Multimodal MRI–EEG fusion for brain–computer interface applications using a lightweight CNN and attention in offline Parkinson’s disease diagnosis

Cardiac disorders are a leading cause of global casualties, emphasizing the need for the initial diagnosis and prevention of cardiovascular diseases (CVDs). Electrocardiogram (ECG) procedures are highly recommended as they provide crucial cardiology information. Telemedicine offers an opportunity to provide low-cost tools and widespread availability for CVD management. In this research, we proposed an IoT-based monitoring and detection system for cardiac patients, employing a two-stage approach. In the initial stage, we used a routing protocol that combines routing by energy and link quality (REL) with dynamic source routing (DSR) to efficiently collect data on an IoT healthcare platform. The second stage involves the classification of ECG images using hybrid-based deep features. Our classification system utilizes the “ECG Images dataset of Cardiac Patients”, comprising 12-lead ECG images with four distinct categories: abnormal heartbeat, myocardial infarction (MI), previous history of MI, and normal ECG. For feature extraction, we employed a lightweight CNN, which automatically extracts relevant ECG features. These features were further optimized through an attention module, which is the method’s main focus. The model achieved a remarkable accuracy of 98.39%. Our findings suggest that this system can effectively aid in the identification of cardiac disorders. The proposed approach combines IoT, deep learning, and efficient routing protocols, showcasing its potential for improving CVD diagnosis and management.

Blood cell classification and counting are vital for the diagnosis of various blood-related diseases, such as anemia, leukemia, lymphoma, and thrombocytopenia. The manual process of blood cell classification and counting is time-consuming, prone to errors, and labor-intensive. Therefore, we have proposed a deep learning (DL)-based automated system for blood cell classification and counting from microscopic blood smear images. We classify a total of nine types of blood cells, including Erythrocyte, Erythroblast, Neutrophil, Basophil, Eosinophil, Lymphocyte, Monocyte, Immature Granulocytes, and Platelet. Several preprocessing steps like image resizing, rescaling, contrast enhancement and augmentation are utilized. To segment the blood cells from the entire microscopic images, we employed the U-Net model. This segmentation technique aids in extracting the region of interest (ROI) by removing complex and noisy background elements. Both pixel-level metrics such as accuracy, precision, and sensitivity, and object-level evaluation metrics like Intersection over Union (IOU) and Dice coefficient are considered to comprehensively evaluate the performance of the U-Net model. The segmentation model achieved impressive performance metrics, including 98.23% accuracy, 98.40% precision, 98.26% sensitivity, 95.97% Intersection over Union (IOU), and 97.92% Dice coefficient. Subsequently, a watershed algorithm is applied to the segmented images to separate overlapped blood cells and extract individual cells. We have proposed a BloodCell-Net approach incorporated with custom light weight convolutional neural network (LWCNN) for classifying individual blood cells into nine types. Comprehensive evaluation of the classifier’s performance is conducted using metrics including accuracy, precision, recall, and F1 score. The classifier achieved an average accuracy of 97.10%, precision of 97.19%, recall of 97.01%, and F1 score of 97.10%. A 5-fold cross-validation technique is applied to split the data, which not only aids in reducing overfitting but also helps in generalizing the model.

SLViT: Shuffle-convolution-based lightweight Vision transformer for effective diagnosis of sugarcane leaf diseases

In recent years, brain computer interfaces (BCIs) have gained popularity in non-medical domains such as the gaming, entertainment, personal health, and marketing industries. A growing number of companies offer various inexpensive consumer grade BCIs and some of these companies have recently introduced the concept of BCI "App stores" in order to facilitate the expansion of BCI applications and provide software development kits (SDKs) for other developers to create new applications for their devices. The BCI applications access to users' unique brainwave signals, which consequently allows them to make inferences about users' thoughts and mental processes. Since there are no specific standards that govern the development of BCI applications, its users are at the risk of privacy breaches. In this work, we perform first comprehensive analysis of BCI App stores including software development kits (SDKs), application programming interfaces (APIs), and BCI applications w.r.t privacy issues. The goal is to understand the way brainwave signals are handled by BCI applications and what threats to the privacy of users exist. Our findings show that most applications have unrestricted access to users' brainwave signals and can easily extract private information about their users without them even noticing. We discuss potential privacy threats posed by current practices used in BCI App stores and then describe some countermeasures that could be used to mitigate the privacy threats. Also, develop a prototype which gives the BCI app users a choice to restrict their brain signal dynamically.

