Search

High-resolution phase-contrast 3D imaging using nano-holotomography typically requires collecting multiple tomograms at varying sample-to-detector distances, usually 3 to 4. This multi-distance approach significantly limits temporal resolution, making it impractical for operando studies. Moreover, shifting the sample complicates reconstruction, requiring precise alignment and interpolation to correct for shift-dependent magnification on the detector. In response, we propose and validate through simulations a novel single-distance approach that leverages coded apertures to structure beam illumination while the sample rotates. This approach is made possible by our proposed joint reconstruction scheme, which integrates coded phase retrieval with 3D tomography. This scheme ensures data consistency and achieves artifact-free reconstructions from a single distance.

This study develops a Convolutional Neural Network (CNN) model for detecting myocardial infarction (MI) from Electrocardiogram (ECG) images. The model, built using the InceptionV3 architecture and optimized through transfer learning, was trained using ECG data obtained from the Ch. Pervaiz Elahi Institute of Cardiology in Pakistan. The dataset includes ECG images representing four different cardiac conditions: myocardial infarction, abnormal heartbeat, history of myocardial infarction, and normal heart activity. The developed model successfully detects MI and other cardiovascular conditions with an accuracy of 93.27%. This study demonstrates that deep learning-based models can provide significant support to clinicians in the early detection and prevention of heart attacks., Comment: 4 pages

Local differential privacy (LDP) has recently emerged as a popular privacy standard. With the growing popularity of LDP, several recent works have applied LDP to spatial data, and grid-based decompositions have been a common building block in the collection and analysis of spatial data under DP and LDP. In this paper, we study three grid-based decomposition methods for spatial data under LDP: Uniform Grid (UG), PrivAG, and AAG. UG is a static approach that consists of equal-sized cells. To enable data-dependent decomposition, PrivAG was proposed by Yang et al. as the most recent adaptive grid method. To advance the state-of-the-art in adaptive grids, in this paper we propose the Advanced Adaptive Grid (AAG) method. For each grid cell, following the intuition that the cell's intra-cell density distribution will be affected by its neighbors, AAG performs uneven cell divisions depending on the neighboring cells' densities. We experimentally compare UG, PrivAG, and AAG using three real-world location datasets, varying privacy budgets, and query sizes. Results show that AAG provides higher utility than PrivAG, demonstrating the superiority of our proposed approach. Furthermore, UG's performance is heavily dependent on the choice of grid size. When the grid size is chosen optimally in UG, AAG still beats UG for small queries, but UG beats AAG for large (coarse-grained) queries.

In conventional tomographic reconstruction, the pre-processing step includes flat-field correction, where each sample projection on the detector is divided by a reference image taken without the sample. When using coherent X-rays as probe, this approach overlooks the phase component of the illumination field (probe), leading to artifacts in phase-retrieved projection images, which are then propagated to the reconstructed 3D sample representation. The problem intensifies in nano-holotomography with focusing optics, that due to various imperfections create high-frequency components in the probe function. Here, we present a new iterative reconstruction scheme for holotomography, simultaneously retrieving the complex-valued probe function. Implemented on GPUs, this algorithm results in 3D reconstruction resolving twice thinner layers in a 3D ALD standard sample measured using nano-holotomography.

In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated learning and federated transfer learning. Specifically, in the proposed feature-based federated learning, we design the extracted features and outputs to be uploaded instead of parameter updates. For this distributed learning model, we determine the required payload and provide comparisons with the existing schemes. Subsequently, we analyze the robustness of feature-based federated transfer learning against packet loss, data insufficiency, and quantization. Finally, we address privacy considerations by defining and analyzing label privacy leakage and feature privacy leakage, and investigating mitigating approaches. For all aforementioned analyses, we evaluate the performance of the proposed learning scheme via experiments on an image classification task and a natural language processing task to demonstrate its effectiveness., Comment: Accepted by IEEE Transactions on Machine Learning in Communications and Networking. arXiv admin note: text overlap with arXiv:2209.05395

