Neuroscience informatics最新文献

Human cognitive load level assessment is a challenging issue in the field of functional brain imaging. This work aims to study different cognitive load levels statistically from brain hemodynamics. Since the functional brain activities can be evaluated by functional near-infrared spectroscopy (fNIRS), a renowned fNIRS dataset is considered for this work. The dataset contains fNIRS data of three types of n-back tasks (0-back, 2-back, and 3-back) of twenty-six healthy volunteers. The fNIRS signals were pre-processed and separated according to the tasks and trials. The mean changes of oxygenated hemoglobin (HbO₂) and deoxygenated hemoglobin (dHb) are calculated from each trial corresponding to the tasks and tested for significant inference among three levels utilizing analysis of variance (ANOVA). From the outcomes of the ANOVA ($p<0.005$), two significant channels (AF7 (frontal) and C3h (motor)) were figured out. The significance of these two channels was further justified using the property consistency test by three different time intervals of hemodynamics inside the total task period. The latter result also explored the functional pattern of the hemodynamics of AF7 and C3h positions. Moreover, two-level cognitive load (due to easy i.e., 0-back test and hard i.e., 2-back and 3-back task) is classified using support vector machine and found classification accuracy in average 73.40%±0.076 for HbO₂ data and 71.48%±0.061 for dHb data. The study signposts the collective role played by both fNIRS signals and statistical valuation of functioning cognitive load efficacy to use fNIRS as a cognitive load assessment biomarker.

An accurate, fully automatic detection and segmentation technique for brain tumors in magnetic resonance images (MRI) is introduced. The approach basically combines geometric active contours segmentation with a deep learning-based initialization. As a pre-processing step, an anisotropic filter is used to smooth the image; afterwards, the segmentation process takes place in two phases: the first one is based on the concept of transfer learning, where a pre-trained convolutional neural network coupled with a detector is fine-tuned using a training set of 388 T1-weighted contrast enhanced MRI images that contain a brain tumor (Meningioma); this trained network is able to automatically detect the location of the tumor by generating a bounding box with certain coordinates. The second phase takes place by using the coordinates of the bounding box to initialize the geometric active contour that iteratively evolves towards the tumor's boundaries. While most of the ingredients of this processing chain are more or less well known, the main contribution of this work is in integrating the various techniques in a novel and hopefully clever form, which could take the best of both geometric segmentation algorithms and neural networks, with a relatively light training phase. The performance of such a processing network is evaluated using a separate testing set of 97 MRI images containing the same type of brain tumor. The technique proves to be remarkably effective, with a precision of 97.92%, recall of 96.91%, F-measure of 97.41% and an average Dice similarity coefficient (DSC) for segmented images above 0.95.

COVID-19 epidemic has swiftly disrupted our day-to-day lives affecting the international trade and movements. Wearing a face mask to protect one's face has become the new normal. In the near future, many public service providers will expect the clients to wear masks appropriately to partake of their services. Therefore, face mask detection has become a critical duty to aid worldwide civilization. This paper provides a simple way to achieve this objective utilising some fundamental Machine Learning tools as TensorFlow, Keras, OpenCV and Scikit-Learn. The suggested technique successfully recognises the face in the image or video and then determines whether or not it has a mask on it. As a surveillance job performer, it can also recognise a face together with a mask in motion as well as in a video. The technique attains excellent accuracy. We investigate optimal parameter values for the Convolutional Neural Network model (CNN) in order to identify the existence of masks accurately without generating over-fitting.

In the rapidly growing world of technology and evolution, the outbreak and emergences diseases have become a critical issue. Precaution, prevention and controlling the diseases by technology has become the major challenge for healthcare professionals and health care industries. Maintaining a healthy lifestyle has become impossible in the busy work schedules. Smart health monitoring system is the solution to the above poses challenges. The recent revolution of industry 5.0 and 5G has led to development of smart cum cost effective sensors which help in real time health monitoring or individuals. The SHM has led to fast, cost effective, and reliable health monitoring services from remote locations which was not possible with traditional health care systems. The integration of blockchain framework improved data security and data privacy of confidential data of patient to prevent the data misuse against patients. Involvement of Deep Learning and Machine learning to analyze health data to achieve multiple targets has helped attain preventive healthcare and fatality management in patients. This has helped in the early detection of chronic diseases which was not possible recently. To make the services more cost effective and real time, the integration of cloud computing and cloud storage has been implemented. The work presents the systematic review of SHM along with recent advancements in SHM with existing challenges.

