arXiv EE and SS @arxiv_eess@qoto.org

This study explores the use of text-prompted MRI image generation with the Stable Diffusion (SD) model to address challenges in acquiring real MRI datasets, such as high costs, limited rare case samples, and privacy concerns. The SD model, pre-trained on natural images, was fine-tuned using the 3T fastMRI dataset and the 0.3T M4Raw dataset, with the goal of generating brain T1, T2, and FLAIR images across different magnetic field strengths. The performance of the fine-tuned model was evaluated using quantitative metrics,including Fréchet Inception Distance (FID) and Multi-Scale Structural Similarity (MS-SSIM), showing improvements in image quality and semantic consistency with the text prompts. To further evaluate the model's potential, a simple classification task was carried out using a small 0.35T MRI dataset, demonstrating that the synthetic images generated by the fine-tuned SD model can effectively augment training datasets and improve the performance of MRI constrast classification tasks. Overall, our findings suggest that text-prompted MRI image generation is feasible and can serve as a useful tool for medical AI applications.

Diffusion MRI (dMRI) tractography enables in vivo mapping of brain structural connections, but traditional connectome generation is time-consuming and requires gray matter parcellation, posing challenges for large-scale studies. We introduce DeepMultiConnectome, a deep-learning model that predicts structural connectomes directly from tractography, bypassing the need for gray matter parcellation while supporting multiple parcellation schemes. Using a point-cloud-based neural network with multi-task learning, the model classifies streamlines according to their connected regions across two parcellation schemes, sharing a learned representation. We train and validate DeepMultiConnectome on tractography from the Human Connectome Project Young Adult dataset ($n = 1000$), labeled with an 84 and 164 region gray matter parcellation scheme. DeepMultiConnectome predicts multiple structural connectomes from a whole-brain tractogram containing 3 million streamlines in approximately 40 seconds. DeepMultiConnectome is evaluated by comparing predicted connectomes with traditional connectomes generated using the conventional method of labeling streamlines using a gray matter parcellation. The predicted connectomes are highly correlated with traditionally generated connectomes ($r = 0.992$ for an 84-region scheme; $r = 0.986$ for a 164-region scheme) and largely preserve network properties. A test-retest analysis of DeepMultiConnectome demonstrates reproducibility comparable to traditionally generated connectomes. The predicted connectomes perform similarly to traditionally generated connectomes in predicting age and cognitive function. Overall, DeepMultiConnectome provides a scalable, fast model for generating subject-specific connectomes across multiple parcellation schemes.

We investigate the end-to-end altitude estimation performance of a convolutional autoencoder-based interference mitigation approach for frequency-modulated continuous-wave (FMCW) radar altimeters. Specifically, we show that a Temporal Convolutional Network (TCN) autoencoder effectively exploits temporal correlations in the received signal, providing superior interference suppression compared to a Least Mean Squares (LMS) adaptive filter. Unlike existing approaches, the present method operates directly on the received FMCW signal. Additionally, we identify key challenges in applying deep learning to wideband FMCW interference mitigation and outline directions for future research to enhance real-time feasibility and generalization to arbitrary interference conditions.

In this paper, we develop and analyze an integral fixed-time sliding mode control method for a scenario in which the system model is only partially known, utilizing Gaussian processes. We present two theorems on fixed-time convergence. The first theorem addresses the fully known system model, while the second considers situations where the system's drift is approximated utilizing Gaussian processes (GP) for approximating unknown dynamics. Both theorems establish the global fixed-time stability of the closed-loop system. The stability analysis is based on a straightforward quadratic Lyapunov function. Our proposed method outperforms an established adaptive fixed-time sliding mode control approach, especially when ample training data is available.

