NtLab

Neurotechnology and Brain-Computer Interface Laboratory (NTLab)

We are dedicated to developing innovative solutions for individuals with reduced mobility and communication abilities. Our research focuses on the study, interpretation, and decoding of electrophysiological signals, with the aim of creating advanced brain-computer interfaces that enhance communication, mobility, rehabilitation, and treatment options for people with neurodegenerative and neurological diseases, as well as those affected by natural aging.

Research lines

Explore our core research areas in neurotechnology and rehabilitation

Understanding Neuro-Motor and Cognitive Mechanisms

In this research line, we aim to investigate neural and physiological signals, along with behavioral information, recorded during real-life situations such as grasping a bottle, walking, or driving a car. We design, implement, and execute experiments to collect data that is used to explore how the brain and body respond to daily-life activities and how these responses change and adapt due to neurodegenerative and neurological diseases, accidents, and the aging process

Research Focus

Neural signatures: Event related potentials, event related synchronization/desynchronization, connectivity, beta bursts
Wearable tech: Mobile brain-body imaging

Real-world validation: Home vs lab comparisons
Therapeutic targets: Identifying plasticity markers

We design controlled experiments in daily activities (e.g., robotic based rehabilitation, object manipulation, locomotion) while recording multimodal data:

Neural: EEG, fNIRS
Physiological: EMG, inertial sensors, eye tracking
Behavioral: Motion capture, task performance metrics

Methods

EEG/ERP Analysis Motion Capture Machine Learning

Biomedical Devices and Orthoses

In this research line, we focus on the design, construction, and testing of wearable devices for the evaluation of movement skills and the monitoring of motor symptoms associated with various clinical conditions such as amyotrophic lateral sclerosis and Parkinson’s disease. We also work on the implementation and validation of upper and lower limb orthotic devices aimed at facilitating and guiding movement recovery and rehabilitation interventions

Technology Development

Wearable sensors: Movement skill quantification
Symptom monitoring: Tremor, bradykinesia, fatigue
Upper limb: Hand/wrist orthoses

Lower limb: Gait-assist exoskeletons
Home-use: Remote monitoring systems

Our development pipeline integrates:

Mechanical design: 3D printing, lightweight composites
Actuation: Soft robotics, servo motors
Feedback systems: Real-time biofeedback algorithms

Clinical Applications

Parkinson's ALS Stroke Spinal Injury Motor declines

AI Methods for Biomedical Signal Decoding

In this research line, we apply machine learning and deep learning techniques to decode and extract motor information and cognitive states from neural and physiological signals. The aim is to enhance our ability to obtain information to provide fast and natural commands in BCI settings, and to interact naturally with assistive technologies for improved user experience and rehabilitative outcomes

Technical Approach

Motor decoding: EEG/EMG pattern recognition
Cognitive states: Attention/fatigue detection
Neural responses: ERP, ERDS, bursts, connectivity

Architectures: LDA, SVM, CNNs, RNNs

Innovation Focus

Developing user-independent models that maintain accuracy across patients with varying symptom severity.

Tech Stack

PyTorch TensorFlow

Neurorehabilitation and Neuroprosthetics

In this research line, we integrate and develop real-time brain-computer interface (BCI) solutions designed to improve mobility and provide rehabilitative treatments for individuals with impaired mobility due to neurodegenerative and neurological diseases, or for those with reduced motor skills caused by physical lesions or aging. We validate the usability of our developed systems in controlled settings with healthy participants and in clinical environments with patients