An Algorithm Classifying Brain Signals in the Control Problem

Brain–computer interface (BCI) technology provides a communication pathway using the human brain motor imaginary signal to develop applications like robotic hands and automated wheelchair, which are useful for the people who come with several motor disabilities. However, the signals which are acquired in a non-invasive approach come with various types of artifacts which badly effect on the accuracy of the prediction. For the above purposes, this paper proposes a model of human motor activity recognition using electroencephalogram (EEG) signal, in which three major time–frequency domain de-noising algorithms, i.e., Discrete Wavelet Transform (DWT), Empirical Mode Decomposition (EMD) and Savitzky–Golay filter are adopted for de-noising the signals acquired in a non-invasive approach. In this paper, initially, the EEG signals are de-noised using de-noising algorithm. After that, important statistical features from selected EEG channels of the dataset are extracted. Finally, the Support Vector Machine (SVM) classification algorithm is used for classifying particular motor activities. Those three major time–frequency domain de-noising algorithms are compared based on five comparison metrics, i.e., mean squared error (MSE), mean absolute error (MAE), signal-to-noise ratio (SNR), peak signal-to-noise ratio (PSNR), cross-correlation and the classification accuracy using SVM classification. For evaluating the proposed model, an online benchmarked dataset with four classes of motor activities has been used. Among the four classes, the first two classes are used in this research. Those are ‘Left-hand movement’ as Class 1 and ‘Right-hand movement’ as Class 2. The experimental result, the DWT-based de-noising method, shows optimal performance.

Motor intention in the posterior parietal cortex

Internet of Things is the connection of physical objects which are embedded with sensors and software for exchanging data with other devices over the internet. It is a collaboration of multiple technologies, such as machine learning, real time analytics, and embedded system. IOT has helped in dealing with various real world problems. One such application area is in the field of environment protection. Due to the enhanced levels of particles and toxic materials in the environment it has become essential to monitor the levels on continuous basis so that required notifications can be generated. The purpose of this paper is to develop an IOT module which can sense the amount of toxic particles in air using the MQ135 sensor which can be later displayed on Thingspeak server. However, when the toxicity in the air crosses the threshold value it will give the notification on twitter. This module can be installed anywhere and when pollution crosses the safe point some external devices can be triggered and send a notification using a WiFi module.

Future emerging technologies in upper limb neuroprosthetic devices will require decoding and executing the user's intended movement. Previous studies, using invasive and non-invasive brain signals, have shown promising results in decoding movement directions during movement execution. Intracortical recordings also allow for decoding of target directions before the actual movement in a reaction task. This thesis contributes to the exciting endeavor of designing practical upper limb neuroprosthetics by investigating the potential of using brain signals recorded non-invasively for detecting the intention to move and decoding directions of a self-paced reaching task before movement initiation. This work has the potential towards a more intuitive and coupled neuro-motor rehabilitation tools. The thesis provides three major contributions: (i) it proposes the use of data-driven and machine learning methods for localizing the regions of interests from scalp surface signals, (ii) it reports on successful detection of movement intention before a self-paced reaching task using amplitudes of on-going slow cortical potentials (SCPs) which is consistent across healthy subjects and chronic stroke patients and (ii) it proposes the use of amplitudes and phase of on-going SCPs for decoding movement directions before the reaching task. First, we reported a method for single trial detection of movement intention before a self-paced reaching task using signal processing and machine learning techniques. We used the movement-related potentials (MRPs) in a narrow frequency range between 0.1 to 1Hz for early detection of movement intention in the first study with 8 healthy subjects using scalp EEG. Movement intention can be detected on average 460ms before the actual onset. The average maximum true positive rates across subjects was 76% peaking at time 167ms before onset. These findings are coherent with the next study on stroke patients and control subjects. In the second study, movement intention can be detected as early as 600ms before the actual onset. More interestingly, the true positive rate reached above 80% for one of the stroke patients (both the paretic and healthy arm) and healthy control subjects. The low false positive rate before the detection of movement intention suggested that the method is promising for future online implementation using appropriate tasks (i.e. goal-oriented reaching). Second, we proposed a method for decoding reaching movement directions before onset using feature selection method called canonical variants analysis (CVA). Across all the subjects, the best selected features are mostly from the frontoparietal regions, which is consistent with previous neurophysiological studies on arm reaching tasks. The results of single trial decoding of movement directions are also promising, with a decoding accuracy before the onset for one of the control healthy subjects was of 71% using the amplitude of on-going SCPs. In addition, at 250ms before onset, the decoding accuracy peaks at 65% with the use of instantaneous phase features. The decoding accuracy for the stroke patients was 40-50% with their paretic arms. Thus, we observe that using phase features has two advantages: (i) the possibility to decode directions earlier and (ii) higher decoding accuracy. The thesis also validates the findings from scalp EEG with the invasive intra-cranial local field potentials recorded from an epileptic patient. We report that movement intention can be detected as early as 2000ms before the onset of movement with accuracy above 90%. The use of electrodes implanted in the supplementary motor area (SMA) for detecting intention with near perfection single trial classification has strengthen the theory that movement preparation starts as early as 1500ms before execution. As for movement directions, the decoding capability is rather low. It should be noticed that there are no electrode implanted in the parietal region that, as we have found in the two EEG studies and has been previously reported, are key for decoding reaching directions. In summary, the work in this thesis suggests that it is possible to recognize above chance level both the intention and direction of a self-paced reaching movement. In particular, movement intention detection can be used for the purpose of early activation of neuro-motor prosthetic devices that could enhance the recovery of stroke patients. In addition, future work derived from this thesis can harness the full potential of early intention detection from human voluntary movement for BCI and neuroprosthetics.

