Cognitive Neurodynamics最新文献

This paper presents an innovative feature engineering framework based on lattice structures for the automated identification of Alzheimer's disease (AD) using electroencephalogram (EEG) signals. Inspired by the Shannon information entropy theorem, we apply a probabilistic function to create the novel Lattice123 pattern, generating two directed graphs with minimum and maximum distance-based kernels. Using these graphs and three kernel functions (signum, upper ternary, and lower ternary), we generate six feature vectors for each input signal block to extract textural features. Multilevel discrete wavelet transform (MDWT) was used to generate low-level wavelet subbands. Our proposed model mirrors deep learning approaches, facilitating feature extraction in frequency and spatial domains at various levels. We used iterative neighborhood component analysis to select the most discriminative features from the extracted vectors. An iterative hard majority voting and a greedy algorithm were used to generate voted vectors to select the optimal channel-wise and overall results. Our proposed model yielded a classification accuracy of more than 98% and a geometric mean of more than 96%. Our proposed Lattice123 pattern, dynamic graph generation, and MDWT-based multilevel feature extraction can detect AD accurately as the proposed pattern can extract subtle changes from the EEG signal accurately. Our prototype is ready to be validated using a large and diverse database.

Tasks with high mental workload often involve higher cognitive functions of the human brain and complex information flow involving multiple brain regions. However, the dynamics of functional connectivity between brain regions during high mental workload have not been well-studied. We use an analysis approach designed to find repeating network states from gamma-band phase locking value networks built from electroencephalograph data collected while participants engaged in tasks with different levels of mental workload. First, we define network states as results of clustering based on the closeness centrality node-level network metric. Second, we found that the transition between network states is not completely random. And, we found significant differences in network state statistics between low and high mental workload. Third, we found significant correlation between features calculated from the network state sequence and behavioral performance. Finally, we use dynamic network features as input to a support vector machine classifier and obtain cross-participant average decoding accuracy of 69.6%. Our methods provide a new perspective for analyzing the dynamics of electroencephalograph signals and have potential application to the decoding of mental workload level.

Currently, with the bloom in artificial intelligence (AI) algorithms, various human-centered smart systems can be utilized, especially in cognitive computing, for the detection of various chronic brain diseases such as epileptic seizure. The primary goal of this research article is to propose a novel human-centered cognitive computing (HCCC) method for segment-wise seizure classification by employing multiresolution extracted data with directed transfer function (DTF) features, termed as the multiresolution directed transfer function (MDTF) approach. Initially, the multiresolution information of the epileptic seizure signal is extracted using a multiresolution adaptive filtering (MRAF) method. These seizure details are passed to the DTF where the information flow of high frequency bands is computed. Thereafter, different measures of complexity such as approximate entropy (AEN) and sample entropy (SAEN) are computed from the extracted high frequency bands. Lastly, a k-nearest neighbor (k-NN) and support vector machine (SVM) are used for classifying the EEG signal into non-seizure and seizure data depending on the multiresolution based information flow characteristics. The MDTF approach is tested on a standard dataset and validated using a dataset from a local hospital. The proposed technique has obtained an average sensitivity of 98.31%, specificity of 96.13% and accuracy of 98.89% using SVM classifier. The average detection rate of the MDTF approach is 97.72% which is greater than the existing approaches. The proposed MDTF method will help neuro-specialists to locate seizure information drift which occurs within the consecutive segments and between two channels. The main advantage of the MDTF approach is its capability to locate the seizure activity contained by the EEG signal with accuracy. This will assist the neurologists with the precise localization of the epileptic seizure automatically and hence will reduce the burden of time-consuming epileptic seizure analysis.

Abstract

Estimating a vanishing point (VP) is a core problem for understanding three-dimensional scenes and autonomous navigation. Existing methods are essential to estimating VPs in indoor and urban environments. However, doing so in diverse, unstructured, changing, and unexpected field environments remains a considerable challenge. Traditional methods of estimating structural VP have some shortcomings as they rely heavily on feature-intensive computation, making them less reliable due to a lack of adequate structures in a field environment due to disorganized disturbances. Inspired by the oblique effect, neurons prefer to respond to horizontal and vertical stimuli more than to diagonal, which can help estimate VPs. This study proposes a methodology to estimate VPs from a monocular camera for a field environment. Local orientation features are assigned to clusters inspired by the oblique effect. By extracting end points of different clusters, virtual local orientation features are reshaped. Based on geometric inferences of orientation, a VP is approximately estimated using optimal estimation and self-selectability. No prior training is needed, and camera calibration and internal parameters are not required. This approach is robust to changes in color and illumination using geometric inference, making it a perfect fit for field environments. Experimental results demonstrated that the method can successfully estimate VPs. This study presents a groundbreaking approach to evaluating VPs using a monocular camera. Inspired by the oblique effect, our method relies on explainable geometric inferences instead of prior training, resulting in a highly robust model that can handle changes in color and illumination. Our proposed approach significantly advances scene understanding and navigation, making it an ideal solution for field environments.

