Noise Scaling Research Articles

Enhancing Amyloid PET Quantification: MRI-Guided Super-Resolution Using Latent Diffusion Models

Amyloid PET imaging plays a crucial role in the diagnosis and research of Alzheimer’s disease (AD), allowing non-invasive detection of amyloid-β plaques in the brain. However, the low spatial resolution of PET scans limits the accurate quantification of amyloid deposition due to partial volume effects (PVE). In this study, we propose a novel approach to addressing PVE using a latent diffusion model for resolution recovery (LDM-RR) of PET imaging. We leverage a synthetic data generation pipeline to create high-resolution PET digital phantoms for model training. The proposed LDM-RR model incorporates a weighted combination of L1, L2, and MS-SSIM losses at both noise and image scales to enhance MRI-guided reconstruction. We evaluated the model’s performance in improving statistical power for detecting longitudinal changes and enhancing agreement between amyloid PET measurements from different tracers. The results demonstrate that the LDM-RR approach significantly improves PET quantification accuracy, reduces inter-tracer variability, and enhances the detection of subtle changes in amyloid deposition over time. We show that deep learning has the potential to improve PET quantification in AD, effectively contributing to the early detection and monitoring of disease progression.

Convergence rates and central limit theorem for 3-D stochastic fractional Boussinesq equations with transport noise

This work investigates the 3-D stochastic modified fractional Boussinesq equations driven by transport noise on the torus. The existence of weak solutions is initially established through Galerkin approximation and compactness techniques. Subsequently, we demonstrate that the weak solutions of stochastic modified fractional Boussinesq equations converge to the unique solution of a deterministic Boussinesq model with fractional dissipation, subject to an appropriate noise scaling, along with providing the quantitative estimates with explicit convergent rates. Finally, the central limit theorem with an explicit convergence rate is established based on the aforementioned scaling limit. It is noteworthy that the scaling limit result of stochastic modified fractional Boussinesq equations to deterministic Boussinesq models with additional fractional dissipation implies that the transport noise regularizes the modified fractional Boussinesq equations, thus leading to “approximate weak uniqueness”.

FDP-FL: differentially private federated learning with flexible privacy budget allocation

Abstract Federated learning (FL) as a privacy-preserving technology enables multiple clients to collaboratively train models on decentralized data. However, transmitting model parameters between local clients and the central server can potentially result in information leakage. Differentially private federated learning (DPFL) has emerged as a promising solution to enhance privacy. Nevertheless, existing DPFL schemes suffer from two issues: (i) most schemes that aim to achieve desired model accuracy may incur a high privacy budget. (ii) several schemes that consider the trade-off between privacy and accuracy by utilizing linear clipping bound may distort numerous model parameters. In this paper, we first propose FDP-FL, a flexible differential privacy approach for FL. FDP-FL introduces a novel series sum privacy budget allocation instead of uniform allocation and enables adaptive and nonlinear noise scale decay. In this way, a tight bound for cumulative privacy loss can be achieved while optimizing model accuracy. Then in order to mitigate gradient leakages caused by honest-but-curious clients and server, we further design client-level FDP-FL and record-level FDP-FL, respectively. Experimental results demonstrate that our FDP-FL improves model accuracy by $\sim $13.3% compared with the basic DP-FL under a fixed privacy budget and outperforms existing trade-off schemes with the same hyperparameter setting.

A survey on various edge detection techniques in image processing and applied disease detection

This paper surveys various edge detection techniques in image processing, focusing on their applicability to disease detection. Many researchers encompass studies conducted in the context of various crops and fruits, shedding light on their effectiveness and adaptability. However, the more techniques are used and improved, less comparison has been made between them to look further at their challenges, such as noise sensitivity, scale variability, edge linking, and real-world variability. Also, the study will systematically survey and analyze literature on the ability of edge detection, including classical methods like Robert, Sobel, Prewitt, and Canny, as well as more advanced techniques such as gradient-based and Gaussian-based. This research aims to comprehensively understand the strengths and limitations of different edge detection techniques and can be used as a reference point for selecting and enhancing novel techniques in image processing. Overview, this paper makes a substantial contribution to the field by addressing both traditional edge detection in image processing and applied disease detection. It serves as a comprehensive guide, offering insights, practical advice, and a consolidated view of current research trends, and highlights the potential of edge detection in contributing to advancements in disease detection methodologies making it a valuable resource for researchers and practitioners.

