Posts by Collection

portfolio

publications

Published in , 1900

A combination of transductive and inductive learning for handling non-stationarities in motor imagery classification.

Published in International Joint Conference on Neural Networks (IJCNN), 2016, 2016

This paper is proposes a combination of transductive and inductive learning for managing non-stationarity in EEG-based BCI

Recommended citation: Raza, H., Cecotti, H., and Prasad, G. (2016). "A combination of transductive and inductive learning for handling non-stationarities in motor imagery classification." IEEE-IJCNN, 2016. 1(1).

Published in , 1900

Current source density estimation enhances the performance of motor-imagery-related brain–computer interface.

Published in IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017

This paper is about CSD pre-processing method for enhanceing the performance of motor-imagery-related brain–computer interface.

Recommended citation: Rathee, D., Raza., H., Prasad, G., and Cecotti, H. (2017). "Current source density estimation enhances the performance of motor-imagery-related brain–computer interface." IEEE-TNSRE, 2017. 25(12), 2461 - 2471.

Identification of predictors of objectively measured physical activity in 12-month-old British infants: a machine learning driven study.

Published in The Lancet, 2017

This paper is about finding predictors of objectively measured physical activity in 12-month-old British infants

Recommended citation: Raza, H., Zhou, SM., Hill, R., Lyons, RA., Brophy, S. (2017). "Identification of predictors of objectively measured physical activity in 12-month-old British infants: a machine learning driven study." The Lancet, 2017. 390, S74.

Online Covariate Shift Detection based Adaptive Brain-Computer Interface to Trigger Hand Exoskeleton Feedback for Neuro-Rehabilitation.

Published in IEEE Transactions on Cognitive and Developmental Systems, 2017

This paper is about detecting covariate shift and adaption in an online BCI system.

Recommended citation: Chowdhury, A., Raza., H., Meena, Y.K., Dutta, A., and Prasad,G. (2017). "Online Covariate Shift Detection based Adaptive Brain-Computer Interface to Trigger Hand Exoskeleton Feedback for Neuro-Rehabilitation." IEEE-TCDS-2017. 1(1).

Published in , 1900

Covariate Shift Estimation and Adaptation based Ensemble Learning for Handling Inter-or-Intra Session Non- Stationarity in EEG based Brain-Computer Interface

Published in Neurocomputing, 2018

This paper is about the adapting non-stationarity in EEG signals using ensemble learning methods.

Recommended citation: Raza, H., Rathee, D., Zhou, SM., Cecotti, H., and Prasad, G. (2018). Covariate Shift Estimation and Adaptation based Ensemble Learning for Handling Inter-or-Intra Session Non- Stationarity in EEG based Brain-Computer Interface.; Neurocomputing, 2018.

Active Physical Practice Followed by Mental Practice Using BCI-Driven Hand Exoskeleton: A Pilot Trial for Clinical Effectiveness and Usability

Published in IEEE Journal of Biomedical and Health Informatics, 2018

This paper is about the BCI-driven handexoskeleton trails conducted on stroke participants.

Recommended citation: Chowdhury, A., Meena, YK., Raza, H., Bhushan, B., Uttam, AK., Pandey, N., Hashmi, AA., Bajpai, A., Dutta, A., and Prasad, G. (2018). Active Physical Practice Followed by Mental Practice Using BCI-Driven Hand Exoskeleton: A Pilot Trial for Clinical Effectiveness and Usability. IEEE Journal of Biomedical and Health Informatics, 2018.

An EEG-EMG correlation-based brain-computer interface for hand orthosis supported neuro-rehabilitation

Published in Journal of neuroscience methods, 2019

In this study, we have introduced a new corticomuscular feature extraction method based on the correlation between band-limited power time-courses (CBPT) associated with EEG and EMG. 16 healthy individuals and 8 hemiplegic patients participated in a BCI-based hand orthosis triggering task, to test the performance of the CBPT method. The healthy population was equally divided into two groups; one experimental group for CBPT-based BCI experiment and another control group for EEG-EMG coherence based BCI experiment.

Recommended citation: Chowdhury, A., Raza, H., Meena, YK., Dutta, A., and Prasad, G. (2019). An EEG-EMG correlation-based brain-computer interface for hand orthosis supported neuro-rehabilitation. Journal of neuroscience methods, 2019.

Predictors of Objectively Measured Physical Activity in 12 month-Old Infants: A Study of Linked Birth Cohort Data with Electronic Health Records

Published in Paediatric Obesity, 2019

This paper examines factors associated with PA levels in 12‐month infants.