Molecular communication (MC), a biologically inspired technology, enables applications in nanonetworks and the Internet of Everything (IoE), with great potential for intra-body systems such as drug delivery, health monitoring, and disease detection. This paper extends our prior work on the Flexure-FET MC receiver by integrating a competitive binding model to enhance performance in high-interference environments, where multiple molecular species coexist in the reception space. Previous studies have largely focused on ligand concentration estimation and detection, without fully addressing the effects of inter-species competition for receptor binding. Our proposed framework captures this competition, offering a more biologically accurate model for multitarget environments. By incorporating competition dynamics, the model improves understanding of MC behavior under interference. This approach enables fine-tuning of receptor responses by adjusting ligand concentrations and receptor affinities, thereby optimizing the performance of the Flexure-FET MC receiver. Comprehensive analysis shows that accounting for competitive binding is crucial for improving reliability and accuracy in complex MC systems. Factors such as signal-to-noise ratio (SNR), symbol error probability (SEP), interferer concentration, and receptor dynamics are shown to significantly affect performance. The proposed framework highlights the need to manage these factors effectively. Results demonstrate that modeling interference through competitive binding offers a realistic system perspective and allows tuning of receiver response, enabling robust detection in environments with multiple coexisting species.

Statistical n-gram language models are widely used for context-biasing tasks in Automatic Speech Recognition (ASR). However, existing implementations lack computational efficiency due to poor parallelization, making context-biasing less appealing for industrial use. This work rethinks data structures for statistical n-gram language models to enable fast and parallel operations for GPU-optimized inference. Our approach, named NGPU-LM, introduces customizable greedy decoding for all major ASR model types - including transducers, attention encoder-decoder models, and CTC - with less than 7% computational overhead. The proposed approach can eliminate more than 50% of the accuracy gap between greedy and beam search for out-of-domain scenarios while avoiding significant slowdown caused by beam search. The implementation of the proposed NGPU-LM is open-sourced.

We study the local stability of nonlinear systems in the Lur'e form with static nonlinear feedback realized by feedforward neural networks (FFNNs). By leveraging positivity system constraints, we employ a localized variant of the Aizerman conjecture, which provides sufficient conditions for exponential stability of trajectories confined to a compact set. Using this foundation, we develop two distinct methods for estimating the Region of Attraction (ROA): (i) a less conservative Lyapunov-based approach that constructs invariant sublevel sets of a quadratic function satisfying a linear matrix inequality (LMI), and (ii) a novel technique for computing tight local sector bounds for FFNNs via layer-wise propagation of linear relaxations. These bounds are integrated into the localized Aizerman framework to certify local exponential stability. Numerical results demonstrate substantial improvements over existing integral quadratic constraint-based approaches in both ROA size and scalability.

We introduce Blind Plug-and-Play Diffusion Models (Blind-PnPDM) as a novel framework for solving blind inverse problems where both the target image and the measurement operator are unknown. Unlike conventional methods that rely on explicit priors or separate parameter estimation, our approach performs posterior sampling by recasting the problem into an alternating Gaussian denoising scheme. We leverage two diffusion models as learned priors: one to capture the distribution of the target image and another to characterize the parameters of the measurement operator. This PnP integration of diffusion models ensures flexibility and ease of adaptation. Our experiments on blind image deblurring show that Blind-PnPDM outperforms state-of-the-art methods in terms of both quantitative metrics and visual fidelity. Our results highlight the effectiveness of treating blind inverse problems as a sequence of denoising subproblems while harnessing the expressive power of diffusion-based priors.

Custom keyword spotting (KWS) allows detecting user-defined spoken keywords from streaming audio. This is achieved by comparing the embeddings from voice enrollments and input audio. State-of-the-art custom KWS models are typically trained contrastively using utterances whose keywords are randomly sampled from training dataset. These KWS models often struggle with confusing keywords, such as "blue" versus "glue". This paper introduces an effective way to augment the training with confusable utterances where keywords are generated and grouped from large language models (LLMs), and speech signals are synthesized with diverse speaking styles from text-to-speech (TTS) engines. To better measure user experience on confusable KWS, we define a new northstar metric using the average area under DET curve from confusable groups (c-AUC). Featuring high scalability and zero labor cost, the proposed method improves AUC by 3.7% and c-AUC by 11.3% on the Speech Commands testing set.

