A motor imagery EEG signal classification algorithm based on recurrence plot convolution neural network

Recurrence quantification analysis of rs-fMRI data: A method to detect subtle changes in the TgF344-AD rat model

BACKGROUND AND OBJECTIVE

Alzheimer's disease (AD) is one of the leading causes of dementia, affecting the world's population at a growing rate. The preclinical stage of AD lasts over a decade, hence understanding AD-related early neuropathological effects on brain function at this stage facilitates early detection of the disease.

METHODS

Resting-state functional magnetic resonance imaging (rs-fMRI) has been a powerful tool for understanding brain function, and it has been widely used in AD research. In this study, we apply Recurrence Quantification Analysis (RQA) on rs-fMRI images of 4-months (4 m) and 6-months-old (6 m) TgF344-AD rats and WT littermates to identify changes related to the AD phenotype and aging. RQA has been focused on areas of the default mode-like network (DMLN) and was performed based on Recurrence Plots (RP). RP is a mathematical representation of any dynamical system that evolves over time as a set of its state recurrences. In this paper, RPs were extracted in order to identify the affected regions of the DMLN at very early stages of AD.

RESULTS

Using the RQA approach, we identified significant changes related to the AD phenotype at 4 m and/or 6 m in several areas of the rat DMLN including the BFB, Hippocampal fields CA1 and CA3, CG1, CG2, PrL, PtA, RSC, TeA, V1, V2. In addition, with age, brain activity of WT rats showed less predictability, while the AD rats presented reduced decline of predictability.

CONCLUSIONS

The results of this study demonstrate that RQA of rs-fMRI data is a potent approach that can detect subtle changes which might be missed by other methodologies due to the brain's non-linear dynamics. Moreover, this study provides helpful information about specific areas involved in AD pathology at very early stages of the disease in a very promising rat model of AD. Our results provide valuable information for the development of early detection methods and novel diagnosis tools for AD.

Hybrid optimization assisted channel selection of EEG for deep learning model-based classification of motor imagery task

OBJECTIVES

To design and develop an approach named HC + SMA-SSA scheme for classifying motor imagery task.

METHODS

The offered model employs a new method for classifying motor imagery task. Initially, down sampling is deployed to pre-process the incoming signal. Subsequently, "Modified Stockwell Transform (ST) and common spatial pattern (CSP) based features are extracted". Then, optimal channel selection is made by a novel hybrid optimization model named as Spider Monkey Assisted SSA (SMA-SSA). Here, "Long Short Term Memory (LSTM) and Bidirectional Gated Recurrent Unit (BI-GRU)" models are used for final classification, whose outcomes are averaged at the end. At last, the improvement of SMA-SSA based model is proven over different metrics.

RESULTS

A superior sensitivity of 0.939 is noted for HC + SMA-SSA that was higher over HC with no optimization and proposed with traditional ST.

CONCLUSIONS

The proposed method achieved effective classification performance in terms of performance measures.

Biometric Recognition Based on Recurrence Plot and InceptionV3 Model Using Eye Movements

The ability to use eye movement signals as a feature in biometric recognition is a novel characteristic of biometric recognition technology. However, present technologies have not fully exploited the correlation features between eye movement signals. To address this, we propose an eye movement biometric recognition model that is based on recurrence plot encoding and the InceptionV3 model. We first encode the original eye movement signal using the recurrence plot to obtain a 2-D image that is then used as input for the InceptionV3 model to perform biometric recognition. Our experimental results using the GazeBaseV2.0 eye movement dataset demonstrate that our proposed model achieved a high biometric recognition accuracy of 96.58% ± 0.66% using the recurrence plot transformation of the horizontal gaze position signals and the InceptionV3 model, surpassing the accuracy achieved by other models. The use of horizontal gaze position eye movement signals for biometric recognition outperforms the use of vertical gaze position signals when using our proposed methods. Furthermore, the biometric recognition that is achieved through recurrent plot encoding is superior to that achieved using Markov transition fields and Gramian angular field transformations.

A study of EEG non-stationarity on inducing false memory in different emotional states

False memory leads to inaccurate decisions and unnecessary challenges. Researchers have conventionally used electroencephalography (EEG) to study false memory under different emotional states. However, EEG non-stationarity has scarcely been investigated. To address this problem, this study utilized the nonlinear method of recursive quantitative analysis to analyze the non-stationarity of EEG signals. Deese-Roediger-McDermott paradigm experiments were used to induce false memory wherein semantic words were highly correlated. The EEG signals of 48 participants with false memory associated with different emotional states were collected. Recurrence rate (RR), determination rate (DET), and entropy recurrence (ENTR) data were generated to characterize EEG non-stationarity. Behavioral outcomes exhibited significantly higher false-memory rates in the positive group than in the negative group. The prefrontal, temporal, and parietal regions yielded significantly higher RR, DET, and ENTR values than other brain regions in the positive group. However, only the prefrontal region had significantly higher values than other brain regions in the negative group. Therefore, positive emotions enhance non-stationarity in brain regions associated with semantics compared with negative emotions, leading to a higher false-memory rate. This suggests that non-stationary alterations in brain regions under different emotional states are correlated with false memory.

A New Method for Determining the Embedding Dimension of Financial Time Series Based on Manhattan Distance and Recurrence Quantification Analysis

Identification of embedding dimension is helpful to the reconstruction of phase space. However, it is difficult to calculate the proper embedding dimension for the financial time series of dynamics. By this Letter, we suggest a new method based on Manhattan distance and recurrence quantification analysis for determining the embedding dimension. By the advantages of the above two tools, the new method can calculate the proper embedding dimension with the feature of stability, accuracy and rigor. Besides, it also has a good performance on the chaotic time series which has a high-dimensional attractors.

An integrated mediapipe-optimized GRU model for Indian sign language recognition

Sign language recognition is challenged by problems, such as accurate tracking of hand gestures, occlusion of hands, and high computational cost. Recently, it has benefited from advancements in deep learning techniques. However, these larger complex approaches cannot manage long-term sequential data and they are characterized by poor information processing and learning efficiency in capturing useful information. To overcome these challenges, we propose an integrated MediaPipe-optimized gated recurrent unit (MOPGRU) model for Indian sign language recognition. Specifically, we improved the update gate of the standard GRU cell by multiplying it by the reset gate to discard the redundant information from the past in one screening. By obtaining feedback from the resultant of the reset gate, additional attention is shown to the present input. Additionally, we replace the hyperbolic tangent activation in standard GRUs with exponential linear unit activation and SoftMax with Softsign activation in the output layer of the GRU cell. Thus, our proposed MOPGRU model achieved better prediction accuracy, high learning efficiency, information processing capability, and faster convergence than other sequential models.