5 October 2022 in IEEE Transactions on Instrumentation and Measurement
In the field of neuroscience, brain activity measurement and analysis are considered crucial areas. Schizophrenia (Sz) is a brain disorder that severely affects thinking, behaviour, and feelings of people worldwide. Thus, an accurate and rapid detection method is needed for proper care and quality treatment of the patients. Electroencephalography (EEG) is proved to be an efficient biomarker in Sz detection as it records the brain activities. This paper aims to improve the performance of EEG-based Sz detection using a deep learning approach in remote applications. A hybrid deep learning model identified as SzHNN (Schizophrenia Hybrid Neural Network), which is a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) has been proposed wherein CNN for local feature extraction and LSTM for classification are utilized. In this paper, the proposed model has been compared with several deep-learning and machine learning-based models. All the models have been evaluated on two different datasets wherein dataset 1 consists of 19 subjects and dataset 2 consists of 16 subjects. The proposed model is also implemented with Internet of Medical Things (IoMT) framework for smart healthcare and remote-based applications. Several experiments have been conducted using various parametric settings on different frequency bands and different sets of electrodes on the scalp. Based on all the experiments, it is evident that the proposed hybrid model (SzHNN) provides the highest classification accuracy of 99.9% compared to other implemented models and existing models of previous papers. The proposed model overcomes the influence of different frequency bands and shows a better accuracy of 96.10%(dataset 1) and 91.00%(dataset 2) with only 5 electrodes. Subject-wise testing is also done for SzHNN, which proposes an accuracy of 90.11% and 89.60% for datasets 1 & 2, respectively.
10 July 2023 in IEEE Transactions on Instrumentation and Measurement
In recent years, advanced computing techniques have been investigated and employed for the computerized detection of brain disorders like schizophrenia. Schizophrenia is a neurological condition leading to hallucinations and disorganized speech in patients. Emerging deep-learning approaches can augment the computer-based diagnosis of this brain disorder by measuring and analyzing the Electroencephalography (EEG) signals. This paper proposes a novel concept of easy-to-wear cap, namely SczCap, integrating hardware and software for acquiring EEG signals from the scalp for accurate schizophrenia detection. In this research, A seven-layer model comprising of convolution neural network (CNN) and temporal convolution network (TCN) is designed and tested using raw EEG data (approach 1) and manually extracted features (approach 2). Three pre-trained models, VGG 16, AlexNet, and ResNet 50, along with the proposed model, have also been implemented in this work. A dataset consisting of EEG signals of 14 healthy and 14 schizophrenic patients is used in this work for the implementations. The performance of the proposed CNN-TCN model (approach 1 & 2) is also presented using non-subject-wise and subject-wise experiments. It is found that the proposed CNN-TCN model using approach 1 outperformed all other implemented models with 99.57% accuracy, 99.51% sensitivity, 99.64% specificity, and 99.63% precision in non-subject-wise experiments. The experimental results also exhibit the superiority of this model over other schizophrenia models in the state of art literature.
25 July 2022 in SN Computer Science
5 September 2020 in International Journal of Information Technology
8 April 2022 in Journal of Circuits, Systems and Computers
12 August 2024 in SN Computer Science