We present a novel multisensory interactive system that integrates mid-air haptic feedback with ocean-themed visual media to foster sustainability awareness. Using focused ultrasound, the system allows users to ”feel” environmental phenomena such as waves, coral reefs, and pollution without wearing devices or touching surfaces. Designed for deployment in public and mobile contexts such as exhibitions, science centers, and mixed-reality installations, the system demonstrates how contactless haptics can extend emotional engagement with environmental issues beyond traditional media. A preliminary study with ten participants showed that mid-air haptics amplified emotional responses and strengthened intentions toward pro-environmental action. This work contributes to mobile and ubiquitous interaction research by exploring how multisensory feedback can make abstract sustainability challenges more tangible and engaging in everyday contexts.

Mid-air haptic technology enables touchless interaction through focused ultrasound and holds promise for inclusive design in mobile and ubiquitous multimedia systems. However, accessibility aspects remain largely unexplored. This poster introduces an accessibility-centered framework for mid-air haptic interaction, building on prior reviews of user experience and technical design. We systematically analyzed 42 studies published between 2014 and 2024 and conducted twelve expert interviews, including accessibility specialists and a visually impaired participant. The analysis highlights three main challenges: low stimulus clarity, limited multimodal feedback, and insufficient personalization. Our proposed framework addresses these gaps through four design dimensions—perceptual optimization, multimodal integration, spatial configuration, and individual calibration. By integrating literature and expert insights, this work advances a structured foundation for accessible mid-air haptic systems and identifies future research directions toward inclusive, touchless interaction in mobile, public, and mixed-reality contexts.

BACKGROUND: Identification of biomarkers, which are measurable characteristics of biological datasets, can be challenging. Although amplicon sequence variants (ASVs) can be considered potential biomarkers, identifying important ASVs in high-throughput sequencing datasets is challenging. Noise, algorithmic failures to account for specific distributional properties, and feature interactions can complicate the discovery of ASV biomarkers. In addition, these issues can impact the replicability of various models and elevate false-discovery rates. Contemporary machine learning approaches can be leveraged to address these issues. Ensembles of decision trees are particularly effective at classifying the types of data commonly generated in high-throughput sequencing (HTS) studies due to their robustness when the number of features in the training data is orders of magnitude larger than the number of samples. In addition, when combined with appropriate model introspection algorithms, machine learning algorithms can also be used to discover and select potential biomarkers. However, the construction of these models could introduce various biases which potentially obfuscate feature discovery. RESULTS: We developed a decision tree ensemble, LANDMark, which uses oblique and non-linear cuts at each node. In synthetic and toy tests LANDMark consistently ranked as the best classifier and often outperformed the Random Forest classifier. When trained on the full metabarcoding dataset obtained from Canada's Wood Buffalo National Park, LANDMark was able to create highly predictive models and achieved an overall balanced accuracy score of 0.96 ± 0.06. The use of recursive feature elimination did not impact LANDMark's generalization performance and, when trained on data from the BE amplicon, it was able to outperform the Linear Support Vector Machine, Logistic Regression models, and Stochastic Gradient Descent models (p ≤ 0.05). Finally, LANDMark distinguishes itself due to its ability to learn smoother non-linear decision boundaries. CONCLUSIONS: Our work introduces LANDMark, a meta-classifier which blends the characteristics of several machine learning models into a decision tree and ensemble learning framework. To our knowledge, this is the first study to apply this type of ensemble approach to amplicon sequencing data and we have shown that analyzing these datasets using LANDMark can produce highly predictive and consistent models.

Fairground: Thrill Laboratory was a series of live events that augmented the experience of amusement rides. A wearable telemetry system captured video, audio, heart-rate and acceleration data, streaming them live to spectator interfaces and a watching audience. In this paper, we present a study of this event, which draws on video recordings and post-event interviews, and which highlights the experiences of riders, spectators and ride operators. Our study shows how the telemetry system transformed riders into performers, spectators into an audience, and how the role of ride operator began to include aspects of orchestration, with the relationship between all three roles also transformed. Critically, the introduction of a telemetry system seems to have had the potential to re-connect riders/performers back to operators/orchestrators and spectators/audience, re-introducing a closer relationship that used to be available with smaller rides. Introducing telemetry to a real-world situation also creates significant complexity, which we illustrate by focussing on a moment of perceived crisis.

This paper highlights the potential of using genetic algorithms to solve cellular resource allocation problems. The objective in this work is to gauge how well a GA-based channel borrower performs when compared to a greedy borrowing heuristic. This is needed to establish how suited GA-like (stochastic search) algorithms are for the solution of optimization problems in mobile computing environments. This involves the creation of a simple mobile networking resource environment and design of a GA-based channel borrower that works within this environment. A simulation environment is also built to compare the performance of the GA-based channel-borrowing method with the heuristic. To enhance the performance of the GA, extra attention is paid to developing an improved mutation operator. The performance of the new operator is evaluated against the heuristic borrowing scheme. For a real-time implementation, the GA needs to have the properties of a micro GA strategy. This involves making improvements to the crossover operator and evaluation procedure so the GA can converge to a "good" solution rapidly.