ABSTRACT
People frequently struggle to juggle their work, family, and social life in today’s fast-paced environment, which can leave them exhausted and worn out. The development of technologies for detecting fatigue while driving is an important field of research since driving when fatigued poses concerns to road safety. In order to throw light on the most recent advancements in this field of research, this paper provides an extensive review of fatigue driving detection approaches based on electroencephalography (EEG) data. The process of fatigue driving detection based on EEG signals encompasses signal acquisition, preprocessing, feature extraction, and classification. Each step plays a crucial role in accurately identifying driver fatigue. In this review, we delve into the signal acquisition techniques, including the use of portable EEG devices worn on the scalp that capture brain signals in real-time. Preprocessing techniques, such as artifact removal, filtering, and segmentation, are explored to ensure that the extracted EEG signals are of high quality and suitable for subsequent analysis. A crucial stage in the fatigue driving detection process is feature extraction, which entails taking pertinent data out of the EEG signals and using it to distinguish between tired and non-fatigued states. We give a thorough rundown of several feature extraction techniques, such as topology features, frequency-domain analysis, and time-domain analysis. Techniques for frequency-domain analysis, such wavelet transform and power spectral density, allow the identification of particular frequency bands linked to weariness. Temporal patterns in the EEG signals are captured by time-domain features such autoregressive modeling and statistical moments. Furthermore, topological characteristics like brain area connection and synchronization provide light on how the brain’s functional network alters with weariness. Furthermore, the review includes an analysis of different classifiers used in fatigue driving detection, such as support vector machine (SVM), artificial neural network (ANN), and Bayesian classifier. We discuss the advantages and limitations of each classifier, along with their applications in EEG-based fatigue driving detection. Evaluation metrics and performance assessment are crucial aspects of any detection system. We discuss the commonly used evaluation criteria, including accuracy, sensitivity, specificity, and receiver operating characteristic (ROC) curves. Comparative analyses of existing models are conducted, highlighting their strengths and weaknesses. Additionally, we emphasize the need for a standardized data marking protocol and an increased number of test subjects to enhance the robustness and generalizability of fatigue driving detection models. The review also discusses the challenges and potential solutions in EEG-based fatigue driving detection. These challenges include variability in EEG signals across individuals, environmental factors, and the influence of different driving scenarios. To address these challenges, we propose solutions such as personalized models, multi-modal data fusion, and real-time implementation strategies. In conclusion, this comprehensive review provides an extensive overview of the current state of fatigue driving detection based on EEG signals. It covers various aspects, including signal acquisition, preprocessing, feature extraction, classification, performance evaluation, and challenges. The review aims to serve as a valuable resource for researchers, engineers, and practitioners in the field of driving safety, facilitating further advancements in fatigue detection technologies and ultimately enhancing road safety.
ABSTRACT
Objective:To explore the correlations of brain network functional connectivity (FC) alterations with cerebrospinal fluid (CSF) pathological biomarkers in patients with Alzheimer's disease (AD).Methods:A total of 39 patients with cognitive impairment, admitted to Department of Neurology, Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University from January 2020 to December 2022 were recruited; 23 patients were with AD and 16 with non-AD. Clinical data were compared between the 2 groups. Resting-state functional MRI (rs-fMRI) data were collected, and FC differences between brain networks and FC differences within brain networks were compared by independent component analysis. Correlations of FC differences between brain networks and FC differences within brain networks with concentrations of β-amyloid protein 1-42 (Aβ 1-42) and Tau protein in CSF were analyzed. Results:Compared with the non-AD group, AD group had significantly lower Aβ 1-42 in CSF ( P<0.05). Compared with those in the non-AD group, FC alterations between the left frontoparietal network (lFPN) and anterior default mode network (aDMN) and between the visual network (VN) and posterior cingulate cortex (PCC), as well as FC alterations in lFPN, were significantly increased in AD group ( P<0.05). Compared with those in the non-AD group, FC alterations between lFPN and cerebellar network (CEN), and FC alterations in aDMN, sensorimotor network (SMN) and VN were significantly decreased in AD group ( P<0.05). In AD group, FC in SMN was positively correlated with total Tau and phosphorylated-Tau181 in CSF ( P<0.05); FC between VN and PCC was positively correlated with total Tau in CSF ( P<0.05). CSF Aβ 1-42 was positively correlated with FC alterations in aDMN and VN, but negatively correlated with FC in FPN ( P<0.05). Conclusion:In AD patients, characteristic changes in FC within and between multiple brain networks are noted, which are related to changes of Tau protein and Aβ 1-42 in CSF.