Noise Scaling in SQUID Arrays

Abstract We numerically investigate the noise scaling in high-T_c commensurate 1D and 2D SQUID arrays. We show that the voltage noise spectral density in 1D arrays violates the scaling rule of ~1/N_p for the number N_p of Josephson junctions in parallel. In contrast, in 2D arrays with N_s 1D arrays in series, the voltage noise spectral density follows more closely the expected scaling behaviour of ~N_s/N_p. Additionally, we reveal how the flux and magnetic field rms noise spectral densities deviate from their expected ~(N_sN_p)^{-1/2} scaling and discuss their implications for designing low noise magnetometers.

Dynamic Tracking Method Based on Improved DeepSORT for Electric Vehicle

The development of electric vehicles has facilitated intelligent transportation, which requires the swift and effective detection and tracking of moving vehicles. To satisfy this demand, this paper presents an enhanced DeepSORT algorithm. By selecting YOLO-SSFS as the front-end detector and incorporating a lightweight and high-precision feature training network called FasterNet, the proposed method effectively extracts vehicle appearance attributes. Besides this, the noise scale adaptive Kalman filter is implemented and the conventional cascade matching process is substituted with global join matching, thereby enhancing overall performance and tracking accuracy. Validation conducted on the VisDrone dataset demonstrates the superiority of this method compared to the original DeepSORT algorithm, exhibiting a 4.76% increase in tracking accuracy and a 3.10% improvement in tracking precision. The findings reveal the advantages of the algorithms in the domain of vehicle detection and tracking, allowing significant technological advancements in intelligent transportation systems.

A variational Bayesian based robust filter for unknown measurement bias and inaccurate noise statistics

In many practical fields, the unknown time-varying measurement biases (additive and multiplicative bias) and heavy-tailed measurement noise caused by some unpredictable anomalous behaviors may degrade the performance of conventional Kalman filter seriously. To solve the state estimation problem of systems with time-varying measurement biases and heavy-tailed measurement noise, this paper proposes a new variational Bayesian (VB) based robust filter. Firstly, the non-Gaussian measurement likelihood probability density function (ML-PDF) with multiplicative and additive measurement bias is built. Then, the conjugate prior distributions for unknown bias and noise scale parameters are selected, and the VB method is utilized to jointly infer the system state, unknown measurement biases and inaccurate measurement noise covariance matrix. Finally, a VB based robust filter is derived and its effectiveness is verified by the numerical simulations.

An Effective Federated Object Detection Framework with Dynamic Differential Privacy

The proliferation of data across multiple domains necessitates the adoption of machine learning models that respect user privacy and data security, particularly in sensitive scenarios like surveillance and medical imaging. Federated learning (FL) offers a promising solution by decentralizing the learning process, allowing multiple participants to collaboratively train a model without sharing their data. However, when applied to complex tasks such as object detection, standard FL frameworks can fall short in balancing the dual demands of high accuracy and stringent privacy. This paper introduces a sophisticated federated object detection framework that incorporates advanced differential privacy mechanisms to enhance privacy protection. Our framework is designed to work effectively across heterogeneous and potentially large-scale datasets, characteristic of real-world environments. It integrates a novel adaptive differential privacy model that strategically adjusts the noise scale during the training process based on the sensitivity of the features being learned and the progression of the model’s accuracy. We present a detailed methodology that includes a privacy budget management system, which optimally allocates and tracks privacy expenditure throughout training cycles. Additionally, our approach employs a hybrid model aggregation technique that not only ensures robust privacy guarantees but also mitigates the degradation of object detection performance typically associated with DP. The effectiveness of our framework is demonstrated through extensive experiments on multiple benchmark datasets, including COCO and PASCAL VOC. Our results show that our framework not only adheres to strict DP standards but also achieves near-state-of-the-art object detection performance, underscoring its practical applicability. For example, in some settings, our method can lower the privacy success rate by 40% while maintaining high model accuracy. This study makes significant strides in advancing the field of privacy-preserving machine learning, especially in applications where user privacy cannot be compromised. The proposed framework sets a new benchmark for implementing federated learning in complex, privacy-sensitive tasks and opens avenues for future research in secure, decentralized machine learning technologies.

