Forecasting is a critical task in decision-making across numerous domains. While historical numerical data provide a start, they fail to convey the complete context for reliable and accurate predictions. Human forecasters frequently rely on additional information, such as background knowledge and constraints, which can efficiently be communicated through natural language. However, in spite of recent progress with LLM-based forecasters, their ability to effectively integrate this textual information remains an open question. To address this, we introduce "Context is Key" (CiK), a time-series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context, requiring models to integrate both modalities; crucially, every task in CiK requires understanding textual context to be solved successfully. We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters, and propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark. Our experiments highlight the importance of incorporating contextual information, demonstrate surprising performance when using LLM-based forecasting models, and also reveal some of their critical shortcomings. This benchmark aims to advance multimodal forecasting by promoting models that are both accurate and accessible to decision-makers with varied technical expertise. The benchmark can be visualized at https://servicenow.github.io/context-is-key-forecasting/v0.

Recent work in prosthetic devices suggests that forearm surface electromyography (sEMG) is a promising technology for human-computer interactions. Specifically, a system able to detect individual finger movement can have many clinical and nonclinical applications. Popular consumer-grade sEMG armbands are limited by their fixed electrode arrangement, which can negatively affect the classification of subtle finger gestures. We propose a low-cost, 3D-printed armband with fully adjustable electrode placement for the detection of single-finger tapping motions. We trained machine learning classifiers on features extracted from eight-channel sEMG signals to detect movement from nine fingers. We obtained a classification accuracy of 71.5 ± 1.1% for a K-Nearest Neighbours (KNN) classifier using features extracted from 500 ms windows of sEMG data. Moreover, a KNN model trained on 200 ms windows from a subset of particularly clean data obtained an accuracy of 93.0 ± 0.5%. We also introduce a novel haptic feedback mechanism to improve user experience when using the armband, and propose an augmented reality typing interface as a potential application of our armband.

Wheelchairs controlled using electroencephalography (EEG) have been proposed to facilitate independent mobility for people with motor disabilities. To date, the majority of these systems have relied on distracting external stimuli such as flashing lights and expensive, medical-grade EEG amplifiers. We propose a wheelchair prototype that uses hand motor imagery (MI) and jaw clench data collected with a consumer-grade EEG system to generate left, right, forward, and stop commands. The signal is classified with logistic regression, and using only two scalp electrodes and a two-second window size, we obtained a mean subject accuracy of 60 ± 5% and a peak subject accuracy of 82± 3%. We introduce a novel control-flow paradigm relying on an intermediate control state, engaged by jaw clenching, to reduce the complexity of our classification problem, as well as real-time spectrograms for neurofeedback training. Additionally, we supplement our system with automated driving features, a location tracker, and a heart-rate monitor to increase usability and safety.