arXiv EE and SS @arxiv_eess@qoto.org

The 3rd AI Olympics with RealAIGym competition poses the challenge of developing a global policy that can swing up and stabilize an underactuated 2-link system Acrobot and/or Pendubot from any configuration in the state space. This paper presents an optimal control-based approach using a real-time Nonlinear Model Predictive Control (MPC). The results show that the controller achieves good performance and robustness and can reliably handle disturbances.

Physics-informed machine learning (PIML) provides a promising solution for building energy modeling and can serve as a virtual environment to enable reinforcement learning (RL) agents to interact and learn. However, challenges remain in efficiently integrating physics priors, evaluating the effectiveness of physics constraints, balancing model accuracy and physics consistency, and enabling real-world implementation. To address these gaps, this study introduces a Physics-Informed Modularized Neural Network (PI-ModNN), which incorporates physics priors through a physics-informed model structure, loss functions, and hard constraints. A new evaluation metric called "temperature response violation" is developed to quantify the physical consistency of data-driven building dynamic models under varying control inputs and training data sizes. Additionally, a physics prior evaluation framework based on rule importance is proposed to assess the contribution of each individual physics prior, offering guidance on selecting appropriate PIML techniques. Results indicate that incorporating physical priors does not always improve model performance; inappropriate priors may decrease model accuracy and consistency. However, hard constraints are effective in enforcing model consistency. Furthermore, we present a general workflow for developing control-oriented PIML models and integrating them with deep reinforcement learning (DRL). Following this framework, a case study implementing DRL in an office space over three months demonstrates potential energy savings of 31.4%. Finally, we provide a general guideline for integrating data-driven models with advanced building control through a four-step evaluation framework, paving the way for reliable and scalable deployment of advanced building controls.

DNA methylation is an epigenetic mechanism that regulates gene expression by adding methyl groups to DNA. Abnormal methylation patterns can disrupt gene expression and have been linked to cancer development. To quantify DNA methylation, specialized assays are typically used. However, these assays are often costly and have lengthy processing times, which limits their widespread availability in routine clinical practice. In contrast, whole slide images (WSIs) for the majority of cancer patients can be more readily available. As such, given the ready availability of WSIs, there is a compelling need to explore the potential relationship between WSIs and DNA methylation patterns. To address this, we propose an end-to-end graph neural network based weakly supervised learning framework to predict the methylation state of gene groups exhibiting coherent patterns across samples. Using data from three cohorts from The Cancer Genome Atlas (TCGA) - TCGA-LGG (Brain Lower Grade Glioma), TCGA-GBM (Glioblastoma Multiforme) ($n$=729) and TCGA-KIRC (Kidney Renal Clear Cell Carcinoma) ($n$=511) - we demonstrate that the proposed approach achieves significantly higher AUROC scores than the state-of-the-art (SOTA) methods, by more than $20\%$. We conduct gene set enrichment analyses on the gene groups and show that majority of the gene groups are significantly enriched in important hallmarks and pathways. We also generate spatially enriched heatmaps to further investigate links between histological patterns and DNA methylation states. To the best of our knowledge, this is the first study that explores association of spatially resolved histological patterns with gene group methylation states across multiple cancer types using weakly supervised deep learning.

This paper presents a deep learning approach to the classification of 160 shortwave radio signals. It addresses the typical challenges of the shortwave spectrum, which are the large number of different signal types, the presence of various analog modulations and ionospheric propagation. As a classifier a deep convolutional neural network is used, that is trained to recognize 160 typical shortwave signal classes. The approach is blind and therefore does not require preknowledge or special preprocessing of the signal and no manual design of discriminative features for each signal class. The network is trained on a large number of synthetically generated signals and high quality recordings. Finally, the network is evaluated on real-world radio signals obtained from globally deployed receiver hardware and achieves up to 90% accuracy for an observation time of only 1 second.