Federated Learning is increasingly used in domains such as healthcare to facilitate collaborative model training without data-sharing. However, datasets located in different sites are often non-identically distributed, leading to degradation of model performance in FL. Most existing methods for assessing these distribution shifts are limited by being dataset or task-specific. Moreover, these metrics can only be calculated by exchanging data, a practice restricted in many FL scenarios. To address these challenges, we propose a novel metric for assessing dataset similarity. Our metric exhibits several desirable properties for FL: it is dataset-agnostic, is calculated in a privacy-preserving manner, and is computationally efficient, requiring no model training. In this paper, we first establish a theoretical connection between our metric and training dynamics in FL. Next, we extensively evaluate our metric on a range of datasets including synthetic, benchmark, and medical imaging datasets. We demonstrate that our metric shows a robust and interpretable relationship with model performance and can be calculated in privacy-preserving manner. As the first federated dataset similarity metric, we believe this metric can better facilitate successful collaborations between sites.

The third ML4H symposium was held in person on December 10, 2023, in New Orleans, Louisiana, USA. The symposium included research roundtable sessions to foster discussions between participants and senior researchers on timely and relevant topics for the \ac{ML4H} community. Encouraged by the successful virtual roundtables in the previous year, we organized eleven in-person roundtables and four virtual roundtables at ML4H 2022. The organization of the research roundtables at the conference involved 17 Senior Chairs and 19 Junior Chairs across 11 tables. Each roundtable session included invited senior chairs (with substantial experience in the field), junior chairs (responsible for facilitating the discussion), and attendees from diverse backgrounds with interest in the session's topic. Herein we detail the organization process and compile takeaways from these roundtable discussions, including recent advances, applications, and open challenges for each topic. We conclude with a summary and lessons learned across all roundtables. This document serves as a comprehensive review paper, summarizing the recent advancements in machine learning for healthcare as contributed by foremost researchers in the field., Comment: ML4H 2023, Research Roundtables

Nanoscale structural and electronic heterogeneities are prevalent in condensed matter physics. Investigating these heterogeneities in three dimensions (3D) has become an important task for understanding their material properties. To provide a tool to unravel the connection between nanoscale heterogeneity and macroscopic emergent properties in magnetic materials, scanning transmission X-ray microscopy (STXM) is combined with X-ray magnetic circular dichroism (XMCD). A vector tomography algorithm has been developed to reconstruct the full 3D magnetic vector field without any prior assumptions or knowledge. 2D STXM projections of single crystalline \ndfeb\ pillars are recorded for two different sample tilt angles while rotating around the vertical tomographic axis using $120$ nm X-ray beams with left and right circular polarization. Image alignment and iterative registration has been implemented, based on the 2D STXM projections for the two tilts. Dichroic projections obtained from difference images are used for the tomographic reconstruction to obtain the 3D magnetization distribution at the nanoscale., Comment: 10 pages, 8 figures

Unmanned aerial vehicle (UAV)-based networks and Internet of Things (IoT) are being considered as integral components of current and next-generation wireless networks. In particular, UAVs can provide IoT devices with seamless connectivity and high coverage and this can be accomplished with effective UAV path planning. In this article, we study robust and decentralized UAV path planning for data collection in IoT networks in the presence of other noncooperative UAVs and adversarial jamming attacks. We address three different practical scenarios, including single UAV path planning, UAV swarm path planning, and single UAV path planning in the presence of an intelligent mobile UAV jammer. We advocate a reinforcement learning framework for UAV path planning in these three scenarios under practical constraints. The simulation results demonstrate that with learning-based path planning, the UAVs can complete their missions with high success rates and data collection rates. In addition, the UAVs can adapt and execute different trajectories as a defensive measure against the intelligent jammer., Comment: 7 pages, 5 figures