Our ability to measure time is vital for daily life, technology use, and even mental health; however, separating pure time perception from other mental processes (like emotions) is a research challenge requiring precise tests to isolate and understand brain activity solely related to time estimation. To address this challenge, we designed an experiment utilizing hypnosis alongside electroencephalography (EEG) to assess differences in time estimation, namely underestimation and overestimation. Hypnotic induction is designed to reduce awareness and meta-awareness, facilitating a detachment from the immediate environment. This reduced information processing load minimizes the need for elaborate internal thought during hypnosis, further simplifying the cognitive landscape. To predict time perception based on brain activity during extended durations (5 min), we employed artificial intelligence techniques. Utilizing Support Vector Machines (SVMs) with both radial basis function (RBF) and polynomial kernels, we assessed their effectiveness in classifying time perception-related brain patterns. We evaluated various feature combinations and different algorithms to identify the most accurate configuration. Our analysis revealed an impressive 80.9% classification accuracy for time perception detection using the RBF kernel, demonstrating the potential of AI in decoding this complex cognitive function.

Motor imagery (MI) is a high-level cognitive process that has been widely applied to brain-computer inference (BCI) and motor recovery. In practical applications, however, huge individual differences and unclear neural mechanisms have seriously hindered the application of MI and BCI systems. Thus, it is urgently needed to explore MI from a new perspective. Here, we applied a hidden Markov model (HMM) to explore the dynamic organization patterns of left- and right-hand MI tasks. Eleven distinct HMM states were identified based on MI-related EEG data. We found that these states can be divided into three metastates by clustering analysis, showing a highly organized structure. We also assessed the probability activation of each HMM state across time. The results showed that the state probability activation of task-evoked have similar trends to that of event-related desynchronization/synchronization (ERD/ERS). By comparing the differences in temporal features of HMM states between left- and right-hand MI, we found notable variations in fractional occupancy, mean life time, mean interval time, and transition probability matrix across stages and states. Interestingly, we found that HMM states activated in the left occipital lobe had higher occupancy during the left-hand MI task, and conversely, during the right-hand MI task, HMM states activated in the right occipital lobe had higher occupancy. Moreover, significant correlations were observed between BCI performance and features of HMM states. Taken together, our findings explored dynamic networks underlying the MI-related process and provided a complementary understanding of different MI tasks, which may contribute to improving the MI-BCI systems.

Conduction delay and failure behaviors of action potentials with a high frequency along nerve fiber are related to the abnormal functions. For instance, upregulation of a hyperpolarization-activated cation current (I_h) is identified to reduce the conduction delay to recover the temporal encoding, and downregulation of the I_h current to enhance the conduction failure rate to ease the pain sensation, with the dynamic mechanisms remaining unclear. In the present paper, the dynamic mechanism is obtained in a chain network model with coupling strength (g_c) and action potentials induced by periodic stimulations with a period (T_s). At first, as the action potentials exhibit a high frequency corresponding to a short T_s and the network has a small g_c, i.e., a short and unrecovered afterpotential and a small coupling current, the conduction delay is reproduced. The conduction failure is reproduced for T_s shorter and g_c smaller than those of the conduction delay, presenting a direct relationship between the two behaviors. Then, the conduction delay and failure are explained with the response time and current threshold of an action potential evoked from the unrecovered afterpotential. The prolonged response time for short T_s and small g_c presents the cause for the conduction delay, and the enhanced threshold for shorter T_s and smaller g_c presents the cause for the conduction failure. Furthermore, reduction of the delay and enhancement of the failure rate respectively induced by upregulation and downregulation of the I_h current are reproduced and explained. The positive I_h current induces Hopf bifurcation advanced and resting membrane potential elevated. Then, upregulation and downregulation of the I_h current induce the afterpotential elevated to shorten the response time and reduced to enhance the threshold, respectively. The results present nonlinear dynamics for the non-faithful conduction behaviors and dynamical mechanism for the modulation effect of the I_h current on the conduction delay and failure related to encoding and pain.

