Machine learning for microcontroller-class hardware: A review
The advancements in machine learning (ML) opened a new opportunity to bring intelligence
to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …
to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …
Difformer: Multi-resolutional differencing transformer with dynamic ranging for time series analysis
Time series analysis is essential to many far-reaching applications of data science and
statistics including economic and financial forecasting, surveillance, and automated …
statistics including economic and financial forecasting, surveillance, and automated …
Primenet: Pre-training for irregular multivariate time series
Real-world applications often involve irregular time series, for which the time intervals
between successive observations are non-uniform. Irregularity across multiple features in a …
between successive observations are non-uniform. Irregularity across multiple features in a …
TFSemantic: A Time–Frequency Semantic GAN Framework for Imbalanced Classification Using Radio Signals
Recently, wireless sensing techniques have been widely used for Internet of Things (IoT)
applications. Unlike traditional device-based sensing, wireless sensing is contactless …
applications. Unlike traditional device-based sensing, wireless sensing is contactless …
Multivariate time series classification based on fusion features
In various areas of real life, Multivariate Time Series Classification (MTSC) is widely used. It
has been the focus of attention of many researchers, and a number of MTSC methods have …
has been the focus of attention of many researchers, and a number of MTSC methods have …
FreqMAE: Frequency-Aware Masked Autoencoder for Multi-Modal IoT Sensing
This paper presents FreqMAE, a novel self-supervised learning framework that synergizes
masked autoencoding (MAE) with physics-informed insights to capture feature patterns in …
masked autoencoding (MAE) with physics-informed insights to capture feature patterns in …
On the amplification of security and privacy risks by post-hoc explanations in machine learning models
A variety of explanation methods have been proposed in recent years to help users gain
insights into the results returned by neural networks, which are otherwise complex and …
insights into the results returned by neural networks, which are otherwise complex and …
[HTML][HTML] CIR-DFENet: Incorporating cross-modal image representation and dual-stream feature enhanced network for activity recognition
Human activity recognition (HAR) based on wearable sensors has been widely used in
various fields such as health monitoring, healthcare, and fitness due to its portability …
various fields such as health monitoring, healthcare, and fitness due to its portability …
NeurIT: Pushing the Limit of Neural Inertial Tracking for Indoor Robotic IoT
Inertial tracking is vital for robotic IoT and has gained popularity thanks to the ubiquity of low-
cost Inertial Measurement Units (IMUs) and deep learning-powered tracking algorithms …
cost Inertial Measurement Units (IMUs) and deep learning-powered tracking algorithms …
Centaur: Robust Multimodal Fusion for Human Activity Recognition
The proliferation of Internet of Things (IoT) and mobile devices equipped with
heterogeneous sensors has enabled new applications that rely on the fusion of time series …
heterogeneous sensors has enabled new applications that rely on the fusion of time series …