Chest X-Ray (CXR) is a widely used clinical imaging modality and has a pivotal role in the diagnosis and prognosis of various lung and heart related conditions. Conventional automated clinical diagnostic tool design strategies relying on radiology reads and supervised learning, entail the cumbersome requirement of high quality annotated training data. To address this challenge, self-supervised pre-training has proven to outperform supervised pre-training in numerous downstream vision tasks, representing a significant breakthrough in the field. However, medical imaging pre-training significantly differs from pre-training with natural images (e.g., ImageNet) due to unique attributes of clinical images. In this context, we introduce Diverse Concept Modeling (DiCoM), a novel self-supervised training paradigm that leverages a student teacher framework for learning diverse concepts and hence effective representation of the CXR data. Hence, expanding beyond merely modeling a single primary label within an image, instead, effectively harnessing the information from all the concepts inherent in the CXR. The pre-trained model is subsequently fine-tuned to address diverse domain-specific tasks. Our proposed paradigm consistently demonstrates robust performance across multiple downstream tasks on multiple datasets, highlighting the success and generalizability of the pre-training strategy. To establish the efficacy of our methods we analyze both the power of learned representations and the speed of convergence (SoC) of our models. For diverse data and tasks, DiCoM is able to achieve in most cases better results compared to other state-of-the-art pre-training strategies. This when combined with the higher SoC and generalization capabilities positions DiCoM to be established as a foundation model for CXRs, a widely used imaging modality.
In modern battlefield scenarios, the reliance on GPS for navigation can be a critical vulnerability. Adversaries often employ tactics to deny or deceive GPS signals, necessitating alternative methods for the localization and navigation of mobile troops. Range-free localization methods such as DV-HOP rely on radio-based anchors and their average hop distance which suffers from accuracy and stability in a dynamic and sparse network topology. Vision-based approaches like SLAM and Visual Odometry use sensor fusion techniques for map generation and pose estimation that are more sophisticated and computationally expensive. This paper proposes a novel framework that integrates landmark-based localization (LanBLoc) with an Extended Kalman Filter (EKF) to predict the future state of moving entities along the battlefield. Our framework utilizes safe trajectory information generated by the troop control center by considering identifiable landmarks and pre-defined hazard maps. It performs point inclusion tests on the convex hull of the trajectory segments to ensure the safety and survivability of a moving entity and determines the next point forward decisions. We present a simulated battlefield scenario for two different approaches (with EKF and without EKF) that guide a moving entity through an obstacle and hazard-free path. Using the proposed method, we observed a percent error of 6.51% lengthwise in safe trajectory estimation with an Average Displacement Error (ADE) of 2.97m and a Final Displacement Error (FDE) of 3.27m. The results demonstrate that our approach not only ensures the safety of the mobile units by keeping them within the secure trajectory but also enhances operational effectiveness by adapting to the evolving threat landscape.
Radio frequency interference (RFI) have been an enduring concern in radio astronomy, particularly for the observations of pulsars which require high timing precision and data sensitivity. In most works of the literature, RFI mitigation has been formulated as a detection task that consists of localizing possible RFI in dynamic spectra. This strategy inevitably leads to a potential loss of information since parts of the signal identified as possibly RFI-corrupted are generally not considered in the subsequent data processing pipeline. Conversely, this work proposes to tackle RFI mitigation as a joint detection and restoration that allows parts of the dynamic spectrum affected by RFI to be not only identified but also recovered. The proposed supervised method relies on a deep convolutional network whose architecture inherits the performance reached by a recent yet popular image-denoising network. To train this network, a whole simulation framework is built to generate large data sets according to physics-inspired and statistical models of the pulsar signals and of the RFI. The relevance of the proposed approach is quantitatively assessed by conducting extensive experiments. In particular, the results show that the restored dynamic spectra are sufficiently reliable to estimate pulsar times-of-arrivals with an accuracy close to the one that would be obtained from RFI-free signals.
Extremely large-scale multiple-input multiple-output (XL-MIMO) systems are capable of improving spectral efficiency by employing far more antennas than conventional massive MIMO at the base station (BS). However, beam training in multiuser XL-MIMO systems is challenging. To tackle these issues, we conceive a three-phase graph neural network (GNN)-based beam training scheme for multiuser XL-MIMO systems. In the first phase, only far-field wide beams have to be tested for each user and the GNN is utilized to map the beamforming gain information of the far-field wide beams to the optimal near-field beam for each user. In addition, the proposed GNN-based scheme can exploit the position-correlation between adjacent users for further improvement of the accuracy of beam training. In the second phase, a beam allocation scheme based on the probability vectors produced at the outputs of GNNs is proposed to address the above beam-direction conflicts between users. In the third phase, the hybrid TBF is designed for further reducing the inter-user interference. Our simulation results show that the proposed scheme improves the beam training performance of the benchmarks. Moreover, the performance of the proposed beam training scheme approaches that of an exhaustive search, despite requiring only about 7% of the pilot overhead.
