- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Neural Networks and Applications
- Advanced Memory and Neural Computing
- Neuroscience and Neural Engineering
- Traffic Prediction and Management Techniques
- Muscle activation and electromyography studies
- Gaze Tracking and Assistive Technology
- Blind Source Separation Techniques
- Transportation Planning and Optimization
- Prosthetics and Rehabilitation Robotics
- Voice and Speech Disorders
- Functional Brain Connectivity Studies
- IoT and GPS-based Vehicle Safety Systems
- Neurobiology of Language and Bilingualism
- Robotic Locomotion and Control
- Phonetics and Phonology Research
- Vehicular Ad Hoc Networks (VANETs)
- Stroke Rehabilitation and Recovery
- Stuttering Research and Treatment
- Parkinson's Disease Mechanisms and Treatments
- Emotion and Mood Recognition
- Artificial Immune Systems Applications
- Modular Robots and Swarm Intelligence
- Assistive Technology in Communication and Mobility
Middlesex University
2013-2024
Middlesex University
2022-2023
University of Ulster
2009-2013
Indian Institute of Technology Kanpur
2011
A novel neural information processing architecture inspired by quantum mechanics and incorporating the well-known Schrodinger wave equation is proposed in this paper. The referred to as recurrent network (RQNN) can characterize a nonstationary stochastic signal time-varying packets. robust unsupervised learning algorithm enables RQNN effectively capture statistical behavior of input facilitates estimation embedded noise with unknown characteristics.
A major challenge in two-class brain-computer interface (BCI) systems is the low bandwidth of communication channel, especially while communicating and controlling assistive devices, such as a smart wheelchair or telepresence mobile robot, which requires multiple motion command options form forward, left, right, backward, start/stop. To address this, an adaptive user-centric graphical user referred to intelligent (iAUI) based on shared control mechanism proposed. The iAUI offers...
This paper discusses the nuances of a social robot, how and why robots are becoming increasingly significant, what they currently being used for. also reflects on current design as means interaction with humans reports potential solutions about several important questions around futuristic these robots. The specific explored in this are: “Do need to look like living creatures that already exist world for interact well them?”; have animated faces ability speak coherent human language them?”...
This paper presents the development of a Robot Operating System (ROS)-based mobile robot control using electromyography (EMG) signals. The proposed robot’s structure is specifically designed to provide modularity and controlled by Raspberry Pi 3 running on top an ROS application Teensy microcontroller. EMG muscle commands are sent with hand gestures that captured Thalmic Myo Armband recognized k-Nearest Neighbour (k-NN) classifier. performance evaluated navigating it through specific paths...
Brain-computer interface (BCI) technology is a means of communication that allows individuals with severe movement disability to communicate external assistive devices using the electroencephalogram (EEG) or other brain signals. This paper presents an alternative neural information processing architecture Schrödinger wave equation (SWE) for enhancement raw EEG signal. The signal obtained during motor imagery (MI) BCI user intrinsically embedded non-Gaussian noise while actual still mystery....
Background Predicting the course of Parkinson's disease is essential for prompt diagnosis and treatment, which may enhance patient outcomes. Objective This study presents a novel method prediction using freely accessible resources. The suggested approach starts with band-pass filter data preprocessing uses Empirical Mode Decomposition (EMD) feature extraction. Then, classification, these features are supplied into an Attention-based Efficient Bidirectional Network (ImCfO_Attn_EffBNet) based...
A filtering methodology inspired by the principles of quantum mechanics and incorporating well-known Schrodinger wave equation is investigated for first time EMG signals. This architecture, referred to as a Recurrent Quantum Neural Network (RQNN) can characterize non-stationary stochastic signal varying packets. An unsupervised learning rule allows RQNN capture statistical behaviour input facilitates estimation an embedded in noise with unknown characteristics. Results from number benchmark...
Electromyography (EMG) signals can be used to integrate with machines and form one assistive system such as a powered exoskeleton. This paper focuses on the design development of low-cost elbow joint exoskeleton for human power augmentation, controlled by EMG. Majority hardware has been designed developed in-house, without using expensively available hardware. A theoretical investigation starting from late 1960s up 2014 carried out. comparison actuators control systems that are commonly...
Swarm robotic systems are heavily inspired by observations of social insects. This often leads to robustness being viewed as an inherent property them. However, this has been shown not always be the case. Because this, fault detection and diagnosis in swarm is utmost importance for ensuring continued operation success swarm. paper provides overview recent work field exogenous robotics, focusing on four areas where research concentrated: immune system, data modelling, blockchain-based methods...
The brain-computer interface (BCI) technology is a means of communication that allows individuals with severe movement disability to communicate external assistive devices using the electroencephalogram (EEG) or other brain signals. human mind and mental processes are inherently quantum in nature. It therefore logical investigate possibility designing new approaches Brain-computer amalgamation classical approaches. This paper presents an intelligent information processing paradigm enhance...
This paper focuses on teaching control systems to engineering students through a blending of traditional lectures; student-focused problem-based self-directed learning projects and student presentations. Engineering field constantly evolves thus module should involve current state-of-the-art research trends. The work presented in this revolves around three miniprojects, each project different aspect be completed within 2 weeks each. aim these miniprojects is get acquainted with the practical...
The most common neurodegenerative diseases are Parkinson's disease. People who have reached the age of 70 or older affected. disease is second incurable illness after Almeria's numerous characteristics that distinguish between people with and those healthy, earlier diagnosis results in reduced severity. These typical signs disease, which include both motor non-motor deficiency patients. handwritten data set, includes spiral wave drawings, was retrieved from UCI equipment. EfficientnetB3...
The demand for passenger transportation, especially by road, has been increasing due to globalisation, resulting in further delays and traffic congestion. This paper addresses issues minimise congestion using source destination information an urban environment. A journey is defined as the traversal of several road links junctions. on are analysed M/M/K Markov technique. at a junction examined Zero-Server Chain In order study multiple junctions, this technique combined with Jackson Network...
A brain computer interface (BCI) allows a person to communicate with external devices using electroencephalogram (EEG) or other signals. typical BCI scheme consists of data acquisition, feature extraction and classification. Using the classifier output, control command is issued intended subject provided appropriate feedback. As part feedback, graphical user (GUI) plays very important role as front-end display for enhancing overall communication bandwidth. This paper focuses on design aspect...
A robotic arm and hand controlled by simulated neurons is presented. The robot makes use of a biological neuron simulator using point neural model. synapses are organised to create finite state automaton including inputs from sensors, outputs effectors. performs simple pick-and-place task. This work proof concept study for longer term approach. It hoped that further will lead more effective flexible robots. As another benefit, it also better understanding human other animal processing,...
The Izhikevich spiking neuron model is a relatively new mathematical framework which able to represent many observed behaviors, excitatory or inhibitory, by simply adjusting set of four parameters. This deterministic in nature and has achieved wide applications analytical numerical analysis biological neurons due largely its plausibility computational efficiency. In this work we present stochastic version the neuron, measure performance transmitting information range frequencies. reveals...