Network-Computation in Neural Systems最新文献

The performance of time-series classification of electroencephalographic data varies strongly across experimental paradigms and study participants. Reasons are task-dependent differences in neuronal processing and seemingly random variations between subjects, amongst others. The effect of data pre-processing techniques to ameliorate these challenges is relatively little studied. Here, the influence of spatial filter optimization methods and non-linear data transformation on time-series classification performance is analyzed by the example of high-frequency somatosensory evoked responses. This is a model paradigm for the analysis of high-frequency electroencephalography data at a very low signal-to-noise ratio, which emphasizes the differences of the explored methods. For the utilized data, it was found that the individual signal-to-noise ratio explained up to 74% of the performance differences between subjects. While data pre-processing was shown to increase average time-series classification performance, it could not fully compensate the signal-to-noise ratio differences between the subjects. This study proposes an algorithm to prototype and benchmark pre-processing pipelines for a paradigm and data set at hand. Extreme learning machines, Random Forest, and Logistic Regression can be used quickly to compare a set of potentially suitable pipelines. For subsequent classification, however, machine learning models were shown to provide better accuracy.

In this paper, we propose a Gudermannian neural network scheme to solve optimal control problems of fractional-order system with delays in state and control. The fractional derivative is described in the Caputo sense. The problem is first transformed, using a Padé approximation, to one without a time-delayed argument. We try to approximate the solution of the Hamiltonian conditions based on the Pontryagin minimum principle. For this purpose, we use trial solutions for the states, Lagrange multipliers, and control functions where these trial solutions are constructed by using two-layered perceptron. We then minimize the error function using an unconstrained optimization scheme where weight and biases associated with all neurons are unknown. Some numerical examples are given to illustrate the effectiveness of the proposed method.

Recognition and diagnosis of stroke from magnetic resonance Image (MRIs) are significant for medical procedures in therapeutic standards. The primary goal of this scheme is the discovery of stroke in tumour locale in brain tissues influenced image. The probability of stroke is categorized on brain tumour influenced images into mild, moderate, or serious cases. The mild and moderate phases of stroke are recognized as "Ahead of schedule" findings and serious cases are distinguished as "Advance" determination. The proposed Glioblastoma brain tumour recognition strategy used the Multifaceted Brain Tumour Image Segmentation test open-access dataset for evaluating the presentation. The brain images are classified utilizing the Deep Neural Networks classification algorithm as normal and abnormal images. The tumour region is segmented from the identified set of abnormal images using the normalized graph cut algorithm. The stroke likelihood is identified using the Deep Neural Networks by analysing the proximity of tumour section in brain matters. The proposed stroke analysis framework accurately groups 10 images as "Right on time" stroke probability images and accomplishes 90% order rate. The proposed stroke prediction framework effectively characterizes images as "Advance" stroke probability images and accomplishes 90% characterization rate.

The segmentation of brain images is a leading quantitative measure for detecting physiological changes and for analysing structural functions. Based on trends and dimensions of brain, the images indicate heterogeneity. Accurate brain tumour segmentation remains a critical challenge despite the persistent efforts of researchers were owing to a variety of obstacles. This impacts the outcome of tumour detection, causing errors. For addressing this issue, a Feature-Map based Transform Model (FMTM) is introduced to focus on heterogeneous features of input picture to map differences and intensity based on transition Fourier. Unchecked machine learning is used for reliable characteristic map recognition in this mapping process. For the determination of severity and variability, the method of identification depends on symmetry and texture. Learning instances are taught to improve precision using predefined data sets, regardless of loss of labels. The process is recurring until the maximum precision of tumour detection is achieved in low convergence. In this research, FMTM has been applied to brain tumour segmentation to automatically extract feature representations and produce accurate and steady performance because of promising performance made by powerful transition Fourier methods. The suggested model's performance is shown by the metrics processing time, precision, accuracy, and F1-Score.

Security and privacy are regarded as the greatest priority in any real-world smart ecosystem built on the Internet of Things (IoT) paradigm. In this study, a SqueezeNet model for IoT threat detection is built using Sine Cosine Sea Lion Optimization (SCSLnO). The Base Station (BS) carries out intrusion detection. The Hausdorff distance is used to determine which features are important. Using the SqueezeNet model, attack detection is carried out, and the network classifier is trained using SCSLnO, which is developed by combining the Sine Cosine Algorithm (SCA) with Sea Lion Optimization (SLnO). BoT-IoT and NSL-KDD datasets are used for the analysis. In comparison to existing approaches, PSO-KNN/SVM, Voting Ensemble Classifier, Deep NN, and Deep learning, the accuracy value produced by devised method for the BoT-IoT dataset is 10.75%, 8.45%, 6.36%, and 3.51% higher when the training percentage is 90.