Unmanned aerial vehicles (UAVs) are expected to be an integral part of wireless networks, and determining collision-free trajectory in multi-UAV non-cooperative scenarios while collecting data from distributed Internet of Things (IoT) nodes is a challenging task. In this paper, we consider a path planning optimization problem to maximize the collected data from multiple IoT nodes under realistic constraints. The considered multi-UAV non-cooperative scenarios involve random number of other UAVs in addition to the typical UAV, and UAVs do not communicate or share information among each other. We translate the problem into a Markov decision process (MDP) with parameterized states, permissible actions, and detailed reward functions. Dueling double deep Q-network (D3QN) is proposed to learn the decision making policy for the typical UAV, without any prior knowledge of the environment (e.g., channel propagation model and locations of the obstacles) and other UAVs (e.g., their missions, movements, and policies). The proposed algorithm can adapt to various missions in various scenarios, e.g., different numbers and positions of IoT nodes, different amount of data to be collected, and different numbers and positions of other UAVs. Numerical results demonstrate that real-time navigation can be efficiently performed with high success rate, high data collection rate, and low collision rate., Comment: The final version of this paper has been accepted in IEEE Internet of Things Journal

Federated learning (FL) is a framework which allows multiple users to jointly train a global machine learning (ML) model by transmitting only model updates under the coordination of a parameter server, while being able to keep their datasets local. One key motivation of such distributed frameworks is to provide privacy guarantees to the users. However, preserving the users' datasets locally is shown to be not sufficient for privacy. Several differential privacy (DP) mechanisms have been proposed to provide provable privacy guarantees by introducing randomness into the framework, and majority of these mechanisms rely on injecting additive noise. FL frameworks also face the challenge of communication efficiency, especially as machine learning models grow in complexity and size. Quantization is a commonly utilized method, reducing the communication cost by transmitting compressed representation of the underlying information. Although there have been several studies on DP and quantization in FL, the potential contribution of the quantization method alone in providing privacy guarantees has not been extensively analyzed yet. We in this paper present a novel stochastic quantization method, utilizing a mixed geometric distribution to introduce the randomness needed to provide DP, without any additive noise. We provide convergence analysis for our framework and empirically study its performance.

In this paper, we address the problem of detecting anomalies among a given set of binary processes via learning-based controlled sensing. Each process is parameterized by a binary random variable indicating whether the process is anomalous. To identify the anomalies, the decision-making agent is allowed to observe a subset of the processes at each time instant. Also, probing each process has an associated cost. Our objective is to design a sequential selection policy that dynamically determines which processes to observe at each time with the goal to minimize the delay in making the decision and the total sensing cost. We cast this problem as a sequential hypothesis testing problem within the framework of Markov decision processes. This formulation utilizes both a Bayesian log-likelihood ratio-based reward and an entropy-based reward. The problem is then solved using two approaches: 1) a deep reinforcement learning-based approach where we design both deep Q-learning and policy gradient actor-critic algorithms; and 2) a deep active inference-based approach. Using numerical experiments, we demonstrate the efficacy of our algorithms and show that our algorithms adapt to any unknown statistical dependence pattern of the processes.

In this paper, we present a multi-agent deep reinforcement learning (deep RL) framework for network slicing in a dynamic environment with multiple base stations and multiple users. In particular, we propose a novel deep RL framework with multiple actors and centralized critic (MACC) in which actors are implemented as pointer networks to fit the varying dimension of input. We evaluate the performance of the proposed deep RL algorithm via simulations to demonstrate its effectiveness. Subsequently, we develop a deep RL based jammer with limited prior information and limited power budget. The goal of the jammer is to minimize the transmission rates achieved with network slicing and thus degrade the network slicing agents' performance. We design a jammer with both listening and jamming phases and address jamming location optimization as well as jamming channel optimization via deep RL. We evaluate the jammer at the optimized location, generating interference attacks in the optimized set of channels by switching between the jamming phase and listening phase. We show that the proposed jammer can significantly reduce the victims' performance without direct feedback or prior knowledge on the network slicing policies. Finally, we devise a Nash-equilibrium-supervised policy ensemble mixed strategy profile for network slicing (as a defensive measure) and jamming. We evaluate the performance of the proposed policy ensemble algorithm by applying on the network slicing agents and the jammer agent in simulations to show its effectiveness., Comment: Published in IEEE Transactions on Machine Learning in Communications and Networking (TMLCN)

