Effective sensor data processing is critical for cyber-physical and IoT systems but often requires specialized expertise. While Large Language Models (LLMs) show promise as autonomouscopilotsfor sensor processing, their capabilities remain underexplored. We introduce SensorBench, the first comprehensive benchmark for evaluating LLMs across diverse real-world sensor datasets and tasks. SensorBench evaluates three paradigms for leveraging LLMs in sensing tasks: Tool-Augmented Coding (TAC), Standalone Coding (SAC), and Direct Answer (DA). We evaluate 8 leading LLM variants, including 2 Large Reasoning Models (LRMs) and 2 domain-specific LLMs, providing a structured reference for absolute performance, latency, and resource requirements. Our analysis reveals that: (1) TAC significantly outperforms SAC and DA; (2) LLMs excel at simple tasks but consistently underperform domain experts on compositional tasks requiring parameter tuning and multi-step reasoning. (3) The reasoning mechanism introduced in LRMs does not yield substantial performance gains. To improve the performance, we explore four prompting strategies and fine-tuning approaches (using our newly released sensor-processing corpus). The results show that self-verification prompting proves most effective, outperforming other methods simultaneously in 48% of tasks, while fine-tuning yields marginal gains. Our analysis suggests that more sophisticated interaction frameworks, such as signal-level self-verification, may bridge the gap to human expert-level performance. This benchmark provides a foundation for evaluating and improving LLMs in sensing applications1.

Explaining the inner workings of deep neural network models have received considerable attention in recent years. Researchers have attempted to provide human parseable explanations justifying why a model performed a specific classification. Although many of these toolkits are available for use, it is unclear which style of explanation is preferred by end-users, thereby demanding investigation. We performed a cross-analysis Amazon Mechanical Turk study comparing the popular state-of-the-art explanation methods to empirically determine which are better in explaining model decisions. The participants were asked to compare explanation methods across applications spanning image, text, audio, and sensory domains. Among the surveyed methods, explanation-by-example was preferred in all domains except text sentiment classification, where LIME's method of annotating input text was preferred. We highlight qualitative aspects of employing the studied explainability methods and conclude with implications for researchers and engineers that seek to incorporate explanations into user-facing deployments.

Modern smartphones and smartwatches are equipped with inertial sensors (accelerometer, gyroscope, and magnetometer) that can be used for Human Activity Recognition (HAR) to infer tasks such as daily activities, transportation modes and, gestures. HAR requires collecting raw inertial sensor values and training a machine learning model on the collected data. The challenge in this approach is that the models are trained for specific devices and device configurations whereas, in reality, the set of devices carried by a person may vary over time. Ideally, one would like activity inferencing to be robust of this variation and provide accurate predictions by making opportunistic use of information from available devices. Moreover, the devices may be located at different parts of the body (e.g. pocket, left and right wrist), may have different sets of sensors (e.g. a smartwatch may not have gyroscope while a smartphone might), and may differ in sampling frequencies. In this paper, we provide a solution which makes use of the information from available devices while being robust to their variations. Instead of training an end-to-end model for every permutation of device combinations and configurations, we propose a scalable deep learning based solution in which each device learns its own sensor fusion model that maps the raw sensor values to a shared low dimensional latent space which we call the 'SenseHAR'-a virtual activity sensor. The virtual sensor has the same format and similar behavior regardless of the subset of devices, sensor's availability, sampling rate, or a device's location. This would help machine learning engineers to develop their application specific (e.g., from gesture recognition to activities of daily life) models in a hardware-agnostic manner based on this virtual activity sensor. Our evaluations show that an application model trained on SenseHAR achieves the state of the art accuracies of 95.32%, 74.22% and 93.13% on PAMAP2, Opportunity(gestures) and our collected datasets respectively.

Tagging animals with sensors is a powerful approach to acquire critical information about the behavioural ecology of free-living animals, which ultimately can provide data to inform best practice in conservation efforts. Sensor tags for such deployments need long lifetimes and incorporate multiple sensors, especially location because space use can contextualize behavior. The tag size needs to be minimal so as not to affect the activities of the animal. Aquatic animals in particular present challenges due to lack of wireless communication and water-proofing. Taking these points into consideration we have designed Aquamote: an ultra-low power, tiny sensor tag (20 x 29 mm2) which integrates accelerometer, gyroscope, magnetometer, depth sensor, GPS and BLE. Our poster will showcase the performance of AquaMote and highlight our design decisions to reduce its size and power consumption.