Geomagnetic disturbances are a threat to the reliability and security of our national critical energy infrastructures. These events specifically result in geomagnetically induced currents, which can cause damage to transformers due to magnetic saturation. In order to mitigate these effects, blocker devices must be placed in optimal locations. Finding this placement requires a dc representation of the ac transmission lines, which this paper discusses. Different decisions in this process, including the method of representing the blocking devices, result in significant variations to the power loss calculations. To analyze these effects, we conclude the paper by comparing the losses on a sample network with different modeling implementations.

Artificial intelligence advances have recently influenced wireless communications, including beam management in fifth-generation (5G) new radio systems. AI-driven models and algorithms are being applied to enhance tasks such as beam selection, prediction, and refinement by leveraging real-time and historical data. These approaches address challenges such as mobility under complex channel conditions, showing promising results compared to traditional methods. Beam management in 5G refers to processes that ensure optimal alignment between the base station and user equipment for effective signal transmission and reception based on real-time channel state information and user positioning. This study leverages accurate beam prediction to identify a smaller subset of beams, resulting in a more efficient, streamlined, and link-adaptive communication system. The innovative approach presented introduces a precise, attention-based prediction model that derives the entire downlink transmission chain in a commercial grade 5G system. The predicted downlink beams are specifically tailored to handle the complexities of none line-of-sight environments known for high-dimensional channel dynamics and scatterer-induced signal variations. This novel method introduces a paradigm shift in utilizing environmental and channel dynamics in contrast to conventional procedures of beam management, which entails complex methods involving exhaustive techniques to predict the best beams. The presented beam prediction results demonstrate robustness in addressing the challenges posed by signal-dispersive environments, showcasing great potential in mobility scenarios.

The performance of battery materials is determined by their composition and the processing conditions employed during commercial-scale fabrication, where raw materials undergo complex processing steps with various additives to yield final products. As the complexity of these parameters expands with the development of industry, conventional one-factor-at-a-time (OFAT) experiment becomes old fashioned. While domain expertise aids in parameter optimization, this traditional approach becomes increasingly vulnerable to cognitive limitations and anthropogenic biases as the complexity of factors grows. Herein, we introduce an iterative machine learning (ML) framework that integrates active learning to guide targeted experimentation and facilitate incremental model refinement. This method systematically leverages comprehensive experimental observations, including both successful and unsuccessful results, effectively mitigating human-induced biases and alleviating data scarcity. Consequently, it significantly accelerates exploration within the high-dimensional design space. Our results demonstrate that active-learning-driven experimentation markedly reduces the total number of experimental cycles necessary, underscoring the transformative potential of ML-based strategies in expediting battery material optimization.

This paper proposes a novel multi-antenna architecture, termed ray antenna array (RAA), which aims to enhance wireless communication performance in a cost-effective manner. RAA is composed of massive cheap antenna elements and a few radio frequency (RF) chains. The massive antenna elements are arranged in a novel ray-like structure, with each ray corresponding to a simple uniform linear array (sULA) with a carefully designed orientation. The antenna elements of each sULA are directly connected to an RF combiner, so that the sULA in each ray is able to form a beam towards a direction matching the ray orientation without relying on any analog or digital beamforming. By further designing a ray selection network (RSN), appropriate sULAs are selected to connect to the RF chains for further baseband processing. Compared to conventional multi-antenna architectures like hybrid analog/digital beamforming (HBF), the proposed RAA has two major advantages. First, it can significantly reduce hardware costs since no phase shifters, which are usually expensive especially in high-frequency systems, are required. Besides, RAA can greatly improve system performance by configuring antenna elements with higher directionality, as each sULA only needs to be responsible for a portion of the total coverage angle. To demonstrate such advantages, in this paper, we first present the input-output model for RAA-based wireless communications, based on which the ray orientations of the RAA are designed. Furthermore, efficient algorithms for joint ray selection and beamforming are proposed for single-user and multi-user RAA-based wireless communications. Simulation results demonstrate the superior performance of RAA compared to HBF while significantly reducing hardware cost.

