the accuracy of wafer classification. It is further validated that the proposed wafer map classification method based on data augmentation can solve the classification problem caused by sample imbalance.

Enhancing Adoption of Sustainable Product Innovations: Addressing Reduced Performance with Risk-Reducing Product Modifications

Past studies have shown that the probability of the successful diffusion of sustainable product innovations is strikingly low. A potentially promising marketing strategy to reduce negative consumer perceptions of sustainable product innovations is risk-reducing product modifications (RPMs), which account for behavioral adjustments and performance uncertainties by employing an additional component that uses established technology. This research strives to empirically test the potential positive effects of RPMs using two studies on electric vehicles with and without range extenders as prime examples of RPM: (1) an online survey of potential adopters and (2) a postadoption survey of early adopters. The results show that RPMs increase the adoption of sustainable product innovations. Consumers’ tendency to overestimate their true needs and their need for insurance against insufficient performance explain the effectiveness of RPM.

Label-Free Light Scattering Imaging with Purified Brownian Motion Differentiates Small Extracellular Vesicles in Cell Microenvironments.

Small extracellular vesicles (sEVs) are heterogeneous biological nanoparticles (NPs) with wide biomedicine applications. Tracking individual nanoscale sEVs can reveal information that conventional microscopic methods may lack, especially in cellular microenvironments. This usually requires biolabeling to identify single sEVs. Here, we developed a light scattering imaging method based on dark-field technology for label-free nanoparticle diffusion analysis (NDA). Compared with nanoparticle tracking analysis (NTA), our method was shown to determine the diffusion probabilities of a single NP. It was demonstrated that accurate size determination of NPs of 41 and 120 nm in diameter is achieved by purified Brownian motion (pBM), without or within the cell microenvironments. Our pBM method was also shown to obtain a consistent size estimation of the normal and cancerous plasma-derived sEVs without and within cell microenvironments, while cancerous plasma-derived sEVs are statistically smaller than normal ones. Moreover, we showed that the velocity and diffusion coefficient are key parameters for determining the diffusion types of the NPs and sEVs in a cancerous cell microenvironment. Our light scattering-based NDA and pBM methods can be used for size determination of NPs, even in cell microenvironments, and also provide a tool that may be used to analyze sEVs for many biomedical applications.

Score Dynamics: Scaling Molecular Dynamics with Picoseconds Time Steps via Conditional Diffusion Model.

We propose score dynamics (SD), a general framework for learning accelerated evolution operators with large timesteps from molecular dynamics (MD) simulations. SD is centered around scores or derivatives of the transition log-probability with respect to the dynamical degrees of freedom. The latter play the same role as force fields in MD but are used in denoising diffusion probability models to generate discrete transitions of the dynamical variables in an SD time step, which can be orders of magnitude larger than a typical MD time step. In this work, we construct graph neural network-based SD models of realistic molecular systems that are evolved with 10 ps timesteps. We demonstrate the efficacy of SD with case studies of the alanine dipeptide and short alkanes in aqueous solution. Both equilibrium predictions derived from the stationary distributions of the conditional probability and kinetic predictions for the transition rates and transition paths are in good agreement with MD. Our current SD implementation is about 2 orders of magnitude faster than the MD counterpart for the systems studied in this work. Open challenges and possible future remedies to improve SD are also discussed.

Research Advanced in Image Generation Based on Diffusion Probability Model

Image generation has been a popular research task in the computer vision community, which aims to learn a distribution from a specific dataset and generate realistic images obeying this distribution. Thanks to the rapid development of deep learning technology, image generation models based on convolutional neural networks, especially generative adversarial networks (GANs) and variational autoencoders (VAEs), have become mainstream frameworks for image generation. However, in recent years, with the gradual deepening of the research on the denoising diffusion probability model (DDPM), the image generation technology based on DDPM has made new breakthroughs in accuracy and speed. Around the Diffusion Model, this paper introduces its latest research progress in image generation and derivative tasks. Specifically, this paper reviews the key techniques and basic theories of the diffusion model in detail. Then, the main research work, improvement mechanism and characteristics of the DDPM-based image generation method are summarized and summarized. This paper focuses on the basic structure and related applications of diffusion models, and evaluates some basic functions. Finally, the current problems and future development directions of image generation technology based on diffusion model are analyzed and summarized.

Diffusion coefficient expression for asymmetric discrete random walk with unequal jump times, lengths, and probabilities

Random walk has wide applications in many fields, such as generative AI, biology, physics, and chemistry. Asymmetric random walk could be described by the drift-diffusion equation. Although random walk has been an extensively investigated topic, the current reported theoretical results for discrete asymmetric random walks are often limited to simple asymmetry due to unequal jump probabilities or lengths. This paper investigated more complicated asymmetric random walks. In the random walk, the particle could take three possible actions at each step: left jump, right jump, or immobile; additionally, each type of action could have different probabilities, times, and lengths. The general diffusion coefficient expressions are derived. The results indicate that the exchanges between different types of actions play critical roles in determining the diffusion coefficient. The obtained theoretical results can be reduced to reported results. The obtained results show that the diffusion coefficients are significantly different between discrete and continuous time asymmetric random walks. Additionally, discrete random walk simulations are performed to verify the obtained theoretical results. There are good agreements between the theoretical predictions and simulation results. The diffusion coefficient and probability distribution function could provide critical information for understanding dynamic processes in many systems, such as polymers or biological systems.

RoughSet-DDPM: An Image Super-Resolution Method Based on Rough set Denoising Diffusion Probability Model

RoughSet-DDPM: An Image Super-Resolution Method Based on Rough set Denoising Diffusion Probability Model

Supplementary Influence Maximization Problem in Social Networks

Due to important applications in viral marketing, influence maximization (IM) has become a well-studied problem. It aims at finding a small subset of initial users so that they can deliver information to the largest amount of users through the word-of-mouth effect. The original IM only considers a singleton item. And the majority of extensions ignore the relationships among different items or only consider their competitive interactions. In reality, the diffusion probability of one item will increase when users adopted supplementary products in advance. Motivated by this scenario, we propose a supplementary independent cascade (IC) and discuss the supplementary IM problem. Our problem is NP-hard, and the computation of the objective function is #P-hard. We notice that the diffusion probability will change when considering the impact of its supplementary product. Therefore, the efficient reverse influence sampling (RIS) techniques cannot be applied to our problem directly even though the objective function is submodular. To address this issue, we utilize the sandwich approximation (SA) strategy to obtain a data-dependent approximate solution. Furthermore, we define the supplementary-based reverse reachable (SRR) sets and then propose a heuristic algorithm. Finally, the experimental results on three real datasets support the efficiency and superiority of our methods.

A Two-Stage Earthquake Event Classification Model Based on Diffusion Probability Model

A Two-Stage Earthquake Event Classification Model Based on Diffusion Probability Model

Anomaly Detection of Industrial Smelting Furnace Incorporated With Accelerated Sampling Denoising Diffusion Probability Model and Conv-Transformer

Anomaly Detection of Industrial Smelting Furnace Incorporated With Accelerated Sampling Denoising Diffusion Probability Model and Conv-Transformer