An EEG channel selection method for motor imagery based on Fisher score and local optimization.

Objective. Multi-channel electroencephalogram (EEG) technology in brain-computer interface (BCI) research offers the advantage of enhanced spatial resolution and system performance. However, this also implies that more time is needed in the data processing stage, which is not conducive to the rapid response of BCI. Hence, it is a necessary and challenging task to reduce the number of EEG channels while maintaining decoding effectiveness.Approach. In this paper, we propose a local optimization method based on the Fisher score for within-subject EEG channel selection. Initially, we extract the common spatial pattern characteristics of EEG signals in different bands, calculate Fisher scores for each channel based on these characteristics, and rank them accordingly. Subsequently, we employ a local optimization method to finalize the channel selection.Main results. On the BCI Competition IV Dataset IIa, our method selects an average of 11 channels across four bands, achieving an average accuracy of 79.37%. This represents a 6.52% improvement compared to using the full set of 22 channels. On our self-collected dataset, our method similarly achieves a significant improvement of 24.20% with less than half of the channels, resulting in an average accuracy of 76.95%.Significance. This research explores the importance of channel combinations in channel selection tasks and reveals that appropriately combining channels can further enhance the quality of channel selection. The results indicate that the model selected a small number of channels with higher accuracy in two-class motor imagery EEG classification tasks. Additionally, it improves the portability of BCI systems through channel selection and combinations, offering the potential for the development of portable BCI systems.

Autonomous ultrasound scanning robotic system based on human posture recognition and image servo control: an application for cardiac imaging.

In traditional cardiac ultrasound diagnostics, the process of planning scanning paths and adjusting the ultrasound window relies solely on the experience and intuition of the physician, a method that not only affects the efficiency and quality of cardiac imaging but also increases the workload for physicians. To overcome these challenges, this study introduces a robotic system designed for autonomous cardiac ultrasound scanning, with the goal of advancing both the degree of automation and the quality of imaging in cardiac ultrasound examinations. The system achieves autonomous functionality through two key stages: initially, in the autonomous path planning stage, it utilizes a camera posture adjustment method based on the human body's central region and its planar normal vectors to achieve automatic adjustment of the camera's positioning angle; precise segmentation of the human body point cloud is accomplished through efficient point cloud processing techniques, and precise localization of the region of interest (ROI) based on keypoints of the human body. Furthermore, by applying isometric path slicing and B-spline curve fitting techniques, it independently plans the scanning path and the initial position of the probe. Subsequently, in the autonomous scanning stage, an innovative servo control strategy based on cardiac image edge correction is introduced to optimize the quality of the cardiac ultrasound window, integrating position compensation through admittance control to enhance the stability of autonomous cardiac ultrasound imaging, thereby obtaining a detailed view of the heart's structure and function. A series of experimental validations on human and cardiac models have assessed the system's effectiveness and precision in the correction of camera pose, planning of scanning paths, and control of cardiac ultrasound imaging quality, demonstrating its significant potential for clinical ultrasound scanning applications.

Face preference detection task based on EEG energy analysis in the source domain.

Facial stimulation can produce specific event-related potential (ERP) component N170 in the fusiform gyrus region. However, the role of the fusiform gyrus region in facial preference tasks is not clear at present, and the current research of facial preference analysis based on EEG signals is mostly carried out in the scalp domain. This paper explores whether the region of the fusiform gyrus is involved in processing face preference emotions in terms of the distribution of energy over the source domain, and finds that the pars orbitalis cortex is most energetically active in the face preference task and that there are significant differences between the left and right hemispheres.Clinical Relevance- The role of pars orbitalis in facial preference may help doctors determine whether the pars orbitalis cortex is lost in clinical practice.

Using Determinant Point Process in Generative Adversarial Networks for SSVEP Signals Synthesis.

Steady-state visual evoked potential (SSVEP) is one of the main paradigms of brain-computer interface (BCI). However, the acquisition method of SSVEP can cause subject fatigue and discomfort, leading to the insufficiency of SSVEP databases. Inspired by generative determinantal point process (GDPP), we utilize the determinantal point process in generative adversarial network (GAN) to generate SSVEP signals. We investigate the ability of the method to synthesize signals from the Benchmark dataset. We further use some evaluation metrics to verify its validity. Results prove that the usage of this method significantly improved the authenticity of generated data and the accuracy (97.636%) of classification using deep learning in SSVEP data augmentation.

A self-learning Monte Carlo tree search algorithm for robot path planning.