In recent years, Brain-Computer Interfaces (BCIs) have gained popularity in non-medical domains such as the gaming, entertainment, personal health, and marketing industries. A growing number of companies offer various inexpensive consumer grade BCIs and some of these companies have recently introduced the concept of BCI "App stores" in order to facilitate the expansion of BCI applications and provide software development kits (SDKs) for other developers to create new applications for their devices. The BCI applications access to users' unique brainwave signals, which consequently allows them to make inferences about users' thoughts and mental processes. Since there are no specific standards that govern the development of BCI applications, its users are at the risk of privacy breaches. In this work, we perform first comprehensive analysis of BCI App stores including software development kits (SDKs), application programming interfaces (APIs), and BCI applications w.r.t privacy issues. The goal is to understand the way brainwave signals are handled by BCI applications and what threats to the privacy of users exist. Our findings show that most applications have unrestricted access to users' brainwave signals and can easily extract private information about their users without them even noticing. We discuss potential privacy threats posed by current practices used in BCI App stores and then describe some countermeasures that could be used to mitigate the privacy threats.

One of the earliest methods to observe the brain dynamic is through Electroencephalogram (EEG) brain signal. It is widely known as a non-invasive, reliable, and affordable way of recording the brain activities. It has become the most wanted way of diagnosis and treatment for mental and brain neurogenerative diseases and abnormalities. It also one of the most appropriate signals in Brain-Computer Interfaces (BCI) applications. BCI frequently used by neuromuscular disorder (post-stroke) patients to aid them in activities of daily living (ADL). In this study, the adequacy of various TL models, i.e., NasNetMobile, and NasNetLarge in extracting features to classify wink-based EEG signals were investigated. The time-frequency scalogram conversion of the Right Wink, Left Wink, and No Wink based on EEG signals was carried out through Continuous Wavelet Transform (CWT) algorithm. The features that were extracted through Transfer Learning (TL) models were fed into a number of k-Nearest Neighbors (kNN) classifier models to determine the performance of various feature extraction methods to classify the winking signals. The input data are divided into training, validation, and testing datasets via a stratified ratio of 60:20:20. It was shown through this study, that the features extracted by means of NasNetLarge were more efficient compared with NasNetMobile. The Classification Accuracy (CA) of training dataset through NasNetLarge pipeline is 98% which was higher compared to NasNetMobile through the kNN model which consists of k-value of 2 and Minkowski Distance. The validation and testing CA attained through NasNetMobile and NasNetLarge models are 100%. Therefore, it could be concluded that the proposed pipeline which consists of CWT-NasNetLarge-kNN is suitable to be adopted to classify wink-based EEG signals for different BCI applications.

Parkinson's disease (PD) is a common neurodegenerative disease, whose main features include movement disorders, cognitive impairment and other non-motor symptoms. With the aging of the population, the incidence of PD has increased year by year, seriously affecting the quality of life of patients. At present, although treatments such as levodopa, deep brain stimulation (DBS) and rehabilitation training can relieve some symptoms, it is difficult to prevent the progression of the disease, and the demand for personalized treatment is increasing. Therefore, neuroregulatory technology based on brain-computer interface (BCI) has become an important research direction in the diagnosis and treatment of PD. BCI technology has shown important application value in disease diagnosis, motor function rehabilitation and cognitive intervention of PD. BCI technology based on electroencephalogram (EEG) can be used to detect abnormal EEG signal patterns in PD patients and assist in early screening of the disease; combined with neuroregulatory technology (such as transcranial magnetic stimulation TMS and functional electrical stimulation FES), BCI can effectively improve the motor function of PD patients. However, the current application of BCI in PD still faces challenges such as insufficient signal decoding accuracy, unstable data quality and poor patient adaptability. Therefore, this article reviews the latest research progress of BCI in the field of PD diagnosis and treatment, and explores its technical bottlenecks and future development directions, in order to provide valuable reference for research in this field.

