{"id":{"repo_id":"strathclyde","oai_identifier":"oai:strathclyde:rn301144t"},"canonical_url":"https://search.dev.ndltd.org/etd/strathclyde/oai:strathclyde:rn301144t","repository":{"repo_id":"strathclyde","name":"University of Strathclyde","base_url":"https://stax.strath.ac.uk/catalog/oai"},"display":{"title":"Real-time control of a robot using brain activity","abstract":"Background: Motor neuron disease (MND) describes a range of pathologies in which a person's voluntary muscle control becomes progressively impaired. Whether MND is on-set alone, or - as it commonly would be - paired with muscular atrophy, sufferers of the disease can face difficulty in establishing and maintaining their movement. These impediments, however, do not necessarily impinge on an individual's cognitive skills. MND, as well as other neurological diseases, such as atrophies and spinal cord injuries, affect neural pathways which may impair ones movement but spares the brain which may remain capable of performing cognitive tasks. Aim: This project aims to develop a proof-of-concept system: a small robot that can be controlled by brain activity through a brain-computer interface. The user will be able to have directional control over the robot. This platform would serve as a test bed for a device to be used by a neurologically impaired, cognitively intact person to communicate or control their environment. Method: The system interface will rely on a pseudo real-time input that is streaming from pre-recorded artefact-free electroencephalogram (EEG) signals. The system consists of mainly of two computing units: a transmitter (Tx) and a receiver (Rx). Tx will process the EEG signal and send a classification signal to the Rx unit. The receiver processes the signal so that the signal is classified into one of four distinct groups. Once classified, the receiver will transmit a control command to the receiver where it will be produce a respective output, thereby controlling the robot. Result: System operation transpires successfully with a latency of less than 160 ms; EEG processing in 40 ms and 118.5 ms from Bluetooth latency. Programmatic EEG classifications occur successfully to various extents and can be easily improves [sic] in future revisions.","abstract_html":"Background: Motor neuron disease (MND) describes a range of pathologies in which a person's voluntary muscle control becomes progressively impaired. Whether MND is on-set alone, or - as it commonly would be - paired with muscular atrophy, sufferers of the disease can face difficulty in establishing and maintaining their movement. These impediments, however, do not necessarily impinge on an individual's cognitive skills. MND, as well as other neurological diseases, such as atrophies and spinal cord injuries, affect neural pathways which may impair ones movement but spares the brain which may remain capable of performing cognitive tasks. Aim: This project aims to develop a proof-of-concept system: a small robot that can be controlled by brain activity through a brain-computer interface. The user will be able to have directional control over the robot. This platform would serve as a test bed for a device to be used by a neurologically impaired, cognitively intact person to communicate or control their environment. Method: The system interface will rely on a pseudo real-time input that is streaming from pre-recorded artefact-free electroencephalogram (EEG) signals. The system consists of mainly of two computing units: a transmitter (Tx) and a receiver (Rx). Tx will process the EEG signal and send a classification signal to the Rx unit. The receiver processes the signal so that the signal is classified into one of four distinct groups. Once classified, the receiver will transmit a control command to the receiver where it will be produce a respective output, thereby controlling the robot. Result: System operation transpires successfully with a latency of less than 160 ms; EEG processing in 40 ms and 118.5 ms from Bluetooth latency. Programmatic EEG classifications occur successfully to various extents and can be easily improves [sic] in future revisions.","abstract_has_math":false,"creators":["Roojee, Javed"],"institution":"University of Strathclyde","degree_name":"mres","degree_level":"masters-pg","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Lakany, Heba"],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017","date_published":"2017","updated_at":"2026-07-24T04:46:48Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.48730/jyvk-sr36"],"render_values":[{"text":"10.48730/jyvk-sr36","href":"https://doi.org/10.48730/jyvk-sr36","code":true}]},{"key":"dc:identifier","label":"Identifier","values":["T14950"],"render_values":[{"text":"T14950","href":null,"code":true}]},{"key":"dc:creator.authoridentifier","label":"Author Identifier","values":["201685486"],"render_values":[{"text":"201685486","href":null,"code":true}]}]},"links":{"outbound_url":"https://stax.strath.ac.uk/concern/theses/rn301144t","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lakany, Heba"]},{"key":"dc:creator","label":"Author","values":["Roojee, Javed"]},{"key":"dc:creator.authoridentifier","label":"Author Identifier","values":["201685486"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2017"]},{"key":"dc:date.issued","label":"Date","values":["2017"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Department of Biomedical Engineering"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Strathclyde"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["masters-pg"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["mres"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["T14950"]},{"key":"dc:identifier.doi","label":"DOI","values":["10.48730/jyvk-sr36"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://stax.strath.ac.uk/concern/theses/rn301144t"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Background: Motor neuron disease (MND) describes a range of pathologies in which a person's voluntary muscle control becomes progressively impaired. Whether MND is on-set alone, or - as it commonly would be - paired with muscular atrophy, sufferers of the disease can face difficulty in establishing and maintaining their movement. These impediments, however, do not necessarily impinge on an individual's cognitive skills. MND, as well as other neurological diseases, such as atrophies and spinal cord injuries, affect neural pathways which may impair ones movement but spares the brain which may remain capable of performing cognitive tasks. Aim: This project aims to develop a proof-of-concept system: a small robot that can be controlled by brain activity through a brain-computer interface. The user will be able to have directional control over the robot. This platform would serve as a test bed for a device to be used by a neurologically impaired, cognitively intact person to communicate or control their environment. Method: The system interface will rely on a pseudo real-time input that is streaming from pre-recorded artefact-free electroencephalogram (EEG) signals. The system consists of mainly of two computing units: a transmitter (Tx) and a receiver (Rx). Tx will process the EEG signal and send a classification signal to the Rx unit. The receiver processes the signal so that the signal is classified into one of four distinct groups. Once classified, the receiver will transmit a control command to the receiver where it will be produce a respective output, thereby controlling the robot. Result: System operation transpires successfully with a latency of less than 160 ms; EEG processing in 40 ms and 118.5 ms from Bluetooth latency. Programmatic EEG classifications occur successfully to various extents and can be easily improves [sic] in future revisions."]