Towards SSVEP-based, portable, responsive Brain-Computer Interface.

A new vision-based long-distance lane perception and front vehicle location method was developed for decision making of full autonomous vehicles on highway roads. Firstly, a real-time long-distance lane detection approach was presented based on a linear-cubic road model for two-lane highways. By using a novel robust lane marking feature which combines the constraints of intensity, edge and width, the lane markings in far regions were extracted accurately and efficiently. Next, the detected lane lines were selected and tracked by estimating the lateral offset and heading angle of ego vehicle with a Kalman filter. Finally, front vehicles were located on correct lanes using the tracked lane lines. Experiment results show that the proposed lane perception approach can achieve an average correct detection rate of 94.37% with an average false positive detection rate of 0.35%. The proposed approaches for long-distance lane perception and front vehicle location were validated in a 286 km full autonomous drive experiment under real traffic conditions. This successful experiment shows that the approaches are effective and robust enough for full autonomous vehicles on highway roads.

Improvement in seizure detection performance by automatic adaptation to the EEG of each patient

Aims: The rise of automation has greatly impacted various aspects of daily life, including attendance management systems. Traditional methods like manual roll calls and card swiping are often inefficient and prone to errors, leading researchers to explore innovative alternatives such as face recognition technology. This technology employs advanced algorithms and image processing techniques to accurately identify individuals based on their unique facial features, thereby enhancing accuracy and security measures. The objective of this project is to develop a face recognition-based attendance system with specific goals, including circuit design, simulation using Proteus Software, implementation, and performance evaluation through rigorous field-testing. Study Design: The system comprises an input subsystem with a Camera module and two output subsystems: an LCD and a Web-database PC software. Initially, custom and stored image data of students are saved in a microSD card of the camera module, and attendance records are updated on a web-database upon successful scanning and recognition of students' faces. Methodology: The implementation process involves assembling various hardware components, including securely mounting the ESP32 CAM and integrating a 16x4 Character LCD Display for visual feedback. LEDs are used as visual indicators for system statuses, while a Power Bank Module ensures consistent power supply. The system is controlled by the ESP32-CAM, which captures and verifies faces, displays actions on the LCD, and updates the web-database with attendance data. Results: Testing results indicate the system's high accuracy, achieving a 100% attendance rate across multiple class sessions with zero misclassifications. Conclusion: The user-friendly interface and seamless wireless connectivity enhance accessibility and real-time monitoring, making it a valuable tool for classroom management and office use. The research has some hardware limitations which includes processing large amounts of facial data requires robust hardware. Inadequate camera resolution or processing power can lead to slow performance or inaccurate recognition. Overall, the face recognition-based attendance system has the potential to revolutionize traditional methods, offering high accuracy, user-friendly features, and robust connectivity, with possible applications beyond education through further refinement and research. Facial recognition-based attendance systems are more accurate and efficient than traditional methods like manual roll calls or card swiping. By automating attendance, they reduce errors and provide real-time updates with web integration. Despite hardware limitations, the system's accuracy and ease of use make it a superior alternative with potential for broader applications.

It is impossible for severely disabled people to browse or learn through the Internet due to the mere lack of independent control of the mouse. This paper proposes a brain computer interface (BCI) to aid severely disabled individuals, such as people disabled by amyotrophic lateral sclerosis (ALS), in browsing or learning on the Internet. By analyzing specific components of event-related potentials (ERPs), cursor control can be achieved. The cursor can be controlled by brain waves in a user-friendly manner to move or click on the web page. The major contributions of this research include: (1) designing a BCI for disabled people, (2) embedding the BCI's cursor controller into a web page, (3) conducting clinical experiments, (4) analysing the experimental results, system accuracy, and effectiveness, and (5) evaluating the system's practicability and giving suggestions for future work. There are two innovative technologies proposed in this research: (1) a specific component of ERPs located at O1, the N2P3 (the difference between the peak and trough of N200 and P300), was used to differentiate targeted from non-targeted (non-selected) signals, (2) instead of a fixed position style BCI, a movable watermark style BCI which follows the cursor was designed. The novel technique supported by a user-friendly interface helps the disabled have contact with the outside world resulting in positive emotions.