Despite large successes of recent language models on diverse tasks, they suffer from severe performance degeneration in low-resource settings with limited training data available. Many existing works tackle this problem by generating synthetic data from the training data and then training models on them, recently using Large Language Models (LLMs). However, in low-resource settings, the amount of seed data samples to use for data augmentation is very small, which makes generated samples suboptimal and less diverse. To tackle this challenge, we propose a novel method that augments training data by incorporating a wealth of examples from other datasets, along with the given training data. Specifically, we first retrieve the relevant instances from other datasets, such as their input-output pairs or contexts, based on their similarities with the given seed data, and then prompt LLMs to generate new samples with the contextual information within and across the original and retrieved samples. This approach can ensure that the generated data is not only relevant but also more diverse than what could be achieved using the limited seed data alone. We validate our proposed Retrieval-Augmented Data Augmentation (RADA) framework on multiple datasets under low-resource settings of training and test-time data augmentation scenarios, on which it outperforms existing LLM-powered data augmentation baselines.
This paper introduces an Electric Vehicle Charging Station (EVCS) model that incorporates real-world constraints, such as slot power limitations, contract threshold overruns penalties, or early disconnections of electric vehicles (EVs). We propose a formulation of the problem of EVCS control under uncertainty, and implement two Multi-Stage Stochastic Programming approaches that leverage user-provided information, namely, Model Predictive Control and Two-Stage Stochastic Programming. The model addresses uncertainties in charging session start and end times, as well as in energy demand. A user's behavior model based on a sojourn-time-dependent stochastic process enhances cost reduction while maintaining customer satisfaction. The benefits of the two proposed methods are showcased against two baselines over a 22-day simulation using a real-world dataset. The two-stage approach proves robust against early disconnections, considering a more significant number of uncertainty scenarios for optimization. The algorithm prioritizing user satisfaction over electricity cost achieves a 20% and 36% improvement in two user satisfaction metrics compared to an industry-standard baseline. Additionally, the algorithm striking the best balance between cost and user satisfaction exhibits a mere 3% relative cost increase compared to the theoretically optimal baseline - for which the nonanticipativity constraint is relaxed - while attaining 94% and 84% of the user satisfaction performance in the two used satisfaction metrics.
Lung cancer is a devastating disease with the highest mortality rate among cancer types. Over 60% of non-small cell lung cancer (NSCLC) patients, which accounts for 87% of diagnoses, require radiation therapy. Rapid treatment initiation significantly increases the patient's survival rate and reduces the mortality rate. Accurate tumor segmentation is a critical step in the diagnosis and treatment of NSCLC. Manual segmentation is time and labor-consuming and causes delays in treatment initiation. Although many lung nodule detection methods, including deep learning-based models, have been proposed, there is still a long-standing problem of high false positives (FPs) with most of these methods. Here, we developed an electronic health record (EHR) guided lung tumor auto-segmentation called EXACT-Net (EHR-enhanced eXACtitude in Tumor segmentation), where the extracted information from EHRs using a pre-trained large language model (LLM), was used to remove the FPs and keep the TP nodules only. The auto-segmentation model was trained on NSCLC patients' computed tomography (CT), and the pre-trained LLM was used with the zero-shot learning approach. Our approach resulted in a 250% boost in successful nodule detection using the data from ten NSCLC patients treated in our institution.
It has been said, arguably, that causality analysis should pave a promising way to interpretable deep learning and generalization. Incorporation of causality into artificial intelligence (AI) algorithms, however, is challenged with its vagueness, non-quantitiveness, computational inefficiency, etc. During the past 18 years, these challenges have been essentially resolved, with the establishment of a rigorous formalism of causality analysis initially motivated from atmospheric predictability. This not only opens a new field in the atmosphere-ocean science, namely, information flow, but also has led to scientific discoveries in other disciplines, such as quantum mechanics, neuroscience, financial economics, etc., through various applications. This note provides a brief review of the decade-long effort, including a list of major theoretical results, a sketch of the causal deep learning framework, and some representative real-world applications in geoscience pertaining to this journal, such as those on the anthropogenic cause of global warming, the decadal prediction of El Ni\~no Modoki, the forecasting of an extreme drought in China, among others.
Bayesian neural networks (BNNs) have recently gained popularity due to their ability to quantify model uncertainty. However, specifying a prior for BNNs that captures relevant domain knowledge is often extremely challenging. In this work, we propose a framework for integrating general forms of domain knowledge (i.e., any knowledge that can be represented by a loss function) into a BNN prior through variational inference, while enabling computationally efficient posterior inference and sampling. Specifically, our approach results in a prior over neural network weights that assigns high probability mass to models that better align with our domain knowledge, leading to posterior samples that also exhibit this behavior. We show that BNNs using our proposed domain knowledge priors outperform those with standard priors (e.g., isotropic Gaussian, Gaussian process), successfully incorporating diverse types of prior information such as fairness, physics rules, and healthcare knowledge and achieving better predictive performance. We also present techniques for transferring the learned priors across different model architectures, demonstrating their broad utility across various settings.
Reconfigurable intelligent surfaces (RISs) have demonstrated significant potential for enhancing communication system performance if properly configured. However, a RIS might also pose a risk to the network security. In this letter, we explore the impact of a malicious RIS on a multi-user multiple-input single-output (MISO) system when the system is unaware of the RIS's malicious intentions. The objective of the malicious RIS is to degrade the \ac{SNR} of a specific \ac{UE}, with the option of preserving the SNR of the other UEs, making the attack harder to detect. To achieve this goal, we derive the optimal RIS phase-shift pattern, assuming perfect channel state information (CSI) at the hacker. We then relax this assumption by introducing CSI uncertainties and subsequently determine the RIS's phase-shift pattern using a robust optimization approach. Our simulations reveal a direct proportionality between the performance degradation caused by the malicious RIS and the number of reflective elements, along with resilience toward CSI uncertainties.