Translocation event detection from raw nanopore current signals is a fundamental step in nanopore signal analysis. Traditional data analysis methods rely on user-defined parameters to extract event information, making the interpretation of experimental results sensitive to parameter choice. While Machine Learning (ML) has seen widespread adoption across various scientific fields, its potential remains underexplored in solid-state nanopore research. In this work, we introduce a nanopore signal generator capable of producing extensive synthetic datasets for machine learning applications and benchmarking nanopore signal analysis platforms. Using this generator, we train deep learning models to detect translocation events directly from raw signals, achieving over 99% true event detection with minimal false positives.

We study how to identify a class of continuous-time nonlinear systems defined by an ordinary differential equation affine in the unknown parameter. We define a notion of asymptotic consistency as $(n, h) \to (\infty, 0)$, and we achieve it using a family of direct methods where the first step is differentiating a noisy time series and the second step is a plug-in linear estimator. The first step, differentiation, is a signal processing adaptation of the nonparametric statistical technique of local polynomial regression. The second step, generalized linear regression, can be consistent using a least squares estimator, but we demonstrate two novel bias corrections that improve the accuracy for finite $h$. These methods significantly broaden the class of continuous-time systems that can be consistently estimated by direct methods.

The increasing integration of Distributed Energy Resources (DERs) in distribution networks presents new challenges for voltage regulation and reactive power support. This paper extends a sensitivity-aware reactive power dispatch algorithm tailored to manage smart inverters operating under different control modes, including PQ, PV, and Volt-Var (VV). The proposed approach dynamically optimizes reactive power dispatch and voltage setpoints, enabling effective coordination among distribution systems as a virtual power plant (VPP) to support the transmission network. The algorithm is applied to the IEEE 13-bus and IEEE-123 bus test systems, and its performance is validated by comparing results with OpenDSS simulations across various operating scenarios. Results show that the maximum error in the voltages is less than 0.015 pu.

This paper presents a novel Short-Term Voltage Stability Index (STVSI), which leverages Lyapunov Exponent-based detection to assess and quantify short-term stability triggered by Over Excitation Limiters (OELs) or undamped oscillations in voltage. The proposed method is measurement-based and decomposes the voltage trajectory into two key components using Empirical Mode Decomposition (EMD): a residual part, which indicates delayed voltage recovery, and an oscillatory part, which captures oscillations. The residual component is critical, as it can detect activation of OELs in synchronous generators or Low Voltage Ride-Through (LVRT) relays in inverter-based resources, potentially leading to instability within the quasisteady-state time frame. Meanwhile, the oscillatory component may indicate either a stable or unstable state in the short term. To accurately assess stability, STVSI employs an entropy-based metric to measure the proximity of the system to instability, with specific indices for short-term voltage stability based on oscillations and recovery. Simulations on the Nordic power system demonstrate that STVSI effectively identifies and categorizes voltage stability issues. Moreover, STVSI not only detects voltage stability conditions but also qualitatively assesses the extent of stability, providing a nuanced measure of stability.

Ensuring accurate violation detection in power systems is paramount for operational reliability. This paper introduces an enhanced voltage recovery violation index (EVRVI), a comprehensive index designed to quantify fault-induced delayed voltage recovery (FIDVR). EVRVI enhances traditional entropy-based methods by leveraging Empirical Mode Decomposition (EMD) to extract key features from the voltage signal, which are then used to quantify over-voltage (OV) and under-voltage (UV) events. Our simulations on the Nordic system, involving over 245k scenarios, demonstrate EVRVI's superior ability to identify and categorize voltage recovery issues compared to the traditional entropy-based measure. EVRVI not only significantly reduces false negatives in violation detection but also provides a reliable framework for over-voltage detection, making it an invaluable tool for modern power system studies.

This paper develops an input-output feedback linearization-based adaptive controller to stabilize and regulate a dual-rotor rotational system (DRRS), whose inertial properties as well as the geometric configuration of rotors are unknown. First, the equations of motion governing the dynamics of DRRS are derived using the Newton-Euler approach. Next, an input-output feedback linearization technique is used to linearize the dynamics from the rotor speeds to the angular position of the system. A finite-time convergent estimator, based on the portion of the DRRS dynamics, is used to update the required parameters in the controller. Finally, the proposed controller is validated in both step and harmonic command-following problems, and the robustness of the controller to the system's parameters is demonstrated.