This paper proposes a self-learning Monte Carlo tree search algorithm (SL-MCTS), which has the ability to continuously improve its problem-solving ability in single-player scenarios. SL-MCTS combines the MCTS algorithm with a two-branch neural network (PV-Network). The MCTS architecture can balance the search for exploration and exploitation. PV-Network replaces the rollout process of MCTS and predicts the promising search direction and the value of nodes, which increases the MCTS convergence speed and search efficiency. The paper proposes an effective method to assess the trajectory of the current model during the self-learning process by comparing the performance of the current model with that of its best-performing historical model. Additionally, this method can encourage SL-MCTS to generate optimal solutions during the self-learning process. We evaluate the performance of SL-MCTS on the robot path planning scenario. The experimental results show that the performance of SL-MCTS is far superior to the traditional MCTS and single-player MCTS algorithms in terms of path quality and time consumption, especially its time consumption is half less than that of the traditional MCTS algorithms. SL-MCTS also performs comparably to other iterative-based search algorithms designed specifically for path planning tasks.

Effect of 3D paradigm synchronous motion for SSVEP-based hybrid BCI-VR system.

A brain-computer interface (BCI) system and virtual reality (VR) are integrated as a more interactive hybrid system (BCI-VR) that allows the user to manipulate the car. A virtual scene in the VR system that is the same as the physical environment is built, and the object's movement can be observed in the VR scene. The four-class three-dimensional (3D) paradigm is designed and moves synchronously in virtual reality. The dynamic paradigm may affect their attention according to the experimenters' feedback. Fifteen subjects in our experiment steered the car according to a specified motion trajectory. According to our online experimental result, different motion trajectories of the paradigm have various effects on the system's performance, and training can mitigate this adverse effect. Moreover, the hybrid system using frequencies between 5 and 10 Hz indicates better performance than those using lower or higher stimulation frequencies. The experiment results show a maximum average accuracy of 0.956 and a maximum information transfer rate (ITR) of 41.033 bits/min. It suggests that a hybrid system provides a high-performance way of brain-computer interaction. This research could encourage more interesting applications involving BCI and VR technologies.

Resting-state SEEG-based brain network analysis for the detection of epileptic area.

BACKGROUND: Most epilepsy research is based on interictal or ictal functional connectivity. However, prolonged electrode implantation may affect patients' health and the accuracy of epileptic zone identification. Brief resting-state SEEG recordings reduce the observation of epileptic discharges by reducing electrode implantation and other seizure-inducing interventions. NEW METHOD: The location coordinates of SEEG in the brain were identified using CT and MRI. Based on undirected brain network connectivity, five functional connectivity measures and data feature vector centrality were calculated. Network connectivity was calculated from multiple perspectives of linear correlation, information theory, phase, and frequency, and the relative influence of nodes on network connectivity was considered. We investigated the potential value of resting-state SEEG for epileptic zone identification by comparing the differences between epileptic and non-epileptic zones, as well as the differences between patients with different surgical outcomes. RESULTS: By comparing the centrality of brain network connectivity between epileptic and non-epileptic zones, we found significant differences in the distribution of brain networks between the two zones. There was a significant difference in brain network between patients with good surgical outcomes and those with poor surgical outcomes (p < 0.01). By combining support vector machines with static node importance, we predicted an AUC of 0.94 ± 0.08 for the epilepsy zone. CONCLUSIONS AND SIGNIFICANCE: The results illustrated that nodes in epileptic zones are distinct from those in non-epileptic zones. Analysis of resting-state SEEG data and the importance of nodes in the brain network may contribute to identifying the epileptic zone and predicting the outcome.

Reviving the Dynamics of Attacked Reservoir Computers.

Physically implemented neural networks are subject to external perturbations and internal variations. Existing works focus on the adversarial attacks but seldom consider attack on the network structure and the corresponding recovery method. Inspired by the biological neural compensation mechanism and the neuromodulation technique in clinical practice, we propose a novel framework of reviving attacked reservoir computers, consisting of several strategies direct at different types of attacks on structure by adjusting only a minor fraction of edges in the reservoir. Numerical experiments demonstrate the efficacy and broad applicability of the framework and reveal inspiring insights into the mechanisms. This work provides a vehicle to improve the robustness of reservoir computers and can be generalized to broader types of neural networks.

Measurement Method of Human Lower Limb Joint Range of Motion Through Human-Machine Interaction Based on Machine Vision.

To provide stroke patients with good rehabilitation training, the rehabilitation robot should ensure that each joint of the limb of the patient does not exceed its joint range of motion. Based on the machine vision combined with an RGB-Depth (RGB-D) camera, a convenient and quick human-machine interaction method to measure the lower limb joint range of motion of the stroke patient is proposed. By analyzing the principle of the RGB-D camera, the transformation relationship between the camera coordinate system and the pixel coordinate system in the image is established. Through the markers on the human body and chair on the rehabilitation robot, an RGB-D camera is used to obtain their image data with relative position. The threshold segmentation method is used to process the image. Through the analysis of the image data with the least square method and the vector product method, the range of motion of the hip joint, knee joint in the sagittal plane, and hip joint in the coronal plane could be obtained. Finally, to verify the effectiveness of the proposed method for measuring the lower limb joint range of motion of human, the mechanical leg joint range of motion from a lower limb rehabilitation robot, which will be measured by the angular transducers and the RGB-D camera, was used as the control group and experiment group for comparison. The angle difference in the sagittal plane measured by the proposed detection method and angle sensor is relatively conservative, and the maximum measurement error is not more than 2.2 degrees. The angle difference in the coronal plane between the angle at the peak obtained by the designed detection system and the angle sensor is not more than 2.65 degrees. This paper provides an important and valuable reference for the future rehabilitation robot to set each joint range of motion limited in the safe workspace of the patient.