Accurate liver segmentation from computed tomography (CT) images is problematic due to non-uniform density, weak boundaries and because there may be multiple liver tumors that have heterogeneous intensities in region(s) of interest (ROIs). So we propose a generalized energy framework that harnesses the statistical intensity approximation with image data on graphs. Our statistical energy term takes advantage of the mixture-of-mixtures Gaussian model to approximate the probability density distribution of the liver and background to better differentiate between the two. The probability density estimation can be combined with the spatial cohesion of the graph-based Dirichlet integral by using graph calculus. Matrix decomposition and differentiation are used to minimize our proposed energy functional. We tested our approach on 20 public high-contrast CT images with single and multiple liver tumors. Our method had an average dice similarity coefficient (DSC) of 93.75±1.29%, an average false positive (FP) rate of 9.43±3.52% and an average false negative (FN) rate of 3.48±1.48%. Our method outperformed the benchmark graph-based Random Walker algorithm (average DSC=81.97±4.09%, average FP rate 34.10±10.53%, and average FN rate 7.10±4.35%).

A new research methodology named Brain Computer Interface (BCI) studies novel human-computer interactions; by means of BCI electronics devices, paralyzed patients are able to interact with the environment using no muscular contractions. This technique provides an external electronics support to all persons with severe motor disabilities, by acquiring in continuous mode the electroencephalogram (EEG) signals and operating some processing to control a computer or other domotics devices. Patients are so allowed to control external devices or to communicate simple messages through the computer, just concentrating their attention either on codified movements or on a letter or icon on a digital keyboard. The use of a customized and optimized spatial filtering technique embedded in the BCI system, based on the detection of the Electroencephalographic activity, improves the accuracy of BCI system itself, thanks to the explicit separation of the signal activity of interest from artefact signals. In this chapter, after an overview of the state-of-the-art research on BCI systems, the spatial filtering problem in EEG signals acquisition will be illustrated. In particular, a spatial filtering algorithm, known as ICA (Independent Component Analysis) and its application will be discussed. Finally, the design and implementation of an embedded system for EEG signals acquisition and real-time processing for BCI applications will be presented. The system is based onto a very performing and reconfigurable hardware platform. Moreover ICA algorithm has been implemented for noise reduction and artifacts removal.

Sleep spindles are one of the most important transient waveforms found in the sleep EEG signal. Here, we introduce a two-stage procedure based on artificial neural networks for the automatic recognition of sleep spindles (SS) in a 19-channel electroencephalographic signal. In the first stage, a pre-processing perception is used for enhancing overall detection and also reducing computation time. In the second stage, the selected Sleep spindle s (SS), classified with neural network post-classifier. Classifying tools in post-processing procedure were MLP and RBSVM that their operations are compared in the last section of the report. Visual inspection of 19-channel EEG from six subjects by one expert in this theme, showed that RBSVM operation is better than MLP with BP (Back propagation) training, that SVM provided 91.4% average sensitivity and 3.85% average false detection rate .

The emergency decision support system proposed in this paper uses data mining technology to analyze and mine a large amount of dynamic operation data and historical operation data in the China-ASEAN natural disaster database, which can be used to analyze the dynamic safety risk and optimize the emergency rescue and disposal plan for China-ASEAN natural disasters. In order to optimize the emergency decision support system, the core algorithm of data mining in the system is improved, an improved sequence analysis algorithm is proposed, and improvement measures are proposed on the basis of the inadequacy of the original Apriori algorithm. Through examples, the data mining algorithm’s specific process of automatically generating response suggestions for security events is demonstrated. The analysis of the data shows that the test results meet the expected results, and the algorithm can effectively make response decisions. The average false detection rate is only 8.05%. In scenarios 2, 3, and 4, all of them have higher emergency response efficiency, respectively, of 0.4445, 0.4616, and 0.5299. The completion time of the emergency response increases as the response level increases.