Text devices are effectively and heavily used for interactions these days. Emotion extraction from the text has derived huge importance and is upcoming area of research in Natural Language Processing. Recognition of emotions from text has high practical utilities for quality improvement like in Human-Computer Interaction, recommendation systems, online education, data mining and so on. However, there are the issues of irrelevant feature extraction during emotion extraction from text. It causes mis-prediction of emotion. To overcome such challenges, this paper proposes a Leaky Relu activated Deep Neural Network (LRA-DNN). The proposed model comes under four categories, such as pre-processing, feature extraction, ranking and classification. The collected data from the dataset are pre-processed for data cleansing, appropriate features are extracted from the pre-processed data, relevant ranks are assigned for each extracted feature in the ranking phase and finally, the data are classified and accurate output is obtained from the classification phase. Publically available datasets are used in this research to compare the results obtained by the proposed LRA-DNN with the previous state-of-art algorithms. The outcomes indicated that the proposed LRA-DNN obtains the highest accuracy, sensitivity, and specificity at the rate of 94.77%, 92.23%, and 95.91% respectively which is promising compared to the existing ANN, DNN and CNN methods. It also efficiently reduces the mis-prediction and misclassification error.

Fetal Alcohol Spectrum Disorder (FASD) comprises the phenotypes induced by prenatal alcohol exposure. Understanding the molecular mechanisms of FASD is needed since it is a public health problem. This study aimed to evaluate the impact of ethanol in the differential gene expression (DGE) of embryonic cells and fetal tissues by performing a transcriptome meta-analysis in microarrays datasets publicly available. The datasets were obtained in the GEO database and DGE was evaluated, followed by meta-analysis. DGE was also analyzed in a RNA-Seq dataset, although it was not included in the meta-analysis. To filter the main candidate genes, a database and literature review was performed, followed by ontologies enrichment analyses. In the meta-analysis, 1,938 genes were deregulated and 487 were perturbed in the RNA-Seq. Calcium homeostasis and neuroinflammation genes were overrepresented in the meta-analysis and RNA-Seq, respectively. After the database and literature review, DOCK8, FOXG1, IL1RN, and PRKN genes were proposed as new candidates for FASD; they are associated with neurodevelopment and neuroinflammation. BDNF and SLC2A1, previously associated to FASD, were also suggested in meta-analysis as candidate genes. It is known neuroinflammation reduction might help to minimize the alcohol damage. Hence, there is an urgent need to understand FASD molecular mechanisms to help in strategies aimed at preventing ethanol-induced neurologic damage.

The visual evoked potential as an electrophysiological signal is mainly used in the neurophysiological exploration of the optic nerves. Traditionally, medical doctors base their diagnosis of specific pathologies related to the time delay of the nerve flow on the time scale. In this context, the VEP latency P100 that reflects a temporal notion is considered the main characteristic on which human interpretation is based. However, its value is influenced by different factors and remains a limited method. This insufficiency triggers our interest instead in deep learning architectures, taking into consideration and adapting to the specificity of each particularity related to the laboratory of the neurophysiological exploration unit in the hospital. The comparison between the results obtained from Matlab by the application of the CNN as well as the RNN, based on the evaluation parameters calculated after k-fold cross-validation, confirms that the CNN-1D architecture can be considered powerful in terms of reliability of classification between signals that are related to pathological subjects and normal ones, which privileges the use of this architecture compared with recurrent neural networks that are less reliable and require more time for execution, subsequently the use of the CNN will allow us to avoid even the extraction of attributes for the discrimination between the two classes object of classification, with the possibility to progressively improve the performance of the solution over time based on the new signals acquired in the VEP analysis laboratory.