Inter-Patient Classification With Encoded Peripheral Pulse Series and Multi-Task Fusion CNN: Application in Type 2 Diabetes.

Diabetes mellitus, a chronic disease associated with elevated accumulation of glucose in the blood, is generally diagnosed through an invasive blood test such as oral glucose tolerance test (OGTT). An effective method is proposed to test type 2 diabetes using peripheral pulse waves, which can be measured fast, simply and inexpensively by a force sensor on the wrist over the radial artery. A self-designed pulse waves collection platform includes a wristband, force sensor, cuff, air tubes, and processing module. A dataset was acquired clinically for more than one year by practitioners. A group of 127 healthy candidates and 85 patients with type 2 diabetes, all between the ages of 45 and 70, underwent assessments in both OGTT and pulse data collection at wrist arteries. After preprocessing, pulse series were encoded as images using the Gramian angular field (GAF), Markov transition field (MTF), and recurrence plots (RPs). A four-layer multi-task fusion convolutional neural network (CNN) was developed for feature recognition, the network was well-trained within 30 minutes based on our server. Compared to single-task CNN, multi-task fusion CNN was proved better in classification accuracy for nine of twelve settings with empirically selected parameters. The results show that the best accuracy reached 90.6% using an RP with threshold ϵ of 6000, which is competitive to that using state-of-the-art algorithms in diabetes classification.

Control System for Vertical Take-Off and Landing Vehicle's Adaptive Landing Based on Multi-Sensor Data Fusion.

Vertical take-off and landing unmanned aerial vehicles (VTOL UAV) are widely used in various fields because of their stable flight, easy operation, and low requirements for take-off and landing environments. To further expand the UAV's take-off and landing environment to include a non-structural complex environment, this study developed a landing gear robot for VTOL vehicles. This article mainly introduces the adaptive landing control of the landing gear robot in an unstructured environment. Based on the depth camera (TOF camera), IMU, and optical flow sensor, the control system achieves multi-sensor data fusion and uses a robotic kinematical model to achieve adaptive landing. Finally, this study verifies the feasibility and effectiveness of adaptive landing through experiments.

Analysis of degradation mechanism of disperse orange 25 in supercritical water oxidation using molecular dynamic simulations based on the reactive force field.

4-[N-(2-cyanoethyl)-N-ethylamino]-4'-nitroazo-benzene (disperse orange 25, DO25) is one of the main components in dyeing wastewater. In this work, supercritical water oxidation (SCWO) process of DO25 has been investigated using the molecular dynamic simulations based on the reactive force field (ReaxFF). For the SCWO system, the effects of temperature, the molecular ratio of DO25, O2 and H2O as well as the reaction time have been analyzed. The simulated results showed that the aromatic rings in DO25 could be attacked by hydroxyl radical, oxygen molecule, and hydroxyl radical together with oxygen molecule, respectively, which caused the aromatic ring-opening reaction to happen mainly through three different pathways. The hydroxyl radicals were mainly from water clusters and H2O2 (which was produced from oxygen molecules reacting with water clusters). However, for the SCW system as comparison, the aromatic rings in DO25 could be attacked by hydroxyl radical only, and the OH radicals just come from water clusters. During the DO25 SCWO degradation process, we also found that N elements in one DO25 molecule were difficult to be converted into environmentally friendly N2 molecules because of steric hindrance, but increasing the number of DO25 molecules could improve the possibility for the connection of N elements, thus promoting N element converting into N2. Extending reaction time could also improve N elements in DO25 to transform into N2 rather than carbonitride.

Enhanced thermoelectric performance and anomalous seebeck effects in topological insulators.

Improving the thermoelectric figure of merit zT is one of the greatest challenges in material science. The recent discovery of topological insulators (TIs) offers new promise in this prospect. In this work, we demonstrate theoretically that zT is strongly size dependent in TIs, and the size parameter can be tuned to enhance zT to be significantly greater than 1. Furthermore, we show that the lifetime of the edge states in TIs is strongly energy dependent, leading to large and anomalous Seebeck effects with an opposite sign to the Hall effect. These striking properties make TIs a promising material for thermoelectric science and technology.