Brain-computer interface (BCI) technology is an innovative human-computer interaction technology that does not rely on the peripheral nerve transmission pathway and muscle tissues, and establishes the connection between the human brain and the external machine. BCI system includes three categories: active, reactive and passive, with the motor imagery brain-computer interface (MI-BCI) is the most common active BCI system. MI-BCI controls external devices by imagining movements in the brain, without actually having to perform the movement. In order to bring more immersion to patients, the introduction of augmented reality (AR) technology can increase the interest of patients and improve the concentration on rehabilitation training. This study reviews the overview of BCI technology, the application of MI-BCI technology in the rehabilitation of nervous system diseases, and the limitations and prospects applications of MI-BCI technology in the rehabilitation of nervous system diseases, so as to provide reference for the application of MI-BCI technology in the diagnosis and rehabilitation of nervous system diseases. Specifically, the overview of BCI technology mainly introduces BCI technology, MI-BCI technology and AR-MI-BCI rehabilitation training system (the process and overall structure of the AR-MI-BCI rehabilitation training system). MI-BCI system has many applications in neurological diseases such as stroke, drug addiction and depression, which can not only effectively assist the diagnosis of neurological diseases, but also activate specific brain regions to promote brain function rehabilitation. MI-BCI system can identify the motor imagery intention of stroke patients and guide them to actively imagine body movements, which is helpful for active rehabilitation of patients. To address the poor generalization issues in traditional machine learning algorithms at the individual level of stroke patients, MI-BCI rehabilitation training system is built on the transfer learning technology. The rehabilitation training system based on AR-MI-BCI can assist drug users to reduce drug addiction and the difficult withdrawal of mental dependence and physical dependence caused by drug abuse, and make drug users have a connection between drugs and resistance emotion. EEG recognition scheme based on MI-BCI multi-frequency brain network can assist in the diagnosis of depression, but MI-BCI technology has some shortcomings in terms of technical development, device cost, patient privacy and clinical application.

The aim of this study was to develop a Brain Computer Interface (BCI) application to control domotic devices usually present at home. Previous studies have shown that people with severe disabilities, both physical and cognitive ones, do not achieve high accuracy results using motor imagery-based BCIs. To overcome this limitation, we propose the implementation of a BCI application using P300 evoked potentials, because neither extensive training nor extremely high concentration level are required for this kind of BCIs. The implemented BCI application allows to control several devices as TV, DVD player, mini Hi-Fi system, multimedia hard drive, telephone, heater, fan and lights. Our aim is that potential users, i.e. people with severe disabilities, are able to achieve high accuracy. Therefore, this domotic BCI application is useful to increase

The Common Spatial Pattern (CSP) method is a powerful technique for feature extraction from multichannel neural activity and widely used in brain computer interface (BCI) applications. By linearly combining signals from all channels, it maximizes variance for one condition while minimizing for the other. However, the method overfits the data in presence of dense recordings and limited amount of training data. To overcome this problem we construct a sparse CSP (sCSP) method such that only subset of channels contributes to feature extraction. The sparsity is achieved by a greedy search based generalized eigenvalue decomposition approach with low computational complexity. Our contributions in this study are extension of the greedy search based solution to have multiple sparse filters and its application in a BCI problem. We show that sCSP outperforms traditional CSP in the classification challenge of the multichannel ECoG data set of BCI competition 2005. Furthermore, it achieves nearly similar performance as infeasible exhaustive search and better than that of obtained by LI norm based sparse solution.

Rehabilitation medicine has developed rapidly in recent years. Brain computer interface and functional electrical stimulation are very cutting-edge technologies in this field. Because brain computer interface provides a real-time operation platform for patients to operate their limbs according to their intention for functional electrical stimulation, the research on BCI based FES has gradually increased in recent years. This paper discusses the current development status and technical application of FES and BCI. The research status of BCI based FES is discussed, and the existing problems of various research are summarized. According to the research findings, this field is a new technology with great application prospects in the field of modern rehabilitation engineering.