We take a step toward a "microscopic" derivation of gauge-string duality. In particular, using mathematical techniques of Strebel differentials and discrete exterior calculus, we obtain a bosonic string worldsheet action for a string embedded in d+1 dimensional asymptotically AdS space from multi-loop Feynman graphs of a quantum field theory of scalar matrices in d-dimensions in the limit of diverging loop number. Our work is building on the program started by 't Hooft in 1974, this time including the holographic dimension which we show to emerge from the continuum of Schwinger parameters of Feynman diagrams., Comment: 5 pages + supplementary material, 4 figures

Federated learning (FL) aims at keeping client data local to preserve privacy. Instead of gathering the data itself, the server only collects aggregated gradient updates from clients. Following the popularity of FL, there has been considerable amount of work, revealing the vulnerability of FL approaches by reconstructing the input data from gradient updates. Yet, most existing works assume an FL setting with unrealistically small batch size, and have poor image quality when the batch size is large. Other works modify the neural network architectures or parameters to the point of being suspicious, and thus, can be detected by clients. Moreover, most of them can only reconstruct one sample input from a large batch. To address these limitations, we propose a novel and completely analytical approach, referred to as the maximum knowledge orthogonality reconstruction (MKOR), to reconstruct clients' input data. Our proposed method reconstructs a mathematically proven high quality image from large batches. MKOR only requires the server to send secretly modified parameters to clients and can efficiently and inconspicuously reconstruct the input images from clients' gradient updates. We evaluate MKOR's performance on the MNIST, CIFAR-100, and ImageNet dataset and compare it with the state-of-the-art works. The results show that MKOR outperforms the existing approaches, and draws attention to a pressing need for further research on the privacy protection of FL so that comprehensive defense approaches can be developed., Comment: Accepted in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024

Federated Learning (FL) is a machine learning framework that enables multiple organizations to train a model without sharing their data with a central server. However, it experiences significant performance degradation if the data is non-identically independently distributed (non-IID). This is a problem in medical settings, where variations in the patient population contribute significantly to distribution differences across hospitals. Personalized FL addresses this issue by accounting for site-specific distribution differences. Clustered FL, a Personalized FL variant, was used to address this problem by clustering patients into groups across hospitals and training separate models on each group. However, privacy concerns remained as a challenge as the clustering process requires exchange of patient-level information. This was previously solved by forming clusters using aggregated data, which led to inaccurate groups and performance degradation. In this study, we propose Privacy-preserving Community-Based Federated machine Learning (PCBFL), a novel Clustered FL framework that can cluster patients using patient-level data while protecting privacy. PCBFL uses Secure Multiparty Computation, a cryptographic technique, to securely calculate patient-level similarity scores across hospitals. We then evaluate PCBFL by training a federated mortality prediction model using 20 sites from the eICU dataset. We compare the performance gain from PCBFL against traditional and existing Clustered FL frameworks. Our results show that PCBFL successfully forms clinically meaningful cohorts of low, medium, and high-risk patients. PCBFL outperforms traditional and existing Clustered FL frameworks with an average AUC improvement of 4.3% and AUPRC improvement of 7.8%.