Background: A brain-computer interface (BCI) is considered a promising tool in neurorehabilitation. For this purpose, movement intention can be detected from brain signals and used as a control command for a robotic device. In most existing studies, a rest interval is provided before each movement to allow the generation of movement intention. However, daily life activities are performed continuously, without such intervals. Method: This paper focuses on detecting movement intention during sequential movements, using neurophysiological analyses that include movement-related cortical potentials (MRCP), event-related desynchronization/synchronization (ERD/ERS) patterns, and, for the first time, inter-trial phase coherence (ITC) analysis. Results: The results showed that during sequential hand movements, including reaching, grasping and lifting objects of various weights, holding the object, lowering it, replacing it, releasing it, and returning the hand to its initial position, two movement intentions were present: the first before starting the hand movement, and the second during the holding phase of the object. Conclusions: In this study, we demonstrated that it is possible to decode the next movement intention while performing the current movement, which can lead to the development of a new generation of intelligent neural prostheses.

Terminal iterative learning control with an application to RTPCVD thickness control

Existing lower limb exoskeletons (LLEs) have demonstrated a lack of sufficient patient involvement during rehabilitation training. To address this issue and better incorporate the patient's motion intentions, this paper proposes an online brain-computer interface (BCI) system for LLE based motor imagery and stacked ensemble. The establishment of this online BCI system enables a comprehensive closed-loop control process, which includes the collection and decoding of brain signals, robotic control, and real-time feedback mechanisms. Additionally, an online experimental protocol that integrates visual and proprioceptive feedback is developed. To enhance decoding precision, we proposed a novel classification algorithm based on the stacking technique, termed weighted random forests-support vector machines (WRF-SVM). In this algorithm, WRFs function as the base learning models, while SVMs act as the meta-learning layer. To assess the efficacy of the BCI system and the classification algorithm, eight subjects were recruited for testing. The outcomes of both online and offline experiments exhibit high classification accuracy, confirming the viability and utility of the BCI system. We are confident that our approach holds significant promise for practical applications in the field of LLE technology.

Electromyographic (EMG) control relies on supervised-learning algorithms that correlate EMG to motor intent. The quality of the training dataset is critical to the runtime performance of the algorithm, but labeling motor intent is imprecise and imperfect. Traditional EMG training data is collected while participants mimic predetermined movements of a virtual hand with their own hand. This assumes participants are perfectly synchronized with the predetermined movements, which is unlikely due to reaction time and signal-processing delays. Prior work has used cross-correlation to globally shift and re-align kinematic data and EMG. Here, we quantify the impact of this global re-alignment on both classification algorithms and regression algorithms with and without a human in the loop. We also introduce a novel trial-by-trial re-alignment method to re-align EMG with kinematics on a per-movement basis. We show that EMG and kinematic data are inherently misaligned, and that reaction time is inconsistent throughout data collection. Both global and trial-by-trial re-alignment significantly improved offline performance for classification and regression. Our trial-by-trial re-alignment further improved offline classification performance relative to global realignment. However, online performance, with a human actively in the loop, was no different with or without re-alignment. This work highlights inaccuracies in labeled EMG data and has broad implications for EMG-control applications.

