A major challenge in developing robust and generalizable Human Activity Recognition (HAR) systems for smart homes is the lack of large and diverse labeled datasets. Variations in home layouts, sensor configurations, and individual behaviors further exacerbate this issue. To address this, we leverage the idea of embodied AI agents—virtual agents that perceive and act within simulated environments guided by internal world models. We introduce AgentSense, a virtual data generation pipeline in which agents live out daily routines in simulated smart homes, with behavior guided by Large Language Models (LLMs). The LLM generates diverse synthetic personas and realistic routines grounded in the environment, which are then decomposed into fine-grained actions. These actions are executed in an extended version of the VirtualHome simulator, which we augment with virtual ambient sensors that record the agents’ activities. Our approach produces rich, privacy-preserving sensor data that reflects real-world diversity. We evaluate AgentSense on five real HAR datasets. Models pretrained on the generated data consistently outperform baselines, especially in low-resource settings. Furthermore, combining the generated virtual sensor data with a small amount of real data achieves performance comparable to training on full real-world datasets. These results highlight the potential of using LLM-guided embodied agents for scalable and cost-effective sensor data generation in HAR.

Personality traits influence how individuals engage, behave, and make decisions during the information-seeking process. However, few studies have linked personality to observable search behaviors. This study aims to characterize personality traits through a multimodal time-series model that integrates eye-tracking data and gaze missingness–periods when the user’s gaze is not captured. This approach is based on the idea that people often look away when they think, signaling disengagement or reflection. We conducted a user study with 25 participants, who used an interactive application on an iPad, allowing them to engage with digital artifacts from a museum. We rely on raw gaze data from an eye tracker, minimizing preprocessing so that behavioral patterns can be preserved without substantial data cleaning. From this perspective, we trained models to predict personality traits using gaze signals. Our results from a five-fold cross-validation study demonstrate strong predictive performance across all five dimensions: Neuroticism (Macro F1 = 77.69%), Conscientiousness (74.52%), Openness (77.52%), Agreeableness (73.09%), and Extraversion (76.69%). The ablation study examines whether the absence of gaze information affects the model performance, demonstrating that incorporating missingness improves multimodal time-series modeling. The full model, which integrates both time-series signals and missingness information, achieves 10-15% higher accuracy and macro F1 scores across all Big Five traits compared to the model without time-series signals and missingness. These findings provide evidence that personality can be inferred from search-related gaze behavior and demonstrate the value of incorporating missing gaze data into time-series multimodal modeling.

Information processing differs across cognitive levels, shaping how individuals interpret and use information. Guided by Bloom's Taxonomy, this study explores how variations in cognitive processing and domain knowledge manifest in observable search behaviors within a hybrid environment that combines a traditional search engine with an LLM-based chat interface. Prior work shows that eye-tracking data can reveal attention patterns, domain knowledge, and personality-related differences in interactive search. By integrating behavioral, physiological, and knowledge-based measures, this study characterizes how cognitive development shapes interaction strategies in interactive search environments, with implications for adaptive and personalized information retrieval systems, and education technology.

Leveraging their inherent mobility and rapid deployment capabilities, Unmanned Aerial Vehicles (UAVs) can deliver computing services to ground devices with enhanced speed and flexibility. Consequently, UAV-based Mobile Edge Computing (MEC) networks have garnered significant research interest and attention. However, in contrast to ground edge servers, UAVs functioning as computing nodes face a unique set of challenges. Their decision-making processes must not only address user computational demands but also concurrently consider critical factors such as energy consumption and optimal deployment strategies. To tackle these challenges, we introduce a multi-UAV deployment and cooperative scheduling strategy designed to comprehensively optimize deployment locations, task latency, overall energy consumption, and the load distribution across the UAV network. Specifically, we decompose the overarching optimization problem into two distinct sub-problems. For the deployment problem, we propose a clustering algorithm rooted in the modularity-improving Louvain method, aiming to minimize both mobile device transmission power and UAV energy consumption. Then, we present a reinforcement learning-based algorithm capable of making dynamic scheduling decisions that adapt to system fluctuations. Finally, we validate the practicality and effectiveness of our integrated deployment and scheduling scheme through rigorous experimental evaluation.

Eye-tracking data has been shown to correlate with a user's knowledge level and query formulation behaviour. While previous work has focused primarily on eye gaze fixations for attention analysis, often requiring additional contextual information, our study investigates the memory-related cognitive dimension by relying solely on pupil dilation and gaze velocity to infer users' topic familiarity and query specificity without needing any contextual information. Using eye-tracking data collected via a lab user study N=18, we achieved a Macro F1 score of 71.25% for predicting topic familiarity with a Gradient Boosting classifier, and a Macro F1 score of 60.54% with a k-nearest neighbours (KNN) classifier for query specificity. Furthermore, we developed a novel annotation guideline - specifically tailored for question answering - to manually classify queries as Specific or Non-specific. This study demonstrates the feasibility of eye-tracking to better understand topic familiarity and query specificity in search.