menu_book Explore the article's raw data

FedEmo: A Privacy-Preserving Framework for Emotion Recognition using EEG Physiological Data

Abstract

Emotions are intricate mental states triggered by neurophysiological adjustments linked to ideas, sensations, behavioral reactions, and a level of pleasure or annoyance. These changes are best traced with the physiological signal Electroencephalogram (EEG), as it records the direct sensations sent by the brain. Recent research on emotion classification methods employs conventional machine learning classifiers to access human emotions and perform automatic emotion recognition tasks. However, they lack in securing users' privacy and sensitive information because they need access to all data. A newly introduced framework Federated Learning (FL), can resolve this problem. It is an approach that aims to create a global model classifier without requiring access to users' local data. This study proposes a novel FL framework, Federated learning for Emotion recognition (FedEmo), for emotion state classification from physiological signal EEG while preserving users' data privacy. It uses Artificial Neural Network (ANN) as a baseline model for classifying emotional states: Arousal, Valence, and Dominance. Adding the concept of federated learning to build a framework FedEmo prevents loss of privacy as it enables the local training on the client's end with an updated model from the global server without compromising privacy. The proposed FedEmo framework approach achieves accuracies of 63.3%, 56.7%, and 52.2% for Valence, Arousal, and Dominance, respectively, using the well-known DREAMER dataset. These results are comparable to the basic centralized ANN model with the additional development of privacy preservation.

article Proceedings Paper

date_range 2023

language English

link Link of the paper

format_quote

Anwar Mohd

Agrawal Manan

Gahlan Neha

Sethia Divyashikha

Singh Gaurav

Chaurasia Rishabh

Sorry! There is no raw data available for this article.

Loading references...

Loading citations...

Featured Keywords

Emotion Recognition

Physiological signals

Federated Learning

Data Privacy

shopping_basket PURCHASE DATA

Assessment of reinforced concrete building damages following the Kahramanmaraş earthquakes in Malatya, Turkey (February 6, 2023)

Abstract

Earthquakes of magnitude Mw = 7.7 and Mw = 7.6 hit the city of Kahramanmaraş (Turkey) on 6 February 2023. These earthquakes caused serious damage in 11 provinces in Turkey resulting in over 50,000 deaths and huge economic losses with the collapse of thousands of buildings. Two consecutive devastating earthquakes have severely damaged the reinforced concrete building stock located in Malatya. There are many reasons reinforced concrete structures suffer damage under the influence of seismic loads. These reasons can be listed as material and section properties that do not comply with earthquake codes, workmanship defects, ground parameters that are not considered and design errors, as seen in field investigations after earthquakes in Turkey in the past. In this research, a field study was conducted on reinforced concrete buildings damaged after the earthquakes in Malatya province. The causes of structural damages in reinforced concrete buildings between 6–26 years of age were assessed in terms of design and material defects. The structural damages were mainly caused due to insufficient stirrups in structural members, short column, strong beam–weak column, failures of infill walls, soft story type collapse, poor concrete quality, and reinforcement corrosion. In addition to the field investigation, the spectrum relationships created using raw acceleration data obtained from DEMP (Disaster and Emergency Management Presidency) stations in Malatya province were compared with the design response spectra.

article Article

date_range 2024

language English

link Link of the paper

Collapsed buildings

Example 1 (jpg)