About 8% of the Ecuadorian population suffers some type of amputation of upper or lower limbs. Due to the high cost of a prosthesis and the fact that the salary of an average worker in the country reached 248 USD in August 2021, they experience a great labor disadvantage and only 17% of them are employed. Thanks to advances in 3D printing and the accessibility of bioelectric sensors, it is now possible to create economically accessible proposals. This work proposes the design of a hand prosthesis that uses electromyography (EMG) signals and neural networks for real-time control. The integrated system has a mechanical and electronic design, and the latter integrates artificial intelligence for control. To train the algorithm, an experimental methodology was developed to record muscle activity in upper extremities associated with specific tasks, using three EMG surface sensors. These data were used to train a five-layer neural network. the trained model was compressed and exported using TensorflowLite. The prosthesis consisted of a gripper and a pivot base, which were designed in Fusion 360 considering the movement restrictions and the maximum loads. It was actuated in real time thanks to the design of an electronic circuit that used an ESP32 development board, which was responsible for recording, processing and classifying the EMG signals associated with a motor intention, and to actuate the hand prosthesis. As a result of this work, a database with 60 electromyographic activity records from three tasks was released. The classification algorithm was able to detect the three muscle tasks with an accuracy of 78.67% and a response time of 80 ms. Finally, the 3D printed prosthesis was able to support a weight of 500 g with a safety factor equal to 15.

EEG recordings have been used to study the spatio-temporal dynamics of brain processes. In motion intention, these analyses have detected EEG patterns present before the movement begins. This dynamics can be mapped using network models based on global functional brain connectivity, estimated from temporal connectivity matrices of all electrodes. However, this temporal matrix representation leads to dense networks containing redundant information. Brain-computer interfaces (BCI) are systems using brain patterns as control signals. Therefore, the simplification of calculations in devices or applications that need brain information with the least number of electrodes, without losing significant information, identifying the most significant channels associated with motion intention, becomes an important task. The aim of this work is to propose a methodology to select EEG electrodes containing significant information during the motor intention. Thus, a single-layer model was fitted to the BNCI Horizon 2020 motor imagery task database (2a of BCI Competition IV), including EEG recordings of four different motor imagery tasks: left hand, right hand, feet, and tongue. The correlation index was computed to estimate the pairwise correlation between EEG channels in \(\alpha _1\) (8–10 Hz), \(\alpha _2\) (10–13 Hz), and \(\beta _1\) (13–18 Hz) bands. To simplify, the adjacency matrices were thresholded. Then, a graph analysis was conducted using the degree and the eigenvector centrality as graph metrics. Later, a statistical analysis was made to identify the most significant channels associated with motion intention. Our results show that the electrodes with significant differences are located in the fronto-central area (C2, C3, FC1, Fz). These results agree with other works but also estimate the electrodes associated with the motor imagery tasks.KeywordsCorrelationEEGFunctional connectivityGraph metricsMotion intention

To determine the probabilistic time for feeding animals with mobile feeders on farms of cattle, it is required to solve the system of Kolmogorov equations. Because of the massive calculations, this work can be done only with the use of computer technology. However, a specific Kolmogorov system of equations is suitable only for a certain number of components in the feed mix. Depending on the chosen feeding ration, this amount can vary significantly. Solving the Kolmogorov equations for feed mixtures with a different number of components is a very laborious process. Therefore, it is required to develop a mathematical model that allows solving the problem of determining the probabilistic feeding time for multicomponent fodder mixtures. In the course of this work, the positions of the theory of random processes, the theory of graphs, and the foundations of mathematical modeling were used. To accomplish the task, Kolmogorov's system of equations for 2-, 3-, and 4-component fodder mixtures was compiled and solved. The combinations of intensities «L» were replaced by the coefficients introduced for visual perception of formulas and the possibility to reveal the patterns of their development with a change in the number of components. The observed regularities are reflected in the algorithm. The final solution of the Kolmogorov equations is also presented, and a general formula is obtained for calculating the probability of finding a mobile feed hopper in the state of distribution of feed. The formula consists of the coefficients which are calculated according to the developed algorithm. Thus, using the proposed algorithm, there is no need to compile and solve Kolmogorov's systems of equations to determine the probability of finding a mobile feed mill in the state of distribution of food. The observed regularities are conveniently implemented in an electronic environment, for example, MS Excel, which will allow modeling of the technological process of preparation and distribution of feed mixes with a different number of components.

