Bubble-Wave-Mitigation Algorithm and Transformer-Based Neural Network Demodulator for Water-Air Optical Camera Communications

Li, Maolin; Ling, Peng; Wen, Shangsheng; Chen, Xiandong; Wen, Fei

doi:10.1109/jphot.2023.3302690

Cited by 4 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, CNNs have gained popularity and have been widely employed as a deep neural network technique in various applications such as medical diagnosis [26], optical camera communication [27], and road classification [28]. CNNs consist of three primary feature layers: convolutional, pooling, and fully connected layers, with an additional layer known as the activation function layer.…”

Section: Convolutional Neural Network Modelmentioning

confidence: 99%

An Efficient EEG Signal Analysis for Emotion Recognition Using FPGA

Ezilarasan,

Leung

2024

Information

View full text Add to dashboard Cite

Electroencephalography (EEG), electromyography (EMG), galvanic skin response (GSR), and electrocardiogram (ECG) are among the techniques developed for collecting psychophysiological data from humans. This study presents a feature extraction technique for identifying emotions in EEG-based data from the human brain. Independent component analysis (ICA) was employed to eliminate artifacts from the raw brain signals before applying signal extraction to a convolutional neural network (CNN) for emotion identification. These features were then learned by the proposed CNN-LSTM (long short-term memory) algorithm, which includes a ResNet-152 classifier. The CNN-LSTM with ResNet-152 algorithm was used for the accurate detection and analysis of human emotional data. The SEED V dataset was employed for data collection in this study, and the implementation was carried out using an Altera DE2 FPGA development board, demonstrating improved performance in terms of FPGA speed and area optimization.

show abstract

Section: Convolutional Neural Network Modelmentioning

confidence: 99%