Automatic segmentation of spine x-ray images based on multiscale feature enhancement network.

Automatic segmentation of vertebrae in spinal x-ray images is crucial for clinical diagnosis, case analysis, and surgical planning of spinal lesions. However, due to the inherent characteristics of x-ray images, including low contrast, high noise, and uneven grey scale, it remains a critical and challenging problem in computer-aided spine image analysis and disease diagnosis applications. In this paper, a Multiscale Feature Enhancement Network (MFENet), is proposed for segmenting whole spinal x-ray images, to aid doctors in diagnosing spinal-related diseases. To enhance feature extraction, the network incorporates a Dual-branch Feature Extraction Module (DFEM) and a Semantic Aggregation Module (SAM). The DFEM has a parallel dual-branch structure. The upper branch utilizes multiscale convolutional kernels to extract features from images. Employing convolutional kernels of different sizes helps capture details and structural information at different scales. The lower branch incorporates attention mechanisms to further optimize feature representation. By modeling the feature maps spatially and across channels, the network becomes more focused on key feature regions and suppresses task-irrelevant information. The SAM leverages contextual semantic information to compensate for details lost during pooling and convolution operations. It integrates high-level feature information from different scales to reduce segmentation result discontinuity. In addition, a hybrid loss function is employed to enhance the network's feature extraction capability. In this study, we conducted a multitude of experiments utilizing dataset provided by the Spine Surgery Department of Henan Provincial People's Hospital. The experimental results indicate that our proposed MFENet demonstrates superior segmentation performance in spinal segmentation on x-ray images compared to other advanced methods, achieving 92.61±0.431 for MIoU, 92.42±0.329 for DSC, and 99.51±0.037 for Global_accuracy. Our model is able to more effectively learn and extract global contextual semantic information, significantly improving spinal segmentation performance, further aiding doctors in analyzing patient conditions.

Prediction of cavity inception speed and underwater radiated noise of a full-scale marine propeller based on a cavitation tunnel model test

Propeller cavitation is a dominant source of underwater radiated noise (URN) from shipping, and the appropriate evaluation of propeller noise mitigation measures is important for ecological ship design. In this study, a model test procedure and scaling method to predict the full-scale URN level from hydrodynamic noise sources were introduced. The cavity size based on the empirical vortex model was considered in the proposed scaling method for a quiet cruise condition with isolated tip vortex cavitation. This relation provides information on the equivalent cavitation number for the model test to have the same relative radius as that of the full-scale tip vortex cavitation. The alternative test cavitation number can also be chosen as close as possible to the point that gives the equivalent tip vortex cavity size if sheet cavitation exists in the condition for the equivalent cavity size. In this case, additional noise scaling should be performed using the ratio of the tip vortex cavity radii. The new scaling exponent introduced in this study varies according to the distance from the cavitation inception condition and shows a decreasing trend from the value at the inception condition as the equivalent cavitation number for the model test decreases. The scaled URN levels based on the proposed method showed reasonable agreement with the measurement results of a full-scale ship. Finally, the noise reduction effect of the specially designed wake control fin and propeller was investigated through a comparative model test following the proposed scaling strategy, and significant noise reductions were observed with changes in the design configuration.

