Long Huang

Cheng Feng, Long Huang, Denis Krompass

We present General Time Transformer (GTT), an encoder-only style foundation model for zero-shot multivariate time series forecasting. GTT is pretrained on a large dataset of 200M high-quality time series samples spanning diverse domains. In our proposed framework, the task of multivariate time series forecasting is formulated as a channel-wise next curve shape prediction problem, where each time series sample is represented as a sequence of non-overlapping curve shapes with a unified numerical magnitude. GTT is trained to predict the next curve shape based on a window of past curve shapes in a channel-wise manner. Experimental results demonstrate that GTT exhibits superior zero-shot multivariate forecasting capabilities on unseen time series datasets, even surpassing state-of-the-art supervised baselines. Additionally, we investigate the impact of varying GTT model parameters and training dataset scales, observing that the scaling law also holds in the context of zero-shot multivariate time series forecasting.

Ruxin Wang, Long Huang, Chen Wang

Handheld phone distraction is the leading cause of traffic accidents. However, few efforts have been devoted to detecting when the phone distraction happens, which is a critical input for taking immediate safety measures. This work proposes a phone-use monitoring system, which detects the start of the driver's handheld phone use and eliminates the distraction at once. Specifically, the proposed system emits periodic ultrasonic pulses to sense if the phone is being held in hand or placed on support surfaces (e.g., seat and cup holder) by capturing the unique signal interference resulted from the contact object's damping, reflection and refraction. We derive the short-time Fourier transform from the microphone data to describe such impacts and develop a CNN-based binary classifier to discriminate the phone use between the handheld and the handsfree status. Additionally, we design an adaptive window-based filter to correct the classification errors and identify each handheld phone distraction instance, including its start, end, and duration. Extensive experiments with fourteen people, three phones and two car models show that our system achieves 99% accuracy of recognizing handheld phone-use instances and 0.76-second median error to estimate the distraction's start time.