Brain Computer Interfacing (BCI) systems, which are a new communicating channel between humans and the computers are growing rapidly. One such a method is based on the Steady State Visual Evoked Potentials (SSVEP), which can be recorded during visual stimulating of the subject by a twinkling light source with a fixed frequency. An important parameter to be considered is the effect of the inter-sources distance on the accuracy of such BCI systems. In particular inter-sources (LEDs) distances of 4, 14, 24, 44 and 64 cm when the sources plane is located 60 cm away from the subject's eyes (producing inter-sources visual angles of 3.8°, 13.4°, 22.6°, 40.2° and 56° respectively) were examined. In addition, four different sweep lengths of 0.5, 1, 2 and 3 seconds are considered. In addition, due to the usage of the AR models for feature extraction from the SSVEP signals, selection of the best AR model together with the best classifier among the LDA, the SVM and the Naive Bayes are studied. It is showed that the BCI system with D=44 cm, AR order of 13 and either the LDA or the SVM classifiers could produce the best results compared to the other cases.

Brain Computer Interface (BCI) creates a new communication channel for people who have motor disabilities. In recent years, SSVEP-based BCI has been focused widely, due to its advantages over other types of BCI. Brain sleepiness during military sentry is an indispensable and prevalent occurrence in military areas. In this study, a novel high-speed SSVEP-based BCI system for military sentinel monitoring is proposed. In order to generate the SSVEPs in brain activity of a sentinel, an experimental setup containing two sets of LEDs with constant twinkling frequency is proposed. In addition, the effects of two different twinkling frequencies of 15 Hz and 20 Hz, three segmentation lengths (sweeps), two FFT-based feature extraction methods, and three classifiers on the system accuracy is investigated. In addition, in order to make a compromise between the accuracy and the computation speed, Information Transfer Rate (ITR) was calculated. The experimental results shows that 20 Hz stimulant is more preferable than 15 Hz one with the best sweep length of 1 second using the Max classifier with ITR value of 19.3 bit/min.

New paradigms for brain computer interfacing (BCI), such as based on imagination of task characteristics, require long training periods, have limited accuracy, and lack adaptation to the changes in the users' conditions. Error potentials generated in response to an error made by the translation algorithm can be used to improve the performance of a BCI, as a feedback extracted from the user and fed into the BCI system. The present study addresses the inclusion of error potentials in a BCI system based on the decoding of movement-related cortical potentials (MRCPs). We theoretically quantify the improvement in accuracy of a BCI system when using error potentials for correcting the output decision, in the general case of multiclass classification. The derived theoretical expressions can be used during the design phase of any BCI system. They were applied to experimentally estimated accuracies in decoding MRCPs and error potentials. The average misclassification rate (n = 6 subjects) of MRCPs associated to the imagination of elbow flexions at two speeds was 26%, with a bit transfer rate of 0.17. The inclusion of error potentials, experimentally recorded and classified with misclassification rate of 20%, led to a theoretical error rate of 14% with a bit transfer rate of 0.30.

