Emotion detection from EEG data using Neurosity Crown

Exploring Neuroscience and EEG Technology

In my journey through the field of neurotechnology, I delved into foundational concepts of neuroscience, focusing on the intricate workings of the brain and its functionalities. This exploration included a detailed understanding of EEG (Electroencephalography) frequency bands—alpha, beta, gamma, theta, and delta—and their correlation with various brain states. Additionally, I gained insights into the standard EEG electrode configurations, specifically the 10-20 system, and the nuances of EEG signal processing using techniques like FIR filters, frequency spectrum analysis, and band power calculation.

This comprehensive understanding enabled me to interpret the technical terminology used in neuroscience-related domains and further investigate advanced EEG technologies. I explored phenomena such as Event-Related Potentials (ERP), Evoked Potentials (EP), and artifacts caused by eye (EOG) and muscle (EMG) movements. Notably, I conducted an experiment that revealed a distinct correlation between eye blinks and spikes in EEG signals, enhancing my grasp of signal analysis.

Neuromarketing using EEG

In this work, we propose a deep neural network, NMNet, to predict consumer preferences for E-commerce products by analyzing neural activity captured through EEG signals. Our approach utilizes a transformer-based model to extract features from EEG signals in both the temporal and spatial domains. We evaluate our approach using a dataset consisting of 1050 EEG signals collected from 25 participants. We compare our approach against the existing baseline and consistently outperform across all evaluation metrics. In order to assess the generalization ability of our proposed method, we employ a diverse set of stimuli during the evaluation phase. This enables us to thoroughly evaluate the performance of our method across a range of different stimuli, providing valuable insights into its effectiveness and adaptability. 

Published paper:

Upadhyay. A, et.al,. 2024. NMNet: Spatial-Temporal Transformer for EEG Signal Analysis in Neuromarketing. In Proceedings of the 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD) (CODS-COMAD '24).

Reports published:

Tech Scan of EEG Devices

As part of my project, I conducted an extensive evaluation of commercially available EEG headsets, documenting their features and comparing them across various parameters, including the number of electrodes, placement, data output, and battery life. This effort culminated in a published report, where I provided an overview of essential EEG terminologies and concepts crucial for selecting EEG headsets. The report offered a comprehensive guide on factors to consider when choosing an EEG device and presented a comparative analysis of 11 different EEG headsets, aiding in informed decision-making.

Use-Cases of EEG Technology

With the procurement of the Neurosity Crown EEG headset, I explored diverse use-cases of EEG technology across sectors such as medical, neuromarketing, wellness, art, and entertainment. This exploration led to a detailed report, highlighting the potential of EEG in various industries. I provided a primer on the data extractable from EEG signals and elaborated on the applications of EEG in these sectors. The report concluded with my perspectives on the future of EEG technology, underscoring its growing significance and applications.

Tech Scan of EEG Software and Tools

I completed an extensive exploration of open-source and free software tools for EEG data visualization, analysis, processing, and recording. This study culminated in a detailed report published, providing a comprehensive guide on the best software solutions available for EEG research. The report evaluates various tools based on their functionalities, user interfaces, and data handling capabilities, offering valuable insights for researchers and developers in the EEG space.