The need for automatic and high-quality emotion annotation is paramount in applications such as continuous emotion recognition and video highlight detection, yet achieving this through manual human annotations is challenging. Inspired by inter-subject correlation (ISC) utilized in neuroscience, this study introduces a novel Electroencephalography (EEG) based ISC methodology that leverages a single-electrode and feature-based dynamic approach. Our contributions are three folds. Firstly, we reidentify two potent emotion features suitable for classifying emotions-first-order difference (FD) an differential entropy (DE). Secondly, through the use of overall correlation analysis, we demonstrate the heterogeneous synchronized performance of electrodes. This performance aligns with neural emotion patterns established in prior studies, thus validating the effectiveness of our approach. Thirdly, by employing a sliding window correlation technique, we showcase the significant consistency of dynamic ISCs across various features or key electrodes in each analyzed film clip. Our findings indicate the method's reliability in capturing consistent, dynamic shared neural synchrony among individuals, triggered by evocative film stimuli. This underscores the potential of our approach to serve as an indicator of continuous human emotion arousal. The implications of this research are significant for advancements in affective computing and the broader neuroscience field, suggesting a streamlined and effective tool for emotion analysis in real-world applications.

The Continuous Boostlet Transform (CBT) is introduced as a powerful tool for analyzing spatiotemporal signals, particularly acoustic wavefields. Overcoming the limitations of classical wavelets, the CBT leverages the Poincaré group and isotropic dilations to capture sparse features of natural acoustic fields. This paper presents the mathematical framework of the CBT, including its definition, fundamental properties, and associated uncertainty principles, such as Heisenberg's, logarithmic, Pitt's, and Nazarov's inequalities. These results illuminate the trade-offs between time and frequency localization in the boostlet domain. Practical examples with constant and exponential functions highlight the CBT's adaptability. With applications in radar, communications, audio processing, and seismic analysis, the CBT offers flexible time-frequency resolution, making it ideal for non-stationary and transient signals, and a valuable tool for modern signal processing.

The real-time assessment of complex motor skills presents a challenge in fields such as surgical training and rehabilitation. Recent advancements in neuroimaging, particularly functional near-infrared spectroscopy (fNIRS), have enabled objective assessment of such skills with high accuracy. However, these techniques are hindered by extensive preprocessing requirements to extract neural biomarkers. This study presents a novel end-to-end deep learning framework that processes raw fNIRS signals directly, eliminating the need for intermediate preprocessing steps. The model was evaluated on datasets from three distinct bimanual motor tasks--suturing, pattern cutting, and endotracheal intubation (ETI)--using performance metrics derived from both training and retention datasets. It achieved a mean classification accuracy of 93.9% (SD 4.4) and a generalization accuracy of 92.6% (SD 1.9) on unseen skill retention datasets, with a leave-one-subject-out cross-validation yielding an accuracy of 94.1% (SD 3.6). Contralateral prefrontal cortex activations exhibited task-specific discriminative power, while motor cortex activations consistently contributed to accurate classification. The model also demonstrated resilience to neurovascular coupling saturation caused by extended task sessions, maintaining robust performance across trials. Comparative analysis confirms that the end-to-end model performs on par with or surpasses baseline models optimized for fully processed fNIRS data, with statistically similar (p<0.05) or improved prediction accuracies. By eliminating the need for extensive signal preprocessing, this work provides a foundation for real-time, non-invasive assessment of bimanual motor skills in medical training environments, with potential applications in robotics, rehabilitation, and sports.