Objective. The use of an electroencephalogram (EEG) anticipation-related component, the expectancy wave (E-wave), in brain–machine interaction was proposed more than 50 years ago. This possibility was not explored for decades, but recently it was shown that voluntary attempts to select items using eye fixations, but not spontaneous eye fixations, are accompanied by the E-wave. Thus, the use of the E-wave detection was proposed for the enhancement of gaze interaction technology, which has a strong need for a mean to decide if a gaze behavior is voluntary or not. Here, we attempted at estimating whether this approach can be used in the context of moving object selection through smooth pursuit eye movements. Approach. Eighteen participants selected, one by one, items which moved on a computer screen, by gazing at them. In separate runs, the participants performed tasks not related to voluntary selection but also provoking smooth pursuit. A low-cost consumer-grade eye tracker was used for item selection. Main results. A component resembling the E-wave was found in the averaged EEG segments time-locked to voluntary selection events of every participant. Linear discriminant analysis with shrinkage regularization classified the intentional and spontaneous smooth pursuit eye movements, using single-trial 300 ms long EEG segments, significantly above chance in eight participants. When the classifier output was averaged over ten subsequent data segments, median group ROC AUC of 0.75 was achieved. Significance. The results suggest the possible usefulness of the E-wave detection in the gaze-based selection of moving items, e.g. in video games. This technique might be more effective when trial data can be averaged, thus it could be considered for use in passive interfaces, for example, in estimating the degree of the user’s involvement during gaze-based interaction.

The Alzheimer's Disease (AD) has become a major threat of human health with its incidence rate ascending year by year. Early diagnosis of AD is very important for AD patients to keep life quality. The resting-state fMRI (rs-fMRI) which precisely reflects the brain changes on the resting state of individuals provides a quantitative approach, which has been introduced to distinguish AD patients from normal population. In this study, we proposed a method to find the most distinctive features identifying AD patients from rs-fMRI images. The ALFF and ReHo parameters based on pre-processed rs-fMRI data were extracted, and some key parameters of the brain functional network based on graph theory were calculated. Then we tested the recognition performance of different classifiers, and the best classification algorithm, that is, Support Vector Machine (SVM) with linear-kernel are selected. Finally through a recursive feature selection procedure, we got the most distinctive feature set. Additionally, this study also implies that there may be several changes in some particular ROIs of the brain during the AD development.

The electroencephalogram (EEG) provides markers of brain disturbances in the field of epilepsy. In short duration EEG data recordings, the epileptic graphoelements may not manifest. The visual analysis of lengthy signals is a tedious task. It is necessary to track the activity on the computer screen and to detect the epileptiform graphoelements and the other pathological activity. The automation of the process is suggested. The procedure is based on processing temporal profiles computed by means of multichannel adaptive segmentation and subsequent classification of detected signal graphoelements. The temporal profiles, function of the class membership in the course of time, reflect the dynamic EEG microstructure and may be used for visual indication of abnormal changes in the EEG using different colors. We will show that Fuzzy c-means (FCM) algorithm can be used for correct classification of epileptic pattern, creating homogeneous compact classes of significant EEG segments.

This paper studies fixed-time consensus of second-order leader-following multi-agent systems with inherent nonlinear dynamics. Firstly, a new fixed-time consensus protocol is designed to solve the tracking problem of the second-order nonlinear systems. By using Lyapunov theory and graph theory, we choose a different Lyapunov function candidate to verify the theoretical results. Then we consider the second-order multi-agent systems with multiple leaders and propose a new protocol to solve the fixed-time containment control problem. Finally, two numerical examples are proposed to demonstrate the effectiveness of the proposed fixed-time protocols.