Recommended citation: Raza, H., Zhou, S., Todd, S., Christian, D., Merchant, E., Morgan, K., Khanom, A., Hill, R., Lynos, R., and Brophy, S. Predictors of objectively measured physical activity in 12‐month‐old infants: A study of linked birth cohort data with electronic health records. Pediatric obesity, p.e12512..

research

talks

Machine Learning and Brain-Computer Interface

Published:

This talk was focused on Brain-Computer interfaceing. Brain-computer interface (BCI) is a collaboration between a brain and a device that enables signals from the brain to direct some external activity, such as control of a cursor or a prosthetic limb. The interface enables a direct communications pathway between the brain and the object to be controlled. I have discussed my research done during my PhD and Post-Doc.

Artificial Intelligence and its application in Brain-Computer Interface

Published:

This talk was focused on Brain-Computer interfaceing. Brain-computer interface (BCI) is a collaboration between a brain and a device that enables signals from the brain to direct some external activity, such as control of a cursor or a prosthetic limb. The interface enables a direct communications pathway between the brain and the object to be controlled. I have discussed my research done during my PhD and Post-Doc.

Non-Stationary Learning in EEG-based Brain-Computer Interface

Published:

A common assumption in traditional supervised learning is the similar probability distribution of data between the training phase and the testing/operating phase. When transitioning from the training to testing phase, a shift in the probability distribution of input data is known as a covariate shift. Covariate shifts commonly arise in a wide range of real-world systems such as electroencephalogram-based brain–computer interfaces (BCIs). In such systems, there is a necessity for continuous monitoring of the process behavior, and tracking the state of the covariate shifts to decide about initiating adaptation in a timely manner. This talk focused on discussing methods to adapt to covariate shift.

Learning Under Dataset Shifts

Published:

Dataset shift is a challenging situation where the joint distribution of inputs and outputs differs between the training and test stages. Covariate shift is a simpler particular case of dataset shift where only the input distribution changes (covariate denotes input), while the conditional distribution of the outputs given the inputs p(y|x) remains unchanged. Dataset shift is present in most practical applications or reasons ranging from the bias introduced by experimental design, to the mere irreproducibility of the testing conditions at training time. For example, in an image classification task, training data might have been recorded under controlled laboratory conditions, whereas the test data may show different lighting conditions.

Machine Learning and Data Science

Published:

The Data Science Intensive (DSI) program is an 8-week hands-on skills training data science course based on solving real-world problems. I have spent two week to deliver first session of this DSI program. I have focused to present on the following topics and we competed on a Kaggle dataset: Advance House Price Prediction

Data Analysis and Predictive Analytics : Southend-on-Sea Borough Council (2-Days)

Published:

This talk tutorial covered Data Analysis and Predictive Analytics using R and R-Studio. In this training delegates were introduced to key R-packages for data visualisation, e.g.in terms of graphs and charts. We have also covered data loading from spreadsheets, data cleaning, feature-preparation, and training a basic predictive model. This workshop covered industry-led examples throughout. It was aimed that delegates having basic knowledge about R from the previous training.

teaching

Data Science and Decision Making

Spring Term (2018): Postgraduate (MSc), University of Essex, 2018

The aim of this module is to familiarise students with the whole pipeline of processing, analysing, presenting and making decisions using data. This is a research-led, MSc level course, where students are expected to develop a complete end-to-end data science application. The course blends data analysis, decision making and visualisation with practical python programming. The module assumes a reasonable programming background and is not suitable for students without prior programming experience.

Data Science and Decision Making

Spring Term (2019): Postgraduate (MSc), University of Essex, 2019

The aim of this module is to familiarise students with the whole pipeline of processing, analysing, presenting and making decisions using data. This is a research-led, MSc level course, where students are expected to develop a complete end-to-end data science application. The course blends data analysis, decision making and visualisation with practical python programming. The module assumes a reasonable programming background and is not suitable for students without prior programming experience.

Data Science and Decision Making

Spring Term (2020): Postgraduate (MSc), University of Essex, 2020

The aim of this module is to familiarise students with the whole pipeline of processing, analysing, presenting and making decisions using data. This is a research-led, MSc level course, where students are expected to develop a complete end-to-end data science application. The course blends data analysis, decision making and visualisation with practical python programming. The module assumes a reasonable programming background and is not suitable for students without prior programming experience. We are going to use Python programming in this module.