Heart rate (HR) and heart rate variability (HRV) are important vital signs for human physical and mental health. Recent research has demonstrated that photoplethysmography (PPG) sensors can infer HR and HRV. However, it is difficult to find a comprehensive PPG-based dataset for HR/HRV studies, especially for various study needs: multiple scenes, long-term monitoring, and multimodality (multiple PPG channels and extra acceleration data). In this study, we collected a comprehensive multimodal long-term dataset to address the gap of missing an all-in-one HR/HRV dataset (denoted as UTSA-PPG). We began by reviewing state-of-the-art datasets, emphasizing their strengths and limitations. Following this, we developed a custom data acquisition system and then collected the UTSA-PPG dataset and compared its key features with those of existing datasets. Additionally, five case studies were conducted, including comparisons with state-of-the-art datasets. The outcomes highlight the value of our dataset, demonstrating its utility for HR/HRV estimation exploration and its potential to aid researchers in creating generalized models for targeted research challenges.

We propose a dim and small target detection algorithm for drone broadcast frames based on the time-frequency analysis of communication protocol. Specifically, by analyzing modulation parameters and frame structures, the prior knowledge of transmission frequency, signal bandwidth, Zadoff-Chu (ZC) sequences, and frame length of drone broadcast frames is established. The RF signals are processed through the designed filter banks, and the frequency domain parameters of bounding boxes generated by the detector are corrected with transmission frequency and signal bandwidth. Given the remarkable correlation characteristics of ZC sequences, the frequency domain parameters of bounding boxes with low confidence scores are corrected based on ZC sequences and frame length, which improves the detection accuracy of dim targets under low signal-to noise ratio (SNR) situations. Besides, a segmented energy refinement method is applied to mitigate the deviation caused by interference signals with high energy strength, which ulteriorly corrects the time domain detection parameters for dim targets. As the sampling duration increases, the detection speed improves while the detection accuracy of broadcast frames termed as small targets decreases. The trade-off between detection accuracy and speed versus sampling duration is established, which helps to meet different drone regulation requirements. Simulation results demonstrate that the proposed algorithm improves the average intersection over union, precision, and recall by 3\%, 1.4\%, and 2.4\%, respectively, compared to existing algorithms. The proposed algorithm also performs strong robustness under varying flight distances, diverse types of environment noise, and different flight visual environment.

Electric energy is difficult to store, requiring stricter control over its generation, transmission, and distribution. A persistent challenge in power systems is maintaining real-time equilibrium between electricity demand and supply. Oversupply contributes to resource wastage, while undersupply can strain the grid, increase operational costs, and potentially impact service reliability. To maintain grid stability, load forecasting is needed. Accurate load forecasting balances generation and demand by striving to predict future electricity consumption. This thesis examines and evaluates four machine learning frameworks for short term load forecasting, including gradient boosting decision tree methods such as Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM). A hybrid framework is also developed. In addition, two recurrent neural network architectures, Long Short Term Memory (LSTM) networks and Gated Recurrent Units (GRU), are designed and implemented. Pearson Correlation Coefficient is applied to assess the relationships between electricity demand and exogenous variables. The experimental results show that, for the specific dataset and forecasting task in this study, machine learning-based models achieved improved forecasting performance compared to a classical ARIMA baseline.

This dissertation proposes an electrocardiogram (ECG) tracking device that diagnoses cardiopulmonary problems using the Internet of Things (IoT) desired results. The initiative is built on the internet observing an electrocardiogram with the AD8232 heart rhythm sensor and the ESP32 expansion kit, using an on-premise connected device platform to transform sensing input into meaningful data. That subsequently supervises an ECG signal and delivers it to an intelligent phone via Wi-Fi for data analysis. That is the pace of the circulating. Assessing body temperature, pulse rate, and coronary arteries are vital measures to defend your health. The heartbeat rate may be measured in two ways: there are by palpating the pulse at the wrist or neck directly or other alternative by utilizing a cardiac sensor. Monitoring alcohol levels in cardiac patients is critical for measuring the influence of liquor on their health and the efficacy of therapy. It assists in recognizing the association between alcohol consumption and cardiac issues, rather than rhythm recorded in beats per minute (bpm). An IR transmitter/receiver pair (OLED) needs to stay compatible up near the sensor's knuckle current or voltage pulse. The detector's electrical output is evaluated by suitable electronic circuits to produce a visual clue (digital display). We must design a cost-effective, user-friendly, and efficient ECG monitoring system with contemporary technology for both persons imprisoned by disease or aging, as well as healthcare professionals. Microcontroller combined with software. A smartphone application is created to monitor the cardiovascular health of distant patients in real-time

