Search Results for author:
Found 48 papers, 18 papers with code
Electrocardiogram-Language Model for Few-Shot Question Answering with Meta Learning
Electrocardiogram (ECG) interpretation requires specialized expertise, often involving synthesizing insights from ECG signals with complex clinical queries posed in natural language.
StatioCL: Contrastive Learning for Time Series via Non-Stationary and Temporal Contrast
However, existing CL methods often introduce false negative pairs (FNPs) by neglecting inherent characteristics and then randomly selecting distinct segments as dissimilar pairs, leading to erroneous representation learning, reduced model performance, and overall inefficiency.
RespLLM: Unifying Audio and Text with Multimodal LLMs for Generalized Respiratory Health Prediction
The high incidence and mortality rates associated with respiratory diseases underscores the importance of early screening.
Electrocardiogram Report Generation and Question Answering via Retrieval-Augmented Self-Supervised Modeling
Interpreting electrocardiograms (ECGs) and generating comprehensive reports remain challenging tasks in cardiology, often requiring specialized expertise and significant time investment.
Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking
Our pretrained models demonstrate superior performance (against existing acoustic models pretrained with general audio on 16 out of 19 tasks) and generalizability (to unseen datasets and new respiratory audio modalities).
FLea: Addressing Data Scarcity and Label Skew in Federated Learning via Privacy-preserving Feature Augmentation
Federated Learning (FL) enables model development by leveraging data distributed across numerous edge devices without transferring local data to a central server.
UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers
This limitation hinders the feasibility of many important on-device wearable event detection (WED) applications, such as heart attack detection.
Balancing Continual Learning and Fine-tuning for Human Activity Recognition
These schemes re-purpose contrastive learning for knowledge retention and, Kaizen combines that with self-training in a unified scheme that can leverage unlabelled and labelled data for continual learning.
FLea: Addressing Data Scarcity and Label Skew in Federated Learning via Privacy-preserving Feature Augmentation
Federated Learning (FL) enables model development by leveraging data distributed across numerous edge devices without transferring local data to a central server.
LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms
With respect to the state-of-the-art (SOTA) Meta CL method, LifeLearner drastically reduces the memory footprint (by 178. 7x), end-to-end latency by 80. 8-94. 2%, and energy consumption by 80. 9-94. 2%.
UDAMA: Unsupervised Domain Adaptation through Multi-discriminator Adversarial Training with Noisy Labels Improves Cardio-fitness Prediction
However, most healthcare datasets with high-quality (gold-standard) labels are small-scale, as directly collecting ground truth is often costly and time-consuming.
TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
On-device training is essential for user personalisation and privacy.
Heart Rate Extraction from Abdominal Audio Signals
Our evaluation shows for the first time that we can successfully extract HR from audio collected from a wearable on the abdomen.
Kaizen: Practical Self-supervised Continual Learning with Continual Fine-tuning
Kaizen is able to balance the trade-off between knowledge retention and learning from new data with an end-to-end model, paving the way for practical deployment of continual learning systems.
Cross-device Federated Learning for Mobile Health Diagnostics: A First Study on COVID-19 Detection
In this paper, we propose FedLoss, a novel cross-device FL framework for health diagnostics.
Turning Silver into Gold: Domain Adaptation with Noisy Labels for Wearable Cardio-Respiratory Fitness Prediction
Deep learning models have shown great promise in various healthcare applications.
Longitudinal cardio-respiratory fitness prediction through wearables in free-living environments
Cardiorespiratory fitness is an established predictor of metabolic disease and mortality.
Improving Feature Generalizability with Multitask Learning in Class Incremental Learning
Many deep learning applications, like keyword spotting, require the incorporation of new concepts (classes) over time, referred to as Class Incremental Learning (CIL).
YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers
In this paper, we propose YONO, a product quantization (PQ) based approach that compresses multiple heterogeneous models and enables in-memory model execution and switching for dissimilar multi-task learning on MCUs.
Enabling On-Device Smartphone GPU based Training: Lessons Learned
Deep Learning (DL) has shown impressive performance in many mobile applications.
A Summary of the ComParE COVID-19 Challenges
The COVID-19 pandemic has caused massive humanitarian and economic damage.
Enhancing the Security & Privacy of Wearable Brain-Computer Interfaces
Consequently, they are susceptible to a multiplicity of attacks across the hardware, software, and networking stacks used that can leak users' brainwave data or at worst relinquish control of BCI-assisted devices to remote attackers.
Exploring Longitudinal Cough, Breath, and Voice Data for COVID-19 Progression Prediction via Sequential Deep Learning: Model Development and Validation
Recent work has shown the potential of using audio data (eg, cough, breathing, and voice) in the screening for COVID-19.
Benchmarking Uncertainty Quantification on Biosignal Classification Tasks under Dataset Shift
A biosignal is a signal that can be continuously measured from human bodies, such as respiratory sounds, heart activity (ECG), brain waves (EEG), etc, based on which, machine learning models have been developed with very promising performance for automatic disease detection and health status monitoring.