Brain-Computer Interface (BCI) research and (future) applications raise important ethical issues that need to be addressed to promote societal acceptance and adequate policies. Here we report on a survey we conducted among 145 BCI researchers at the 4th International BCI conference, which took place in May–June 2010 in Asilomar, California. We assessed respondents’ opinions about a number of topics. First, we investigated preferences for terminology and definitions relating to BCIs. Second, we assessed respondents’ expectations on the marketability of different BCI applications (BCIs for healthy people, BCIs for assistive technology, BCIs-controlled neuroprostheses and BCIs as therapy tools). Third, we investigated opinions about ethical issues related to BCI research for the development of assistive technology: informed consent process with locked-in patients, risk-benefit analyses, team responsibility, consequences of BCI on patients’ and families’ lives, liability and personal identity and interaction with the media. Finally, we asked respondents which issues are urgent in BCI research.

The brain signals are generally measured by Electroencephalogram (EEG) in Brain-Computer Interface (BCI) applications. In motor imagery-based BCI, the performed MI tasks (e.g., imagined hand movement) are identified through a classification algorithm to communicate and control the device. Consequently, improving the performance of the classifier is crucial to the success of the BCI system. One of the most popular linear classifier in BCI applications is the Support Vector Machine (SVM). This paper improves the performance of MI-based BCI by finding the optimum free kernel parameters of the SVM classifier. A real-coded genetic algorithm is utilized to determine the free kernel parameters of the SVM. The performance of this method is evaluated using publicly available BCI Competition IV dataset IIa for right and left hand motor imagery tasks. The results show that using real-valued GA-based SVM with Polynomial or Gaussian kernel improves the average accuracy over nine subjects compared with the baseline (i.e., the grid search method). Hence, using automated method (GA) helps us in improving the performance of the MI-based BCI especially for subjects with poor performance.

Electroencephalogram (EEG) is the most convenient method for recording the electrical activities of the brain, for Brain Computer Interface (BCI) applications. This EEG data is notoriously noisy. A variety of frequency estimation techniques are used in feature extraction . This is possible due to the presence of information of interest in frequency bands which are well defined. The application of EMD (Empirical Mode Decomposition) on the recorded EEG waves of subjects’, renders time-frequency data depicting instantaneous frequencies. EMD is chosen to obtain Hilbert–Huang Transform (HHT) of the data which is chosen over Fourier Transform (FT) owing to the nonstationarity, closely spaced frequency bands of interest and low SNR of the recorded data. HHT of the data can be used to obtain a feature or signature, which can be used as a command signal for various BCI applications.

Steady State Visual Evoked Potential (SSVEP) has been commonly adopted in Brain Computer Interface (BCI) applications. For wearable BCI applications, several aspects of SSVEP-based BCI systems, such as speed, subject variability, and accurate target detection, are under ongoing research investigations. Up to date, Canonical Correlation Analysis (CCA) has been considered the state-of-the-art feature extraction method for SSVEP-based BCI systems. Nevertheless, although CCA outperforms traditional SSVEP detection methods, such as Power Spectral Density Analysis (PSDA), achieving high accuracies when detecting target frequencies is still a challenging task due to user variation and physiological changes in the human body. In this paper, we investigate an SSVEP-based BCI application using wireless EEG recording and an Android tablet-based user interface. We propose a fusion of CCA and PSDA solutions at the score level by dividing their score space into multiple partitions, and extract and combine their complementary discriminative information to minimize the detection error in a linear fashion. We investigated transforming the fusion score space to lower dimensions with the purpose of alleviating redundancy. As such, we employed Principal Component Analysis (PCA), and Linear Discriminant Analysis (LDA). Our experimental results demonstrated that our proposed score fusion method is effective in reducing the effect of noise and non-stationary elements in EEG dynamics. Average detection accuracies improved from 63% for CCA to 72% for fusion+PCA and further improved to 98% for fusion+LDA.