As artificial intelligence plays an increasingly substantial role in decisions affecting humans and society, the accountability of automated decision systems has been receiving increasing attention from researchers and practitioners. Fairness, which is concerned with eliminating unjust treatment and discrimination against individuals or sensitive groups, is a critical aspect of accountability. Yet, for evaluating fairness, there is a plethora of fairness metrics in the literature that employ different perspectives and assumptions that are often incompatible. This work focuses on group fairness. Most group fairness metrics desire a parity between selected statistics computed from confusion matrices belonging to different sensitive groups. Generalizing this intuition, this paper proposes a new equal confusion fairness test to check an automated decision system for fairness and a new confusion parity error to quantify the extent of any unfairness. To further analyze the source of potential unfairness, an appropriate post hoc analysis methodology is also presented. The usefulness of the test, metric, and post hoc analysis is demonstrated via a case study on the controversial case of COMPAS, an automated decision system employed in the US to assist judges with assessing recidivism risks. Overall, the methods and metrics provided here may assess automated decision systems' fairness as part of a more extensive accountability assessment, such as those based on the system accountability benchmark.

Can robots mold soft plastic materials by shaping depth images? The short answer is no: current day robots can't. In this article, we address the problem of shaping plastic material with an anthropomorphic arm/hand robot, which observes the material with a fixed depth camera. Robots capable of molding could assist humans in many tasks, such as cooking, scooping or gardening. Yet, the problem is complex, due to its high-dimensionality at both perception and control levels. To address it, we design three alternative data-based methods for predicting the effect of robot actions on the material. Then, the robot can plan the sequence of actions and their positions, to mold the material into a desired shape. To make the prediction problem tractable, we rely on two original ideas. First, we prove that under reasonable assumptions, the shaping problem can be mapped from point cloud to depth image space, with many benefits (simpler processing, no need for registration, lower computation time and memory requirements). Second, we design a novel, simple metric for quickly measuring the distance between two depth images. The metric is based on the inherent point cloud representation of depth images, which enables direct and consistent comparison of image pairs through a non-uniform scaling approach, and therefore opens promising perspectives for designing \textit{depth image -- based} robot controllers. We assess our approach in a series of unprecedented experiments, where a robotic arm/hand molds flour from initial to final shapes, either with its own dataset, or by transfer learning from a human dataset. We conclude the article by discussing the limitations of our framework and those of current day hardware, which make human-like robot molding a challenging open research problem., Comment: Accepted to IEEE Transactions on Robotics (T-RO)

Interest in agricultural robotics has increased considerably in recent years due to benefits such as improvement in productivity and labor reduction. However, current problems associated with unstructured environments make the development of robotic harvesters challenging. Most research in agricultural robotics focuses on single arm manipulation. Here, we propose a dual-arm approach. We present a dual-arm fruit harvesting robot equipped with a RGB-D camera, cutting and collecting tools. We exploit the cooperative task description to maximize the capabilities of the dual-arm robot. We designed a Hierarchical Quadratic Programming based control strategy to fulfill the set of hard constrains related to the robot and environment: robot joint limits, robot self-collisions, robot-fruit and robot-tree collisions. We combine deep learning and standard image processing algorithms to detect and track fruits as well as the tree trunk in the scene. We validate our perception methods on real-world RGB-D images and our control method on simulated experiments., Comment: Accepted to IEEE International Conference on Automation Science and Engineering (CASE) 2023

Memory designs require timing margins to compensate for aging and fabrication process variations. With technology downscaling, aging mechanisms became more apparent, and larger margins are considered necessary. This, in return, means a larger area requirement and lower performance for the memory. Bias Temperature Instability (BTI) is one of the main contributors to aging, which slows down transistors and ultimately causes permanent faults. In this paper, first, we propose a low-cost aging mitigation scheme, which can be applied to existing hardware to mitigate aging on memory address decoder logic. We mitigate the BTI effect on critical transistors by applying a rejuvenation workload to the memory. Such an auxiliary workload is executed periodically to rejuvenate transistors that are located on critical paths of the address decoder. Second, we analyze workloads' efficiency to optimize the mitigation scheme. Experimental results performed with realistic benchmarks demonstrate several-times lifetime extension with a negligible execution overhead., Comment: 2022 IEEE 23rd Latin American Test Symposium (LATS)