Transfer learning between deep neural networks using heterogeneous electrical biosignals.

• Ano de defesa: 2024
• Autor(a) principal: Santos, Andréa Leão Jesus Menezes dos
• Orientador(a): Oliveira, Luciano Rebouças de
• Banca de defesa: Oliveira , Luciano Rebouças de , Angelo, Michele Fúlvia , Ribeiro, Vinicius Gadis
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Instituição de defesa: Universidade Federal da Bahia
• Programa de Pós-Graduação: Programa de Pós-Graduação em Ciência da Computação (PGCOMP)
• Departamento: Instituto de Computação - IC
• País: Brasil
• Palavras-chave em Português: Transfer learning; Electrical biosignals; Recurrent neural network (RNN); Computação
• Área do conhecimento CNPq: CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: https://repositorio.ufba.br/handle/ri/41595

The global health systems are currently unable to adequately meet the high demand for care for people with neurological disorders. This impacts the quality of treatment offered, leading to issues such as the prescription of improper medications, difficulty accessing treatment, late detection of diseases, and more. Neurological disorders include conditions such as dementia, epilepsy, Alzheimer's, Parkinson's, multiple sclerosis, and others. To improve the treatment of these diseases, devices for the acquisition of electrical biosignals have been developed to provide greater accuracy, patient comfort, and, in some cases, lower costs. Recognizing this scenario, we aimed to investigate the possibility of using transfer learning among artificial neural networks to address these problems. Additionally, we attempted to reduce the mathematical complexity of electrical biosignal data by transforming it from time domain to frequency domain, representing it as algebraic functions rather than sine functions. Based on these ideas, we explored the potential of transfer learning to enhance the predictive accuracy of a neural network model processing diverse electrical biosignals with non-identical features and label spaces in a frequency domain. We integrated similarity analysis between biosignals into our methodology to prevent negative transfer learning using the dynamic time warping (DTW) technique. We selected the long short-term memory (LSTM) neural network to develop the proposed architecture, and the public datasets used for the experiment were the TUEG EEG Corpora (electroencephalogram), ECG Heartbeat Categorization (electrocardiogram), and EMG Classify Gestures (electroneuromyography). Using the baseline outcomes as a reference, we selected the ECG as the source domain. Then, we calculated the similarity between the biosignals, trained the model with the features identified as having the lowest distance, and transferred the weights and bias to the EEG and EMG models to process their own dataset, named the target domain. In summary, we present two scenarios to experiment and explore the potential of an effective transfer learning application with heterogeneous electrical biosignals in the frequency domain, from ECG to EMG and ECG to EEG, respectively. We discovered a promising outcome in the first scenario when the source and target datasets were balanced, even with a small target dataset. In the second context, we observed a discreet decrease in performance, also referred to as negative transfer learning, when utilizing a balanced source domain with an imbalanced and robust target dataset. Although we encountered some limitations, such as the high computational cost of calculating the similarity between the biosignals and the preprocessing strategy applied, among others detailed in this work, our experiment demonstrated the potential for transferring learning between neural networks processing heterogeneous electric biosignal datasets.