Self-selected walking speed is a key outcome for exercise-based rehabilitation programs following lower-extremity trauma. This work introduces a novel reinforcement learning-based assist-as-needed (RL-AAN) controller for ankle exoskeletons, aimed at gait speed training. Built on an actor–critic architecture, the RL-AAN controller integrates a control objective that balances the trade-off between expected stride velocity (SV) errors and exoskeleton assistance. This approach allows the exoskeleton to progressively reduce ankle plantar- and dorsiflexion (PDF) assistance as the user’s performance improves, promoting active participation. The desired assistive torque is computed as the product of the actor output and the wearer’s biomechanical ankle PDF moment, estimated by a subject-agnostic model, thereby ensuring personalized and biomechanically relevant assistance. In a proof-of-concept study with healthy individuals walking on a self-paced treadmill with ankle weights, the RL-AAN controller outperformed a conventional Fixed-K controller—achieving greater immediate speed increases during assisted walking (14.2% vs. 10.0% relative to unassisted perturbed walking) and inducing short-term gait speed adaptation post-training, not observed with the conventional controller. These findings highlight the potential of RL-AAN control for subject-tailored gait training, with promising clinical implications for exercise-based rehabilitation in individuals with neurological or musculoskeletal gait impairments.

We propose Orionet, efficient parallel implementations of Point-to-Point Shortest Paths (PPSP) queries using bidirectional search (BiDS) and other heuristics, with an additional focus on batch PPSP queries. We present a framework for parallel PPSP built on existing single-source shortest paths (SSSP) frameworks by incorporating novel pruning conditions. As a result, we develop efficient parallel PPSP algorithms based on early termination, bidirectional search, A* search, and bidirectional A*---all with simple and efficient implementations.

Recruiting participants is a cornerstone of Human-Centric Computing (HCC) research, especially in Digital Health research and development. Effective recruitment ensures that the developed systems reflect the needs and experiences of the intended users. This paper explores recruitment strategies, challenges, and experiences encountered in a project focused on enhancing telehealth through technology co-design, development, and evaluation. By detailing recruitment efforts in the Palliative Care cohort through the think-aloud and simulation study phases, this paper provides insights and practical recommendations for future HCC research in the digital health area.

Federated Learning (FL) presents a decentralized approach to model training in the agri-food sector and offers the potential for improved machine learning performance, while ensuring the safety and privacy of individual farms or data silos. However, the conventional FL approach has two major limitations. First, the heterogeneous data on individual silos can cause the global model to perform well for some clients but not all, as the update direction on some clients may hinder others after they are aggregated. Second, it is lacking with respect to the efficiency perspective concerning communication costs during FL and large model sizes. This paper proposes a new technical solution that utilizes network pruning on client models and aggregates the pruned models. This method enables local models to be tailored to their respective data distribution and mitigate the data heterogeneity present in agri-food data. Moreover, it allows for more compact models that consume less data during transmission. We experiment with a soybean yield forecasting dataset and find that this approach can improve inference performance by 15.5% to 20% compared to FedAvg, while reducing local model sizes by up to 84% and the data volume communicated between the clients and the server by 57.1% to 64.7%. Our method demonstrates the potential to use efficient models that are more environmentally friendly to support the agri-food sector’s transition to net zero. Future enhancements of this method could further optimize distributed learning in agri-food, enhancing sustainability and applicability.

The increasing adoption of machine learning and AI models in finance and banking poses challenges for model testing and model risk management (MRM). Conventional testing has limitations in evaluating more complex models while the latest testing methodologies have not yet been widely productionized. We propose a model-agnostic testing algorithm based on counterfactual generation for machine learning models in finance. Our method provides actionable counterfactual samples that can guide future model analysis and improvement. To make our algorithm modeler-friendly, we design a cloud-native implementation that is easy to integrate with any new and existing models, and ready for production-level automation, scalability, and parallel processing.

This paper presents the results of an investigation aimed at characterizing the multipath radio channel for WCDMA signals in an operational network. The measurement campaign was conducted in Hutchison3G's network in London. It is a well known fact that multipath radio propagation plays a key role on the performance of any wireless communication system. Knowledge of the multipath fading characteristics in a real environment is crucial for an accurate prediction of the performances of advanced technologies such as high speed downlink packet access (HSDPA) or multimedia broadcast multicast service (MBMS).