Impulsive noise (IN) commonly generated by power devices can severely degrade the performance of high sensitivity wireless receivers. Accurate channel state information (CSI) knowledge is essential for designing optimal maximum a posteriori detectors. This paper examines blind channel estimation methods based on the expectation-maximization (EM) algorithm tailored for scenarios impacted by bursty IN, which can be described by the Markov-Middleton model. We propose a constrained EM algorithm that exploits the trellis structure of the IN model and the transmitted binary phase shift keying (BPSK) symbols. By enforcing shared variance among specific trellis states and symmetry in the transition matrix, the proposed constrained EM algorithm adapted for the bursty IN channel has an almost two times faster convergence rate and better estimation performance than the standard EM approach. We comprehensively evaluate the robustness of both standard and constrained EM estimators under different types of CSI uncertainties. The results indicate that the final estimations of both EM estimators are robust enough to mismatch Markov-Middleton model parameters. However, as the level of CSI uncertainty increases, the convergence rate decreases.

Sensor-based human activity recognition is a key technology for many human-centered intelligent applications. However, this research is still in its infancy and faces many unresolved challenges. To address these, we propose a comprehensive optimization process approach centered on multi-attention interaction. We first utilize unsupervised statistical feature-guided diffusion models for highly adaptive data enhancement, and introduce a novel network architecture-Multi-branch Spatiotemporal Interaction Network, which uses multi-branch features at different levels to effectively Sequential ), which uses multi-branch features at different levels to effectively Sequential spatio-temporal interaction to enhance the ability to mine advanced latent features. In addition, we adopt a multi-loss function fusion strategy in the training phase to dynamically adjust the fusion weights between batches to optimize the training results. Finally, we also conducted actual deployment on embedded devices to extensively test the practical feasibility of the proposed method in existing work. We conduct extensive testing on three public datasets, including ablation studies, comparisons of related work, and embedded deployments.

The global trends in the construction of modern structures require the integration of sensors together with data recording and analysis modules so that their integrity can be continuously monitored for safe-life, economic and ecological reasons. This process of measuring and analyzing the data from a distributed sensor network all over a structural system in order to quantify its condition is known as structural health monitoring (SHM). Guided ultrasonic wave-based techniques are increasingly being adapted and used in several SHM systems which benefit from built-in transduction, large inspection ranges, and high sensitivity to small flaws. Nonetheless, for the design of a trustworthy health monitoring system, a vast amount of information regarding the inherent physical characteristics of the sources and their propagation and interaction across the structure is crucial. Moreover, any SHM system which is expected to transition to field operation must take into account the influence of environmental and operational changes which cause modifications in the stiffness and damping of the structure and consequently modify its dynamic behaviour. On that account, special attention is paid in this paper to the development of an efficient SHM methodology where robust signal processing and pattern recognition techniques are integrated for the correct interpretation of complex ultrasonic waves within the context of damage detection and identification. The methodology is based on an acousto-ultrasonics technique where the discrete wavelet transform is evaluated for feature extraction and selection, linear principal component analysis for data-driven modelling and selforganizing maps for a two-level clustering under the principle of local density. At the end, the methodology is experimentally demonstrated and results show that all the damages were detectable and identifiable.

Anxiety-provoking activities, such as public speaking, can trigger heightened anxiety responses in individuals with anxiety disorders. Recent research suggests that physiological signals, including electrocardiogram (ECG) and electrodermal activity (EDA), collected via wearable devices, can be used to detect anxiety in such contexts through machine learning models. However, the generalizability of these anxiety prediction models across different activities and diverse populations remains underexplored-an essential step for assessing model bias and fostering user trust in broader applications. To address this gap, we conducted a study with 111 participants who engaged in three anxiety-provoking activities. Utilizing both our collected dataset and two well-known publicly available datasets, we evaluated the generalizability of anxiety detection models within participants (for both same-activity and cross-activity scenarios) and across participants (within-activity and cross-activity). In total, we trained and tested more than 3348 anxiety detection models (using six classifiers, 31 feature sets, and 18 train-test configurations). Our results indicate that three key metrics-AUROC, recall for anxious states, and recall for non-anxious states-were slightly above the baseline score of 0.5. The best AUROC scores ranged from 0.62 to 0.73, with recall for the anxious class spanning 35.19% to 74.3%. Interestingly, model performance (as measured by AUROC) remained relatively stable across different activities and participant groups, though recall for the anxious class did exhibit some variation.