},{"key":"dc:description.abstract","label":"Abstract","values":["Background: Motor neuron disease (MND) describes a range of pathologies in which a person's voluntary muscle control becomes progressively impaired. Whether MND is on-set alone, or - as it commonly would be - paired with muscular atrophy, sufferers of the disease can face difficulty in establishing and maintaining their movement. These impediments, however, do not necessarily impinge on an individual's cognitive skills. MND, as well as other neurological diseases, such as atrophies and spinal cord injuries, affect neural pathways which may impair ones movement but spares the brain which may remain capable of performing cognitive tasks. Aim: This project aims to develop a proof-of-concept system: a small robot that can be controlled by brain activity through a brain-computer interface. The user will be able to have directional control over the robot. This platform would serve as a test bed for a device to be used by a neurologically impaired, cognitively intact person to communicate or control their environment. Method: The system interface will rely on a pseudo real-time input that is streaming from pre-recorded artefact-free electroencephalogram (EEG) signals. The system consists of mainly of two computing units: a transmitter (Tx) and a receiver (Rx). Tx will process the EEG signal and send a classification signal to the Rx unit. The receiver processes the signal so that the signal is classified into one of four distinct groups. Once classified, the receiver will transmit a control command to the receiver where it will be produce a respective output, thereby controlling the robot. Result: System operation transpires successfully with a latency of less than 160 ms; EEG processing in 40 ms and 118.5 ms from Bluetooth latency. Programmatic EEG classifications occur successfully to various extents and can be easily improves [sic] in future revisions."]},{"key":"dc:title","label":"Title","values":["Real-time control of a robot using brain activity"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lakany, Heba"],"dc:creator":["Roojee, Javed"],"dc:creator.authoridentifier":["201685486"],"dc:date":["2017"],"dc:date.issued":["2017"],"dc:description":["Background: Motor neuron disease (MND) describes a range of pathologies in which a person's voluntary muscle control becomes progressively impaired. Whether MND is on-set alone, or - as it commonly would be - paired with muscular atrophy, sufferers of the disease can face difficulty in establishing and maintaining their movement. These impediments, however, do not necessarily impinge on an individual's cognitive skills. MND, as well as other neurological diseases, such as atrophies and spinal cord injuries, affect neural pathways which may impair ones movement but spares the brain which may remain capable of performing cognitive tasks. Aim: This project aims to develop a proof-of-concept system: a small robot that can be controlled by brain activity through a brain-computer interface. The user will be able to have directional control over the robot. This platform would serve as a test bed for a device to be used by a neurologically impaired, cognitively intact person to communicate or control their environment. Method: The system interface will rely on a pseudo real-time input that is streaming from pre-recorded artefact-free electroencephalogram (EEG) signals. The system consists of mainly of two computing units: a transmitter (Tx) and a receiver (Rx). Tx will process the EEG signal and send a classification signal to the Rx unit. The receiver processes the signal so that the signal is classified into one of four distinct groups. Once classified, the receiver will transmit a control command to the receiver where it will be produce a respective output, thereby controlling the robot. Result: System operation transpires successfully with a latency of less than 160 ms; EEG processing in 40 ms and 118.5 ms from Bluetooth latency. Programmatic EEG classifications occur successfully to various extents and can be easily improves [sic] in future revisions."],"dc:description.abstract":["Background: Motor neuron disease (MND) describes a range of pathologies in which a person's voluntary muscle control becomes progressively impaired. Whether MND is on-set alone, or - as it commonly would be - paired with muscular atrophy, sufferers of the disease can face difficulty in establishing and maintaining their movement. These impediments, however, do not necessarily impinge on an individual's cognitive skills. MND, as well as other neurological diseases, such as atrophies and spinal cord injuries, affect neural pathways which may impair ones movement but spares the brain which may remain capable of performing cognitive tasks. Aim: This project aims to develop a proof-of-concept system: a small robot that can be controlled by brain activity through a brain-computer interface. The user will be able to have directional control over the robot. This platform would serve as a test bed for a device to be used by a neurologically impaired, cognitively intact person to communicate or control their environment. Method: The system interface will rely on a pseudo real-time input that is streaming from pre-recorded artefact-free electroencephalogram (EEG) signals. The system consists of mainly of two computing units: a transmitter (Tx) and a receiver (Rx). Tx will process the EEG signal and send a classification signal to the Rx unit. The receiver processes the signal so that the signal is classified into one of four distinct groups. Once classified, the receiver will transmit a control command to the receiver where it will be produce a respective output, thereby controlling the robot. Result: System operation transpires successfully with a latency of less than 160 ms; EEG processing in 40 ms and 118.5 ms from Bluetooth latency. Programmatic EEG classifications occur successfully to various extents and can be easily improves [sic] in future revisions."],"dc:identifier":["T14950"],"dc:identifier.doi":["10.48730/jyvk-sr36"],"dc:identifier.uri":["https://stax.strath.ac.uk/concern/theses/rn301144t"],"dc:publisher.department":["Department of Biomedical Engineering"],"dc:publisher.institution":["University of Strathclyde"],"dc:title":["Real-time control of a robot using brain activity"],"dc:type.qualificationlevel":["masters-pg"],"dc:type.qualificationname":["mres"]},"updated_at":"2026-07-24T04:46:48Z"}