Electroencephalography-based (EEG) microstate analysis is a promising and widely studied method in which spontaneous cerebral activity is segmented into sub second level quasi-stable states and analyzed. Currently it is being widely explored due to increasing evidence of the association of microstates with cognitive functioning and large-scale brain networks identified by functional magnetic resonance imaging (fMRI). In our study using the four archetypal microstates (A, B, C and D), we investigated the changes in resting state EEG microstate dynamics in persons with temporal lobe epilepsy (TLE) and idiopathic generalized epilepsy (IGE) compared to healthy controls (HC). Machine learning was applied to study its feasibility in differentiating between different groups using microstate statistics. We found significant differences in all parameters related to Microstate D (fronto-parietal network) in TLE patients and Microstate B (visual processing) in IGE patients compared to HCs. Occurrence, duration and time coverage of Microstate B was highest in IGE when compared to the other groups. We also found significant deviations in transition probabilities for both epilepsy groups, particularly into Microstate C (salience network) in IGE. Classification accuracy into clinical groups was found to exceed 70% using microstate parameters which improved on incorporating neuropsychological test differences. To the best of our knowledge, the current study is the first to compare and validate the use of microstate features to discriminate between two disparate epilepsy syndromes (TLE, IGE) and HCs using machine learning suggesting that resting state EEG microstates can be used for endophenotyping and to study resting state dysfunction in epilepsy.

Abstract

Task-free brain activity exhibits spontaneous fluctuations between functional states, characterized by synchronized activation patterns in distributed resting-state (RS) brain networks. The temporal dynamics of the networks’ electrophysiological signatures reflect individual variations in brain activity and connectivity linked to mental states and cognitive functions and can predict or monitor vulnerability to develop psychiatric or neurological disorders. In particular, RS alpha fluctuations modulate perceptual sensitivity, attentional shifts, and cognitive control, and could therefore reflect a neural correlate of increased vulnerability to sensory distortions, including the proneness to hallucinatory experiences. We recorded 5 min of RS EEG from 33 non-clinical individuals varying in hallucination proneness (HP) to investigate links between task-free alpha dynamics and vulnerability to hallucinations. To this end, we used a dynamic brain state allocation method to identify five recurrent alpha states together with their spatiotemporal dynamics and most active brain areas through source reconstruction. The dynamical features of a state marked by activation in somatosensory, auditory, and posterior default-mode network areas predicted auditory and auditory-verbal HP, but not general HP, such that individuals with higher vulnerability to auditory hallucinations spent more time in this state. The temporal dynamics of spontaneous alpha activity might reflect individual differences in attention to internally generated sensory events and altered auditory perceptual sensitivity. Altered RS alpha dynamics could therefore instantiate a neural marker of increased vulnerability to auditory hallucinations.

Neurodevelopmental disorders (NDs) often hamper multiple functional prints of a child brain. Despite several studies on their neural and speech responses, multimodal researches on NDs are extremely rare. The present work examined the electroencephalography (EEG) and speech signals of the ND and control children, who performed “Hindi language” vocal tasks (V) of seven different categories, viz. ‘vowel’, ‘consonant’, ‘one syllable’, ‘multi-syllable’, ‘compound’, ‘complex’, and ‘sentence’ (V1–V7). Statistical testing of EEG parameters showed substantially high beta and gamma band energies in frontal, central, and temporal head sites of NDs for tasks V1–V5 and in parietal too for V6. For the ‘sentence’ task (V7), the NDs yielded significantly high theta and low alpha energies in the parietal area. These findings imply that even performing a general context-based task exerts a heavy cognitive loading in neurodevelopmental subjects. They also exhibited poor auditory comprehension while executing a long phrasing. Further, the speech signal analysis manifested significantly high amplitude (for V1–V7) and frequency (for V3–V7) perturbations in the voices of ND children. Moreover, the classification of subjects as ND or control was done via EEG and speech features. We attained 100% accuracy, precision, and F-measure using EEG features of all tasks, and using speech features of the ‘complex’ task. Jointly, the ‘complex’ task transpired as the best vocal stimuli among V1–V7 for characterizing ND brains. Meanwhile, we also inspected inter-relations between EEG energies and speech attributes of the ND group. Our work, thus, represents a unique multimodal layout to explore the distinctiveness of neuro-impaired children.