Battery degradation is governed by complex and randomized cyclic conditions, yet existing modeling and prediction frameworks usually rely on rigid, unchanging protocols that fail to capture real-world dynamics. The stochastic electrical signals make such prediction extremely challenging, while, on the other hand, they provide abundant additional information, such as voltage fluctuations, which may probe the degradation mechanisms. Here, we present chemistry-aware battery degradation prediction under dynamic conditions with machine learning, which integrates hidden Markov processes for realistic power simulations, an automated batch-testing system that generates a large electrochemical dataset under randomized conditions, an interfacial chemistry database derived from high-throughput X-ray photoelectron spectroscopy for mechanistic probing, and a machine learning model for prediction. By automatically constructing a polynomial-scale feature space from irregular electrochemical curves, our model accurately predicts both battery life and critical knee points. This feature space also predicts the composition of the solid electrolyte interphase, revealing six distinct failure mechanisms-demonstrating a viable approach to use electrical signals to infer interfacial chemistry. This work establishes a scalable and adaptive framework for integrating chemical engineering and data science to advance noninvasive diagnostics and optimize processes for more durable and sustainable energy storage technologies.

Cardiovascular disease remains one of the leading causes of mortality worldwide, underscoring the need for accurate as well as interpretable diagnostic machine learning tools. In this work, we investigate heart disease classification using electrocardiogram (ECG) data from two widely-utilized datasets: The MIT-BIH Arrhythmia and the PTB-XL datasets. We adapt a hierarchical attention network (HAN), originally developed for text classification, into an ECG-based heart-disease classification task. Our adapted HAN incorporates two attention layers that focus on ECG data segments of varying sizes. We conduct a comparative analysis between our adapted HAN and a more sophisticated state-of-the-art architecture, featuring a network with convolution, attention, and transformer layers (CAT-Net). Our empirical evaluation encompasses multiple aspects including test accuracy (quantified by 0-1 loss); model complexity (measured by the number of model parameters); and interpretability (through attention map visualization). Our adapted HAN demonstrates comparable test accuracy with significant reductions in model complexity and enhanced interpretability analysis: For the MIT-BIH dataset, our adapted HAN achieves 98.55\% test accuracy compared to 99.14\% for CAT-Net, while reducing the number of model parameters by a factor of 15.6. For the PTB-XL dataset, our adapted HAN achieves a 19.3-fold reduction in model complexity compared to CAT-Net, with only a 5\% lower test accuracy. From an interpretability perspective, the significantly simpler architecture and the hierarchical nature of our adapted HAN model facilitate a more straightforward interpretability analysis based on visualizing attention weights. Building on this advantage, we conduct an interpretability analysis of our HAN that highlights the regions of the ECG signal most relevant to the model's decisions.

Lithium-ion battery health management has become increasingly important as the application of batteries expands. Precise forecasting of capacity degradation is critical for ensuring the healthy usage of batteries. In this paper, we innovatively propose MSPMLP, a multi-scale capacity prediction model utilizing the mixture of experts (MoE) architecture and patch-based multi-layer perceptron (MLP) blocks, to capture both the long-term degradation trend and local capacity regeneration phenomena. Specifically, we utilize patch-based MLP blocks with varying patch sizes to extract multi-scale features from the capacity sequence. Leveraging the MoE architecture, the model adaptively integrates the extracted features, thereby enhancing its capacity and expressiveness. Finally, the future battery capacity is predicted based on the integrated features, achieving high prediction accuracy and generalization. Experimental results on the public NASA dataset indicate that MSPMLP achieves a mean absolute error (MAE) of 0.0078, improving by 41.8\% compared to existing methods. These findings highlight that MSPMLP, owing to its multi-scale modeling capability and generalizability, provides a promising solution to the battery capacity prediction challenges caused by capacity regeneration phenomena and complex usage conditions. The code of this work is provided at https://github.com/LeiYuzhu/CapacityPredict.