An electric bicycle tracking algorithm for improved traffic management

This paper proposes an efficient electric bicycle tracking algorithm, EBTrack, utilizing the high-precision and lightweight YOLOv7 as the target detector to enhance the efficiency of illegal detection and recognition of electric bicycles. The EBTrack effectively captures the position and trajectory of electric bicycles in complex traffic monitoring scenarios. Firstly, we introduce the feature extraction network, ResNetEB, specifically designed for feature re-identification of electric bicycles. To maintain real-time performance, feature extraction is performed only when generating new object IDs, minimizing the impact on processing speed. Secondly, for accurate target trajectory prediction, we incorporate an adaptive modulated noise scale Kalman filter. Additionally, considering the uncertainty of electric bicycle entry directions in traffic monitoring scenarios, we design a specialized matching mechanism to reduce frequent ID switching. Finally, to validate the algorithm's effectiveness, we have collected diverse video image data of electric bicycle and urban road traffic in Hefei, Anhui Province, encompassing different perspectives, time periods, and weather conditions. We have trained the proposed detector and have evaluated its tracking performance on this comprehensive dataset. Experimental results demonstrate that EBTrack achieves impressive accuracy, with 89.8 % MOTA (Multiple Object Tracking Accuracy) and 94.2 % IDF1 (ID F1-Score). Furthermore, the algorithm effectively reduces ID switching, significantly improving tracking stability and continuity.

Efficient differential privacy enabled federated learning model for detecting COVID-19 disease using chest X-ray images.

The rapid spread of COVID-19 pandemic across the world has not only disturbed the global economy but also raised the demand for accurate disease detection models. Although many studies have proposed effective solutions for the early detection and prediction of COVID-19 with Machine Learning (ML) and Deep learning (DL) based techniques, but these models remain vulnerable to data privacy and security breaches. To overcome the challenges of existing systems, we introduced Adaptive Differential Privacy-based Federated Learning (DPFL) model for predicting COVID-19 disease from chest X-ray images which introduces an innovative adaptive mechanism that dynamically adjusts privacy levels based on real-time data sensitivity analysis, improving the practical applicability of Federated Learning (FL) in diverse healthcare environments. We compared and analyzed the performance of this distributed learning model with a traditional centralized model. Moreover, we enhance the model by integrating a FL approach with an early stopping mechanism to achieve efficient COVID-19 prediction with minimal communication overhead. To ensure privacy without compromising model utility and accuracy, we evaluated the proposed model under various noise scales. Finally, we discussed strategies for increasing the model's accuracy while maintaining robustness as well as privacy.

Better Differentially Private Approximate Histograms and Heavy Hitters using the Misra-Gries Sketch

Better Differentially Private Approximate Histograms and Heavy Hitters using the Misra-Gries Sketch

Population health implications of exposure to pervasive military aircraft noise pollution.

While the adverse health effects of civil aircraft noise are relatively well studied, impacts associated with more intense and intermittent noise from military aviation have been rarely assessed. In recent years, increased training at Naval Air Station Whidbey Island, USA has raised concerns regarding the public health and well-being implications of noise from military aviation. This study assessed the public health risks of military aircraft noise by developing a systematic workflow that uses acoustic and aircraft operations data to map noise exposure and predict health outcomes at the population scale. Acoustic data encompassing seven years of monitoring efforts were integrated with flight operations data for 2020-2021 and a Department of Defense noise simulation model to characterize the noise regime. The model produced contours for day-night, nighttime, and 24-h average levels, which were validated by field monitoring and mapped to yield the estimated noise burden. Established thresholds and exposure-response relationships were used to predict the population subject to potential noise-related health effects, including annoyance, sleep disturbance, hearing impairment, and delays in childhood learning. Over 74,000 people within the area of aircraft noise exposure were at risk of adverse health effects. Of those exposed, substantial numbers were estimated to be highly annoyed and highly sleep disturbed, and several schools were exposed to levels that place them at risk of delay in childhood learning. Noise in some areas exceeded thresholds established by federal regulations for public health, residential land use and noise mitigation action, as well as the ranges of established exposure-response relationships. This study quantified the extensive spatial scale and population health burden of noise from military aviation.We employed a novel GIS-based workflow for relating mapped distributions of aircraft noise exposure to a suite of public health outcomes by integrating acoustic monitoring and simulation data with a dasymetric population density map. This approach enables the evaluation of population health impacts due to past, current, and future proposed military operations. Moreover, itcanbemodified for application to other environmental noise sources and offers an improved open-sourcetool to assess the population health implications of environmental noise exposure, inform at-risk communities, and guide efforts in noise mitigation and policy governing noise legislation, urban planning, and land use.

