Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data. Many algorithms are designed for online time series forecasting, with some exploiting cross-variable dependency while others assume independence among variables. Given every data assumption has its own pros and cons in online time series modeling, we propose Online ensembling Network (OneNet). It dynamically updates and combines two models, with one focusing on modeling the dependency across the time dimension and the other on cross-variate dependency. Our method incorporates a reinforcement learning-based approach into the traditional online convex programming framework, allowing for the linear combination of the two models with dynamically adjusted weights. OneNet addresses the main shortcoming of classical online learning methods that tend to be slow in adapting to the concept drift. Empirical results show that OneNet reduces online forecasting error by more than 50%compared to the State-Of-The-Art (SOTA) method.

B.4 Existing theoretical intuition and empirical comparison to the proposed OCP block.

In such cases, re-training the model from scratch could be time-consuming.

Multi-channel audio alignment is a key requirement in bioacoustic monitoring, spatial audio systems, and acoustic localization. However, existing methods often struggle to address nonlinear clock drift and lack mechanisms for quantifying uncertainty. Traditional methods like Cross-correlation and Dynamic Time Warping assume simple drift patterns and provide no reliability measures. Meanwhile, recent deep learning models typically treat alignment as a binary classification task, overlooking inter-channel dependencies and uncertainty estimation. We introduce a method that combines cross-attention mechanisms with confidence-weighted scoring to improve multi-channel audio synchronization. We extend BEATs encoders with cross-attention layers to model temporal relationships between channels. We also develop a confidence-weighted scoring function that uses the full prediction distribution instead of binary thresholding. Our method achieved first place in the BioDCASE 2025 Task 1 challenge with 0.30 MSE average across test datasets, compared to 0.58 for the deep learning baseline. On individual datasets, we achieved 0.14 MSE on ARU data (77% reduction) and 0.45 MSE on zebra finch data (18% reduction). The framework supports probabilistic temporal alignment, moving beyond point estimates. While validated in a bioacoustic context, the approach is applicable to a broader range of multi-channel audio tasks where alignment confidence is critical. Code available on: https://github.com/Ragib-Amin-Nihal/BEATsCA

Monitoring respiration parameters such as respiratory rate could be beneficial to understand the impact of training on equine health and performance and ultimately improve equine welfare. In this work, we compare deep learning-based methods to an adapted signal processing method to automatically detect cyclic respiratory events and extract the dynamic respiratory rate from microphone recordings during high intensity exercise in Standardbred trotters. Our deep learning models are able to detect exhalation sounds (median F1 score of 0.94) in noisy microphone signals and show promising results on unlabelled signals at lower exercising intensity, where the exhalation sounds are less recognisable. Temporal convolutional networks were better at detecting exhalation events and estimating dynamic respiratory rates (median F1: 0.94, Mean Absolute Error (MAE) $\pm$ Confidence Intervals (CI): 1.44$\pm$1.04 bpm, Limits Of Agreements (LOA): 0.63$\pm$7.06 bpm) than long short-term memory networks (median F1: 0.90, MAE$\pm$CI: 3.11$\pm$1.58 bpm) and signal processing methods (MAE$\pm$CI: 2.36$\pm$1.11 bpm). This work is the first to automatically detect equine respiratory sounds and automatically compute dynamic respiratory rates in exercising horses. In the future, our models will be validated on lower exercising intensity sounds and different microphone placements will be evaluated in order to find the best combination for regular monitoring.

An upcoming national news channel is replacing human anchors with hyper-realistic AI-generated avatars. Channel 1, set to launch next year, plans to use digitally generated people and digital doubles of real actors who had their bodies scanned. Demonstration videos show anchors that talk, look, and move like real humans, but were designed on computers using artificial intelligence technology. Channel 1 plans to stream its news on TV apps and is set to add a translation feature to roll it out globally. The outlet's founder told DailyMail.com

The ability to predict the behavior of a wireless channel in terms of the frame delivery ratio is quite valuable, and permits, e.g., to optimize the operating parameters of a wireless network at runtime, or to proactively react to the degradation of the channel quality, in order to meet the stringent requirements about dependability and end-to-end latency that typically characterize industrial applications. In this work, prediction models based on the exponential moving average (EMA) are investigated in depth, which are proven to outperform other simple statistical methods and whose performance is nearly as good as artificial neural networks, but with dramatically lower computational requirements. Regarding the innovation and motivation of this work, a new model that we called EMA linear combination (ELC), is introduced, explained, and evaluated experimentally. Its prediction accuracy, tested on some databases acquired from a real setup based on Wi-Fi devices, showed that ELC brings tangible improvements over EMA in any experimental conditions, the only drawback being a slight increase in computational complexity.

To enable highly automated vehicles where the driver is no longer a safety backup, the vehicle must deal with various Functional Insufficiencies (FIs). Thus-far, there is no widely accepted functional architecture that maximizes the availability of autonomy and ensures safety in complex vehicle operational design domains. In this paper, we present a survey of existing methods that strive to prevent or handle FIs. We observe that current design-time methods of preventing FIs lack completeness guarantees. Complementary solutions for on-line handling cannot suitably increase safety without seriously impacting availability of journey continuing autonomous functionality. To fill this gap, we propose the Safety Shell, a scalable multi-channel architecture and arbitration design, built upon preexisting functional safety redundant channel architectures. We compare this novel approach to existing architectures using numerical case studies. The results show that the Safety Shell architecture allows the automated vehicle to be as safe or safer compared to alternatives, while simultaneously improving availability of vehicle autonomy, thereby increasing the possible coverage of on-line functional insufficiency handling.

Interpretable time series prediction is crucial for safety-critical areas such as healthcare and autonomous driving. Most existing methods focus on interpreting predictions by assigning important scores to segments of time series. In this paper, we take a different and more challenging route and aim at developing a self-interpretable model, dubbed Counterfactual Time Series (CounTS), which generates counterfactual and actionable explanations for time series predictions. Specifically, we formalize the problem of time series counterfactual explanations, establish associated evaluation protocols, and propose a variational Bayesian deep learning model equipped with counterfactual inference capability of time series abduction, action, and prediction. Compared with state-of-the-art baselines, our self-interpretable model can generate better counterfactual explanations while maintaining comparable prediction accuracy.