ABSTRACT
ObjectiveTo compare the functional connectivity of brain networks in stroke patients with upper limb motor dysfunction during unilateral or bilateral upper limb movement using functional near-infrared spectroscopy (fNIRS). MethodsFrom April to June, 2021, 40 stroke patients with upper limb motor dysfunction in Department of Rehabilitation Medicine, Huashan Hospital, finished unilateral (affected) and bilateral upper limb movement. Eight-minute fNIRS data were collected before and after movement, and the functional activities and connectivity of prefrontal cortex (PFC), upper limb and hand functional area (H), primary sensory cortex (S1) were analyzed based on oxygenated hemoglobin. ResultsFunctional activities increased in affected H after unilateral task (t = -3.135, P < 0.05), while the functional connectivity increased between affected H and affected S1, affected H and unaffected S1, and affected S1 and unaffected S1 (|t| > 3.218, P < 0.05). There was no significant difference in the functional activities and connectivity of all the areas after bilateral upper limb task (|t| < 2.385, P > 0.05). The improvement of affected H was more after unilateral task than after bilateral upper limb task (t = 2.026, P < 0.05). ConclusionUnilateral affected upper limb training is more effective on functional activities and connectivity for corresponding brain regions than bilateral task.
ABSTRACT
OBJECTIVE@#To observe the changes of functional connectivity of brain pain-emotion regulation region in patients with cervical spondylosis of cervical type by functional magnetic resonance imaging (fMRI).@*METHODS@#Thirty-two subjects were selected. Of them, 16 patients with cervical spondylosis of cervical type were divided into an observation group and 16 healthy subjects into a control group. The patients in the observation group were treated with acupuncture at Tianzhu (BL 10), Jingbailao (EX-HN 15), Jianzhongshu (SI 15) and @*RESULTS@#In the observation group, the VAS score was (1.94±1.12) after the treatment, which was lower than (5.62±1.20) before treatment (@*CONCLUSION@#Pain involves the formation and expression of "pain-emotion-cognition". Acupuncture can systematically regulate the brain functional connections between cognitive regions such as dorsal prefrontal lobe and anterior cingulate gyrus and emotional regions such as insula and VTA in patients with cervical spondylosis of cervical type, suggesting that acupuncture has a multi-dimensional and comprehensive regulation effect on pain.
Subject(s)
Humans , Acupuncture Therapy , Brain/diagnostic imaging , Emotions , Magnetic Resonance Imaging , Pain , Spondylosis/therapyABSTRACT
Objective To detect whether and where brain functional connectivity exists in the resting state of patients with early-onset schizophrenia by using functional magnetic resonance imaging (fMRI). Methods Nineteen early-onset schizophrenic patients were diagnosed with Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition (DSM-IV) of American Psychiatric Association. The 19 early-onset schizophrenic patients and another 19 healthy volunteers underwent fMRI in resting state. Cingulate gyrus was selected as region of interest and the difference was analyzed in the cingulate gyrus functional connectivity pattern between the 19 patients with early-onset schizophrenia (EOS) and 19 matched controls using resting-state fMRI. A two-sample t test was performed on the individual in a voxel by voxel manner. Results Statistical map was set a combined threshold of P＜0.005 and the number of voxel>20. Functional connectivity in the resting state was abnormal in the patients,including decreased functional connectivity and increased functional connectivity. The abnormal area was distributed all over the brain. The brain area with decreased functional connectivity included bilateral posterior cerebellar lobes, superior frontal gyrus, middle frontal gyrus, gyrus rectus,hippocampus, cuneus gyrus,fusiform gyrus,middle occipital gyrus,inferior occipital gyrus, right inferior temporal gyrus,right middle temporal gyrus, and right angular gyrus. The brain area with increased functional connectivity included left middle temporal and left inferior temporal gyrus. Conclusion Abnormal cingulate gyrus functional connectivity of schizophrenia might exist in the resting state. Resting state fMRI is important for the research of schizophrenia.