Electrocardiogram (ECG) and Phonocardiogram (PCG) signals are linked by a latent coupling signal representing the electrical-to-mechanical cardiac transformation. While valuable for cardiovascular disease (CVD) detection, this coupling signal is traditionally estimated using deconvolution methods that amplify noise, limiting clinical utility. In this paper, we propose Noise-Robust Multi-Modal Coupling Signal Estimation (NMCSE), which reformulates the problem as distribution matching via optimal transport theory. By jointly optimizing amplitude and temporal alignment, NMCSE mitigates noise amplification without additional preprocessing. Integrated with our Temporal-Spatial Feature Extraction network, NMCSE enables robust multi-modal CVD detection. Experiments on the PhysioNet 2016 dataset with realistic hospital noise demonstrate that NMCSE reduces estimation errors by approximately 30% in Mean Squared Error while maintaining higher Pearson Correlation Coefficients across all tested signal-to-noise ratios. Our approach achieves 97.38% accuracy and 0.98 AUC in CVD detection, outperforming state-of-the-art methods and demonstrating robust performance for real-world clinical applications.

Electroencephalography-based Emotion Recognition (EEG-ER) has become a growing research area in recent years. Analyzing 216 papers published between 2018 and 2023, we uncover that the field lacks a unified evaluation protocol, which is essential to fairly define the state of the art, compare new approaches and to track the field's progress. We report the main inconsistencies between the used evaluation protocols, which are related to ground truth definition, evaluation metric selection, data splitting types (e.g., subject-dependent or subject-independent) and the use of different datasets. Capitalizing on this state-of-the-art research, we propose a unified evaluation protocol, EEGain (https://github.com/EmotionLab/EEGain), which enables an easy and efficient evaluation of new methods and datasets. EEGain is a novel open source software framework, offering the capability to compare - and thus define - state-of-the-art results. EEGain includes standardized methods for data pre-processing, data splitting, evaluation metrics, and the ability to load the six most relevant datasets (i.e., AMIGOS, DEAP, DREAMER, MAHNOB-HCI, SEED, SEED-IV) in EEG-ER with only a single line of code. In addition, we have assessed and validated EEGain using these six datasets on the four most common publicly available methods (EEGNet, DeepConvNet, ShallowConvNet, TSception). This is a significant step to make research on EEG-ER more reproducible and comparable, thereby accelerating the overall progress of the field.

Objective: To conduct a systematic assessment of machine learning applications that utilize electrocardiogram (ECG) and heart sound data in the development of cost-effective detection tools for rheumatic heart disease (RHD) from the year 2015 to 2025, thereby supporting the World Heart Federation's "25 by 25" mortality reduction objective through the creation of alternatives to echocardiography in underserved regions. Methods: Following PRISMA-ScR guidelines, we conducted a comprehensive search across PubMed, IEEE Xplore, Scopus, and Embase for peer-reviewed literature focusing on ML-based ECG/PCG analysis for RHD detection. Two independent reviewers screened studies, and data extraction focused on methodology, validation approaches, and performance metrics. Results: Analysis of 37 relevant studies revealed that convolutional neural networks (CNNs) have become the predominant technology in post-2020 implementations, achieving a median accuracy of 93.7%. However, 73% of studies relied on single-center datasets, only 10.8% incorporated external validation, and none addressed cost-effectiveness. Performance varied markedly across different valvular lesions, and despite 44% of studies originating from endemic regions, significant gaps persisted in implementation science and demographic diversity. Conclusion: While ML-based ECG/PCG analysis shows promise for RHD detection, substantial methodological limitations hinder clinical translation. Future research must prioritize standardized benchmarking frameworks, multimodal architectures, cost-effectiveness assessments, and prospective trials in endemic settings. Significance: This review provides a critical roadmap for developing accessible ML-based RHD screening tools to help bridge the diagnostic gap in resourceconstrained settings where conventional auscultation misses up to 90% of cases and echocardiography remains inaccessible.