Objective: To compare the antibody persistence 5 years after primary immunization with 5 μg and 10 μg recombinant hepatitis B vaccine (HepB) among newborns with normal and high response. Methods: Newborns who completed three doses of 5 μg HepB made by recombinant dexyribonucleic acid technique in Saccharomyces (HepB-SC) or 10 μg HepB made by recombinant dexyribonucleic acid technique in Hansenula polymorpha (HepB-HP) were recruited. Standardized questionnaire was used and blood samples were collected 1-6 months (T(0)) and five years (T(1)) after the third dose respectively. The titer of anti-HBs was detected by chemiluminescence microparticle imunoassay (CMIA). Those who achieved normal or high antibody response (anti-HBs titer ≥100 mIU/ml) were included in the study and the positive rate (≥10 mIU/ml) and titer of anti-HBs at T(1) were compared between 5 μg HepB group and 10 μg HepB group. Multivariable analysis was conducted to identify the independent factors associated with the antibody persistence. Results: The positive rate of anti-HBs at T(1) was 49.92% (943/1 883) and 75.92% (1 135/1 495) respectively in 5 μg HepB group and 10μg HepB group, the difference was significant (χ(2)=237.75, P<0.001). The anti-HBs geometric mean concentrations at T(1) were 10.23 mIU/ml (95%CI: 9.38-11.16) and 28.91 mIU/ml (95%CI: 26.65-31.35) in the two groups respectively, the difference was also significant (F=280.36, P<0.001). Among those whose anti-HBs titer was<10 mIU/ml at T(1), the distributions of anti-HBs titer were significantly different between 5 μg HepB group and 10 μg HepB group (χ(2)=39.75, P<0.001). The multivariable analysis showed that dosage of HepB was independently associated with both positive rate and titer of anti-HBs at T(1) after excluding the other factors[P<0.001, OR=1.44 (95%CI: 1.20-1.73); P<0.001, β=0.27 (95%CI: 0.14-0.40)]. Conclusion: Five year anti-HBs persistence after primary immunization with 10 μg HepB might be better than that after primary immunization with 5 μg HepB among infants who achieved normal or high anti-HBs response after primary HepB immunization.

A brain-computer interface (BCI) is a system that allows an individual to communicate with a computer or other external device using brain activity alone. Electroencephalography (EEG) is a common approach for detecting brain activity in BCI systems, as it provides a non-invasive measure of brain activity with high temporal resolution. Deep learning methods, such as convolutional neural networks (CNNs), have been applied to the analysis of EEG data for BCI applications, and have shown promising results in terms of accuracy and reliability. In this literature survey, we reviewed the use of CNNs for the classification of EEG data in real time to identify specific brain commands. Challenges to the development of an effective BCI using EEG and deep learning methods include the variability of EEG signals across individuals and the high dimensionality of the EEG data. Further research is needed to address these challenges and improve the accuracy and reliability of BCI systems using deep learning methods.

Brain-computer interface (BCI) has great potential to replace lost upper limb function. Thus, there has been great interest in the development of BCI-controlled robotic arm. However, few studies have attempted to use noninvasive electroencephalography (EEG)-based BCI to achieve high-level control of a robotic arm. In this paper, a high-level control architecture combining augmented reality (AR) BCI and computer vision was designed to control a robotic arm for performing a pick and place task. A steady-state visual evoked potential (SSVEP)-based BCI paradigm was adopted to realize the BCI system. Microsoft's HoloLens was used to build an AR environment and served as the visual stimulator for eliciting SSVEPs. The proposed AR-BCI was used to select the objects that need to be operated by the robotic arm. The computer vision was responsible for providing the location, color and shape information of the objects. According to the outputs of the AR-BCI and computer vision, the robotic arm could autonomously pick the object and place it to specific location. Online results of 11 healthy subjects showed that the average classification accuracy of the proposed system was 91.41%. These results verified the feasibility of combing AR, BCI and computer vision to control a robotic arm, and are expected to provide new ideas for innovative robotic arm control approaches.

Brain-computer interfaces (BCIs) have tremendous application potential in communication, mechatronic control and rehabilitation. However, existing BCI systems are bulky, expensive and require laborious preparation before use. This study proposes a practical and user-friendly BCI system without compromising performance. A hybrid asynchronous BCI system was developed based on an elaborately designed wearable electroencephalography (EEG) amplifier that is compact, easy to use and offers a high signal-to-noise ratio (SNR). The wearable BCI system can detect P300 signals by processing EEG signals from three channels and operates asynchronously by integrating blink detection. The wearable EEG amplifier obtains high quality EEG signals and introduces preprocessing capabilities to BCI systems. The wearable BCI system achieves an average accuracy of 94.03±4.65%, an average information transfer rate (ITR) of 31.42±7.39 bits/min and an average false-positive rate (FPR) of 1.78%. The experimental results demonstrate the feasibility and practicality of the developed wearable EEG amplifier and BCI system. Wearable asynchronous BCI systems with fewer channels are possible, indicating that BCI applications can be transferred from the laboratory to real-world scenarios.