COVID-19 pandemic created a turmoil across nations due to Severe Acute Respiratory Syndrome Corona virus-1(SARS - Co-V-2). The severity of COVID-19 symptoms is starting from cold, breathing problems, issues in respiratory system which may also lead to life threatening situations. This disease is widely contaminating and transmitted from man-to-man. The contamination is spreading when the human organs like eyes, nose, and mouth get in contact with contaminated fluids. This virus can be screened through performing a nasopharyngeal swab test which is time consuming. So the physicians are preferring the fast detection methods like chest radiography images and CT scans. At times some confusion in finding out the accurate disorder from chest radiography images can happen. To overcome this issue this study reviews several deep learning and machine learning procedures to be implemented in X-ray images of chest. This also helps the professionals to find out the other types of malfunctions happening in the chest other than COVID-19 also. This review can act as a guidance to the doctors and radiologists in identifying the COVID-19 and other types of viruses causing illness in the human anatomy and can provide aid soon.

Dimension reduction is one of the most sought-after strategies to cope with high-dimensional ever-expanding datasets. To address this, a novel deep-learning architecture has been designed with multiple deconstruction and single reconstruction layers for non-negative matrix factorization aimed at low-rank approximation. This design ensures that the reconstructed input matrix has a unique pair of factor matrices. The two-stage approach, namely, pretraining and stacking, aids in the robustness of the architecture. The sigmoid function has been adjusted in such a way that fulfils the non-negativity criteria and also helps to alleviate the data-loss problem. Xavier initialization technique aids in the solution of the exploding or vanishing gradient problem. The objective function involves regularizer that ensures the best possible approximation of the input matrix. The superior performance of MDSR-NMF, over six well-known dimension reduction methods, has been demonstrated extensively using five datasets for classification and clustering. Computational complexity and convergence analysis have also been presented to establish the model.

The interpeak latency is a crucial characteristic of upper limb somatosensory evoked potentials (USEPs). However, the existing research on the correlation between interpeak latency and consciousness disorders is currently limited. We aimed to investigate how USEPs can contribute to the diagnosis of consciousness disorders. A retrospective analysis was conducted on 10 patients who underwent repetitive transcranial magnetic stimulation (rTMS) for consciousness disorders. The interpeak latency N13-N20, Glasgow coma scale (GCS), and Chinese Nanjing persistent vegetative state scale (CNPVSS) were evaluated before and after rTMS treatment, and the linear correlation between N13-N20, GCS, and CNPVSS was analysed. The scores of CNPVSS and GCS significantly increased in the first, second, and third months after rTMS. The N13-N20 was shorter in the second and third months after rTMS compared to before treatment. rTMS was found to shorten the N13-N20 latency, and there was a negative correlation between N13-N20 and the score of consciousness disorders. N13-N20 can serve as an objective index for evaluating consciousness disorders. This research provides potential insights for doctors in diagnosing patients with consciousness disorders.

Background: The use of shorter TR and finer atlases in rs-fMRI can provide greater detail on brain function and anatomy. However, there is limited understanding of the effect of this combination on brain network properties.

Methods: A study was conducted with 20 healthy young volunteers who underwent rs-fMRI scans with both shorter (0.5s) and long (2s) TR. Two atlases with different degrees of granularity (90 vs 200 regions) were used to extract rs-fMRI signals. Several network metrics, including small-worldness, Cp, Lp, Eloc, and Eg, were calculated. Two-factor ANOVA and two-sample t-tests were conducted for both the single spectrum and five sub-frequency bands.

Results: The network constructed using the combination of shorter TR and finer atlas showed significant enhancements in Cp, Eloc, and Eg, as well as reductions in Lp and γ in both the single spectrum and subspectrum (p < 0.05, Bonferroni correction). Network properties in the 0.082-0.1 Hz frequency range were weaker than those in the 0.01-0.082 Hz range.

Conclusion: Our findings suggest that the use of shorter TR and finer atlas can positively affect the topological characteristics of brain networks. These insights can inform the development of brain network construction methods.

Neural Style Transfer (NST) has been a widely researched topic as of late enabling new forms of image manipulation. Here we perform an extensive study on NST algorithms and extend the existing methods with custom modifications for application to Indian art styles. In this paper, we aim to provide a comprehensive analysis of various methods ranging from the seminal work of Gatys et al which demonstrated the power of Convolutional Neural Networks (CNNs) in creating artistic imagery by separating and recombining image content and style, to the state of the art image-to-image translation models which use Generative Adversarial Networks (GANs) to learn the mapping between two domain of images. We observe and infer based on the results produced by the models on which one could be a more suitable approach for Indian art styles, especially Tanjore paintings which are unique compared to the Western art styles. We then propose the method which is more suitable for the domain of Indian Art style along with custom architecture which includes an enhancement and evaluation module. We then present evaluation methods, both qualitative and quantitative which includes our proposed metric, to evaluate the results produced by the model.