Evaluating Contrastive Learning on Wearable Timeseries for Downstream Clinical Outcomes
Vast quantities of person-generated health data (wearables) are collected but the process of annotating to feed to machine learning models is impractical.
Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications
Our findings suggest that replay with exemplars-based schemes such as iCaRL has the best performance trade-offs, even in complex scenarios, at the expense of some storage space (few MBs) for training examples (1% to 5%).
Earables for Detection of Bruxism: a Feasibility Study
Bruxism is a disorder characterised by teeth grinding and clenching, and many bruxism sufferers are not aware of this disorder until their dental health professional notices permanent teeth wear.
Segmentation-free Heart Pathology Detection Using Deep Learning
Cardiovascular (CV) diseases are the leading cause of death in the world, and auscultation is typically an essential part of a cardiovascular examination.
High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm
Moreover, these pipelines are deterministic in nature, making them unable to capture predictive uncertainty.
Sounds of COVID-19: exploring realistic performance of audio-based digital testing
In this paper, we explore the realistic performance of audio-based digital testing of COVID-19.
Anticipatory Detection of Compulsive Body-focused Repetitive Behaviors with Wearables
Body-focused repetitive behaviors (BFRBs), like face-touching or skin-picking, are hand-driven behaviors which can damage one's appearance, if not identified early and treated.
FastICARL: Fast Incremental Classifier and Representation Learning with Efficient Budget Allocation in Audio Sensing Applications
Various incremental learning (IL) approaches have been proposed to help deep learning models learn new tasks/classes continuously without forgetting what was learned previously (i. e., avoid catastrophic forgetting).
Knowing when we do not know: Bayesian continual learning for sensing-based analysis tasks
Our experiments prove the robustness and reliability of the learned models to adapt to the changing sensing environment, and show the suitability of using uncertainty of the predictions to assess their reliability.
Modelling Urban Dynamics with Multi-Modal Graph Convolutional Networks
Relative to state-of-the-art deep learning models, our model reduces the RSME by ~ 28% in London and ~ 13% in Paris.
Modelling Cooperation and Competition in Urban Retail Ecosystems with Complex Network Metrics
Lastly, we build a supervised machine learning model to predict the impact of a given new venue on its local retail ecosystem.
Uncertainty-Aware COVID-19 Detection from Imbalanced Sound Data
To handle these issues, we propose an ensemble framework where multiple deep learning models for sound-based COVID-19 detection are developed from different but balanced subsets from original data.
The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates
The INTERSPEECH 2021 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the COVID-19 Cough and COVID-19 Speech Sub-Challenges, a binary classification on COVID-19 infection has to be made based on coughing sounds and speech; in the Escalation SubChallenge, a three-way assessment of the level of escalation in a dialogue is featured; and in the Primates Sub-Challenge, four species vs background need to be classified.
The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms
To meet the energy and latency requirements of these embedded platforms the framework is built from the ground up to provide predictive uncertainty based only on one forward pass and a negligible amount of additional matrix multiplications with theoretically proven correctness.
SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
Machine learning and deep learning have shown great promise in mobile sensing applications, including Human Activity Recognition.
Bayesian Pseudocoresets
Standard Bayesian inference algorithms are prohibitively expensive in the regime of modern large-scale data.
Exploring Contrastive Learning in Human Activity Recognition for Healthcare
Human Activity Recognition (HAR) constitutes one of the most important tasks for wearable and mobile sensing given its implications in human well-being and health monitoring.
Self-supervised transfer learning of physiological representations from free-living wearable data
Our contributions are two-fold: i) the pre-training task creates a model that can accurately forecast HR based only on cheap activity sensors, and ii) we leverage the information captured through this task by proposing a simple method to aggregate the learnt latent representations (embeddings) from the window-level to user-level.
Learning Generalizable Physiological Representations from Large-scale Wearable Data
To date, research on sensor-equipped mobile devices has primarily focused on the purely supervised task of human activity recognition (walking, running, etc), demonstrating limited success in inferring high-level health outcomes from low-level signals, such as acceleration.
$β$-Cores: Robust Large-Scale Bayesian Data Summarization in the Presence of Outliers
Modern machine learning applications should be able to address the intrinsic challenges arising over inference on massive real-world datasets, including scalability and robustness to outliers.
Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data
This work opens the door to further investigation of how automatically analysed respiratory patterns could be used as pre-screening signals to aid COVID-19 diagnosis.
Federated Principal Component Analysis
We present a federated, asynchronous, and $(\varepsilon, \delta)$-differentially private algorithm for PCA in the memory-limited setting.
Topic-Enhanced Memory Networks for Personalised Point-of-Interest Recommendation
Point-of-Interest (POI) recommender systems play a vital role in people's lives by recommending unexplored POIs to users and have drawn extensive attention from both academia and industry.
The architecture of innovation: Tracking face-to-face interactions with ubicomp technologies
The layouts of the buildings we live in shape our everyday lives.
Computers and Society Human-Computer Interaction Social and Information Networks
