Related papers: Towards Causally Interpretable Wi-Fi CSI-Based Hum…

With the growing demand for device-free and privacy-preserving sensing solutions, Wi-Fi sensing has emerged as a promising approach for human pose estimation (HPE). However, existing methods often process vast amounts of channel state…

Human Activity Recognition (HAR) describes the machines ability to recognize human actions. Nowadays, most people on earth are health conscious, so people are more interested in tracking their daily activities using Smartphones or Smart…

Most deep learning recommendation models operate as black boxes, relying on latent representations that obscure their decision process. This lack of intrinsic interpretability raises concerns in applications that require transparency and…

In a wireless network, the efficiency of scheduling algorithms over time-varying channels depends heavily on the accuracy of the Channel State Information (CSI), which is usually quite ``costly'' in terms of consuming network resources.…

In Wi-Fi systems, channel state information (CSI) plays a crucial role in enabling access points to execute beamforming operations. However, the feedback overhead associated with CSI significantly hampers the throughput improvements. Recent…

Recently, domain generalization (DG) has emerged as a promising solution to mitigate distribution-shift issue in sensor-based human activity recognition (HAR) scenario. However, most existing DG-based works have merely focused on modeling…

The utilization of Wi-Fi based human activity recognition has gained considerable interest in recent times, primarily owing to its applications in various domains such as healthcare for monitoring breath and heart rate, security, elderly…

This paper presents DeepCRF, a new framework that harnesses deep learning to extract subtle micro-signals from channel state information (CSI) measurements, enabling robust and resilient radio-frequency fingerprinting (RFF) of…

We introduce the Rule Network with Selective Logical Operators (RNS), a novel neural architecture that employs \textbf{selective logical operators} to adaptively choose between AND and OR operations at each neuron during training. Unlike…

This paper introduces {HINER}, a novel neural representation for compressing HSI and ensuring high-quality downstream tasks on compressed HSI. HINER fully exploits inter-spectral correlations by explicitly encoding of spectral wavelengths…

Human Activity Recognition (HAR) stands as a pivotal technique within pattern recognition, dedicated to deciphering human movements and actions utilizing one or multiple sensory inputs. Its significance extends across diverse applications,…

Despite their success and widespread adoption, the opaque nature of deep neural networks (DNNs) continues to hinder trust, especially in critical applications. Current interpretability solutions often yield inconsistent or oversimplified…

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…

In this paper, we propose an LLM-Guided Exemplar Selection framework to address a key limitation in state-of-the-art Human Activity Recognition (HAR) methods: their reliance on large labeled datasets and purely geometric exemplar selection,…

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Empowered by deep learning, semantic communication marks a paradigm shift from transmitting raw data to conveying task-relevant meaning, enabling more efficient and intelligent wireless systems. In this study, we explore a deep…

Wearable-based Human Activity Recognition (HAR) is a key task in human-centric machine learning due to its fundamental understanding of human behaviours. Due to the dynamic nature of human behaviours, continual learning promises HAR systems…

There has been significant focus on creating neuro-symbolic models for interpretable image classification using Convolutional Neural Networks (CNNs). These methods aim to replace the CNN with a neuro-symbolic model consisting of the CNN,…

Implicit Neural Networks (INRs) have emerged as powerful representations to encode all forms of data, including images, videos, audios, and scenes. With video, many INRs for video have been proposed for the compression task, and recent…

Recent neuro-symbolic approaches have successfully extracted symbolic rule-sets from CNN-based models to enhance interpretability. However, applying similar techniques to Vision Transformers (ViTs) remains challenging due to their lack of…