A Pilot Study of Observation Poisoning on Selective Reincarnation in Multi-Agent Reinforcement Learning

This research explores the vulnerability of selective reincarnation, a concept in Multi-Agent Reinforcement Learning (MARL), in response to observation poisoning attacks. Observation poisoning is an adversarial strategy that subtly manipulates an agent’s observation space, potentially leading to a misdirection in its learning process. The primary aim of this paper is to systematically evaluate the robustness of selective reincarnation in MARL systems against the subtle yet potentially debilitating effects of observation poisoning attacks. Through assessing how manipulated observation data influences MARL agents, we seek to highlight potential vulnerabilities and inform the development of more resilient MARL systems. Our experimental testbed was the widely used HalfCheetah environment, utilizing the Independent Deep Deterministic Policy Gradient algorithm within a cooperative MARL setting. We introduced a series of triggers, namely Gaussian noise addition, observation reversal, random shuffling, and scaling, into the teacher dataset of the MARL system provided to the reincarnating agents of HalfCheetah. Here, the “teacher dataset” refers to the stored experiences from previous training sessions used to accelerate the learning of reincarnating agents in MARL. This approach enabled the observation of these triggers’ significant impact on reincarnation decisions. Specifically, the reversal technique showed the most pronounced negative effect for maximum returns, with an average decrease of 38.08% in Kendall’s tau values across all the agent combinations. With random shuffling, Kendall’s tau values decreased by 17.66%. On the other hand, noise addition and scaling aligned with the original ranking by only 21.42% and 32.66%, respectively. The results, quantified by Kendall’s tau metric, indicate the fragility of the selective reincarnation process under adversarial observation poisoning. Our findings also reveal that vulnerability to observation poisoning varies significantly among different agent combinations, with some exhibiting markedly higher susceptibility than others. This investigation elucidates our understanding of selective reincarnation’s robustness against observation poisoning attacks, which is crucial for developing more secure MARL systems and also for making informed decisions about agent reincarnation.

Engineering Clock Transitions in Molecular Lanthanide Complexes.

Molecular lanthanide (Ln) complexes are promising candidates for the development of next-generation quantum technologies. High-symmetry structures incorporating integer spin Ln ions can give rise to well-isolated crystal field quasi-doublet ground states, i.e., quantum two-level systems that may serve as the basis for magnetic qubits. Recent work has shown that symmetry lowering of the coordination environment around the Ln ion can produce an avoided crossing or clock transition within the ground doublet, leading to significantly enhanced coherence. Here, we employ single-crystal high-frequency electron paramagnetic resonance spectroscopy and high-level ab initio calculations to carry out a detailed investigation of the nine-coordinate complexes, [HoIIIL1L2], where L1 = 1,4,7,10-tetrakis(2-pyridylmethyl)-1,4,7,10-tetraaza-cyclododecane and L2 = F- (1) or [MeCN]0 (2). The pseudo-4-fold symmetry imposed by the neutral organic ligand scaffold (L1) and the apical anionic fluoride ion generates a strong axial anisotropy with an mJ = ±8 ground-state quasi-doublet in 1, where mJ denotes the projection of the J = 8 spin-orbital moment onto the ∼C4 axis. Meanwhile, off-diagonal crystal field interactions give rise to a giant 116.4 ± 1.0 GHz clock transition within this doublet. We then demonstrate targeted crystal field engineering of the clock transition by replacing F- with neutral MeCN (2), resulting in an increase in the clock transition frequency by a factor of 2.2. The experimental results are in broad agreement with quantum chemical calculations. This tunability is highly desirable because decoherence caused by second-order sensitivity to magnetic noise scales inversely with the clock transition frequency.

Reduced-Order Model for Supersonic Transport Takeoff Noise Scaling with Cruise Mach Number

The recent interest in the development of supersonic transport raises concerns about an increase in community noise around airports. As noise certification standards for supersonic transport other than Concorde have not yet been developed by the International Civil Aviation Organization, there is a need for a physics-based scaling rule for supersonic transport takeoff noise performance. Assuming supersonic transport takeoff noise levels are dominated by the engine mixed jet velocity and the aircraft-to-microphone propagation distance, this paper presents a reduced-order model for supersonic transport takeoff noise levels as a function of four scaling groups: cruise Mach number, takeoff aerodynamic efficiency, takeoff speed, and number of installed engines. This paper finds that, as cruise Mach number increases, supersonic transport takeoff noise levels increase while their thrust cutback noise reduction potential decreases. Assuming constant aerodynamic efficiency, takeoff speed, and number of installed engines, the takeoff noise levels and noise reduction potential of a Mach 2.2 aircraft are found to be ∼15.3 dB higher and ∼19.2 dB less compared to a Mach 1.4 aircraft, respectively. This scaling rule can potentially yield a simple guideline for estimating an approximate noise limit for supersonic transport, depending on their cruise Mach number.

Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution

Image super-resolution is a fundamentally ill-posed problem because multiple valid high-resolution images exist for one low-resolution image. Super-resolution methods based on diffusion probabilistic models can deal with the ill-posed nature by learning the distribution of high-resolution images conditioned on low-resolution images, avoiding the problem of blurry images in PSNR-oriented methods. However, existing diffusion-based super-resolution methods have high time consumption with the use of iterative sampling, while the quality and consistency of generated images are less than ideal due to problems like color shifting. In this paper, we propose Efficient Conditional Diffusion Model with Probability Flow Sampling (ECDP) for image super-resolution. To reduce the time consumption, we design a continuous-time conditional diffusion model for image super-resolution, which enables the use of probability flow sampling for efficient generation. Additionally, to improve the consistency of generated images, we propose a hybrid parametrization for the denoiser network, which interpolates between the data-predicting parametrization and the noise-predicting parametrization for different noise scales. Moreover, we design an image quality loss as a complement to the score matching loss of diffusion models, further improving the consistency and quality of super-resolution. Extensive experiments on DIV2K, ImageNet, and CelebA demonstrate that our method achieves higher super-resolution quality than existing diffusion-based image super-resolution methods while having lower time consumption. Our code is available at https://github.com/Yuan-Yutao/ECDP.

Matrix factorization recommender based on adaptive Gaussian differential privacy for implicit feedback

Matrix factorization (MF) is an effective technique in recommendation systems. Since MF needs to utilize and analyze large amounts of user data during the recommendation process, this may lead to the leakage of personal data. Most of the current privacy-preserving MF research aims to protect explicit feedback, but ignores the protection of implicit feedback. In response to this limitation, we propose an adaptive differentially private MF (ADPMF) for implicit feedback. The proposed model is trained under the framework of Bayesian personalized ranking and uses gradient perturbation to achieve the (ϵ,δ)-differential privacy. In our model, we design two effective methods, adaptive clipping and adaptive noise scale, to improve recommendation performance while maintaining privacy. We use Gaussian Differential Privacy (GDP) to accommodate privacy analysis for dynamically changing clipping thresholds and noise scale. Theoretical analysis and experimental results demonstrate that ADPMF not only achieves highly accurate recommendations but also provides differential privacy protection for implicit feedback. The results show that ADPMF can improve the recommended performance substantially by 10% to 20% compared to the current privacy-preserving recommendation methods and has promising application prospects in various fields.

Privacy Amplification by Sampling under User-level Differential Privacy

Random sampling is an effective tool for reducing the computational costs of query processing in large databases. It has also been used frequently for private data analysis, in particular, under differential privacy (DP). An interesting phenomenon that the literature has identified, is that sampling can amplify the privacy guarantee of a mechanism, which in turn leads to reduced noise scales that have to be injected. All existing privacy amplification results only hold in the standard, record-level DP model. Recently, user-level differential privacy (user-DP) has gained a lot of attention as it protects all data records contributed by any particular user, thus offering stronger privacy protection. Sampling-based mechanisms under user-DP have not been explored so far, except naively running the mechanism on a sample without privacy amplification, which results in large DP noises. In fact, sampling is in even more demand under user-DP, since all state-of-the-art user-DP mechanisms have high computational costs due to the complex relationships between users and records. In this paper, we take the first step towards the study of privacy amplification by sampling under user-DP, and give the amplification results for two common user-DP sampling strategies: simple sampling and sample-and-explore. The experimental results show that these sampling-based mechanisms can be a useful tool to obtain some quick and reasonably accurate estimates on large private datasets.