Imagined Speech (IS) is the imagination of speech without using the tongue or muscles. In recent studies, IS tasks are increasingly investigated for the Brain-Computer Interface (BCI) applications. Electroencephalography (EEG) signals, which record brain activity, can be used to analyze BCI-based tasks utilizing Machine Learning (ML) methods. The current paper considers decoding IS brain waves using the fusion of classical signal processing, Graph Signal Processing (GSP), and Graph Learning (GL) based features. The proposed fusion method, named GraphIS (short for a Graph-based Imagined Speech BCI decoder), is applied to the four-class classification (three classes of the imagined words, in addition to the rest state) on EEG recordings of fifteen subjects. Results show that GSP and GL-based features can highly improve the performance of classification outcomes compared to using only classical signal processing features and over the state-of-the-art Common Spatial Pattern (CSP) feature extractor by considering the spatial information of the signals as well as interactions between channels in regions of interest. The proposed GraphIS method leads to a mean accuracy of 50.10% in the studied four-class IS classification task, compared to using only one feature set with an accuracy of 47.86% and 46.10%, and also the state-of-the-art CSP with an accuracy of 47.10%. Additionally, using an EEG connectivity map of the electrode signals obtained from GL methods, we also found a strong connection in the right frontal region as well as in the left frontal regions during IS, which had not been focused on in the previous IS papers.

Increased population has led to create the environmental related issues. Zinc Oxide has great attention due to its application in versatile smart and functional material. In the recent paper, we have observed the variation in shape and size for different precursor (0.45 M - Zn acetate dihydrate, Zn nitrate hexahydrate) with aloe vera extract ZnO nanoparticles, data analytics have been prepared with annealing at 650 ^∘C. The prepared solution was analyzed by using simple solution method. Structural, morphological, optical and electrical properties defined certain nanomaterials. XRD spectra showed polycrystalline in nature. In the case of Zn nitrate, more instance peaks are found and SEM reveals the particle size drop into a range of 50-90 nm. Analysis of FTIR was conducted to classify the mineral constituents. The further capacitance levels are measured at a low scale. The resistivity spectrum of ZnO nanoparticles ranged from $3\times {10}^{-2}$ to $5\times {10}^{-2}$ (in cm)⁻¹. Optical band gap of the synthesized particles lies in the range of 3.10-3.20 eV, which confirmed that nanoparticles are suitable for gas sensor and solar cell applications. These synthesized nanoparticles can further be used for the neuroscience application such as fabrication of medical instruments and for medical purpose too. In turn, these materials contribute to novel diagnostic and therapeutic strategies, including drug delivery, neuroprotection, neural regeneration, neuroimaging and neurosurgery.

Background: Prophylactic treatment for recurrence of febrile seizure generally consists of intermittent administration of diazepam or clobazam, or long-term treatment with valproic acid or phenobarbital. However, the adverse effects outweigh the benefits. A newer, effective, more tolerable drug treatment is warranted.

Objective: To study melatonin efficacy in prevention of recurrence of one or more episodes of either simple or complex febrile seizure compared to a control group.

Methods: A quasi-experimental study in children who were diagnosed with febrile seizure in Bhumibol Adulyadej Hospital, between 6 months to 5 years old, divided into two groups, melatonin group and control group, depending upon parental convenience. Melatonin was given 0.3 mg/kg/dose every 8 hours for 48 to 72 hours during febrile illness to melatonin group if body temperature was more than 37.5 °C. Control group had no medicine. Patients were followed at 3 and 6 months.

Results: The study included 23 patients in the melatonin group and 41 in the control group. Mean age of diagnosed of febrile seizure onset was 17.3 and 21.6 months, respectively. In the melatonin group, 8.7% of patients had recurrent febrile seizure compared to 36.6% in the control group, which is statistically significant (P-value 0.015, RD −0.28(95%CI: −0.46 to −0.09)). There was no statistically significant difference in adverse effects between the two groups.

Conclusion: This study demonstrates the efficacy and safety of short-term melatonin use to prevent the recurrence of one or more episodes of either simple or complex-febrile seizure in children.