pbarnaghi Goto Github PK

activity_patterns_digital_biomarker

A Digital Biomarker for Identifying Changes in Daily Activity Patterns

amdriot

A prediction-based data reduction method that exploits LMS adaptive filters in the Internet of Things

basic-ml-code

Basic ML code in python/mathlab

cancersymptomnetworks

Demo of my code and expirements on cancer symptoms and their symptom clusters. Please see the following site.

cml-ukdri

An introduction to the UTI risk analysis in people with dementia project at the Uk DRI Care Research and Technology Centre

continual_learning_papers

Relevant papers in Continual Learning

course-content

NMA Computational Neuroscience course

dcarte

Data ingestion tools to standardise data-driven analysis across data domains e.g., IoT, behavioural, physiological. (UK DRI Care Research & Technology)

entropy-analysis-pipeline

Code for the Entropy Pipeline

f-hmc

Implementation of folded Folded Hamiltonian Monte Carlo for data imputation and augmentation on data collected from cancer patients who self-reported their symptoms experience during chemotherapy by a team in the School of the Nursing University of California.

generative_ca

This project contains the implementation of using the generative models in continuous authentication on motion sensor data from the H-MOG dataset.

ieee-sig-tcbdin

IEEE SIG on Big Data Intelligent Networking

knowledge-acquisition-toolkit

The Knowledge Acquisition Tool (KAT) is a software toolkit that implements the state-of-the-art machine learning and data analytic methods for sensors data. The algorithms and methods implemented in KAT are used for processing and analysing the smart city data in the CityPulse project.

lagrangian-multipliers-roonak_rezvani

This work proposes a segmentation and aggregation method which represents time series frames as vectors by first applying Piecewise Aggregate Approximation (PAA) and then applying Lagrangian Multipliers. This method allows representing the continuous data as a series of patterns that can be used and processed by various higher-level methods.

lossadaptedplasticity

Code for the Loss Adapted Plasticity Algorithm

medtimeline

The MedTimeline library aims to provide a standardised process for pre-processing and generating patient journey timelines for the cardiology EHR dataset. Developed by Louise Rigny (Great Ormond Street Hospital for Children)

minder_utils

The library to access the UK DRI minder study data developed by Alex Capstick and Honglin Li.

ml4ns

Machine Learning for Neuroscience Module, Spring 2023 (https://www.imperial.ac.uk/study/courses/postgraduate-taught/translational-neuroscience/)

msc-briansciences

MSc Projects

neuralnet_plasticity

Basic code on synaptic plasticity in neural networks

non-conforming-sources

Code made available for paper on Non-Conforming Data Sources

pbarnaghi.github.io

sparc

Wellcome Trust Ideathon (Winner of Best Mental Health Entry) - This is an early stage and preliminary work to address the challenges of participant retention in long-term mental health clinical trials by providing researchers with estimation and guidance

task-conditional-neural-networks-tcnn_honglin_li

Task Conditional Neural Networks (TCNN) leverage the probabilistic neural networks to estimate the probability density of the training samples. Then produce the task likelihood during the test state to fire the task-specific neurons correspondin to the test sampels. TCNN can detect and learn the new tasks fully-automatically without informing the changes to the model.

tihm-dataset

TIHM: An open dataset for remote healthcare monitoring in dementia