Major depressive disorder (MDD) is characterized by impairments in mood and cognitive functioning, and it is a prominent source of global disability and stress. A functional magnetic resonance imaging (fMRI) can aid clinicians in their assessments of individuals for the identification of MDD. Herein, we employ a deep learning approach to the issue of MDD classification. Resting-state fMRI data from 821 individuals with MDD and 765 healthy controls (HCs) is employed for investigation. An ensemble model based on graph neural network (GNN) has been created with the goal of identifying patients with MDD among HCs as well as differentiation between first-episode and recurrent MDDs. The graph convolutional network (GCN), graph attention network (GAT), and GraphSAGE models serve as a base models for the ensemble model that was developed with individual whole-brain functional networks. The ensemble's performance is evaluated using upsampling and downsampling, along with 10-fold cross-validation. The ensemble model achieved an upsampling accuracy of 71.18% and a downsampling accuracy of 70.24% for MDD and HC classification. While comparing first-episode patients with recurrent patients, the upsampling accuracy is 77.78% and the downsampling accuracy is 71.96%. According to the findings of this study, the proposed GNN-based ensemble model achieves a higher level of accuracy and suggests that our model produces can assist healthcare professionals in identifying MDD.
Mindfulness meditators often show greater efficiency in resolving response conflicts than non-meditators. However, the neural mechanisms underlying the improved behavioral efficiency are unclear. Here, we investigated frontal theta dynamics - a neural mechanism involved in cognitive control processes - in long-term mindfulness meditators. The dynamics of EEG theta oscillations (4-8Hz) recorded over the medial frontal cortex (MFC) were examined in terms of their power (MFC theta power) and their functional connectivity with other brain areas (the MFC-centered theta network). Using a flanker-type paradigm, EEG data were obtained from twenty-two long-term mindfulness meditators and compared to those from twenty-three matched controls without meditation experience. Meditators showed more efficient cognitive control after conflicts, evidenced by fewer error responses irrespective of response timing. Furthermore, meditators exhibited enhanced conflict modulations of the MFC-centered theta network shortly before the response, in particular for the functional connection between the MFC and the motor cortex. In contrast, MFC theta power was comparable between groups. These results suggest that the higher behavioral efficiency after conflicts in mindfulness meditators could be a function of increased engagement to control the motor system in association with the MFC-centered theta network.
Network slicing shows promise as a means to endow 5G networks with flexible and dynamic features. Network function virtualization (NFV) and software-defined networking (SDN) are the key methods for deploying network slicing, which will enable end-to-end (E2E) isolation services permitting each slice to be customized depending on service requirements. The goal of this investigation is to construct network slices through a machine learning algorithm and allocate resources for the newly created slices using dynamic programming in an efficient manner. A substrate network is constructed with a list of key performance indicators (KPIs) like CPU capacity, bandwidth, delay, link capacity, and security level. After that, network slices are produced by employing multi-layer perceptron (MLP) using the adaptive moment estimation (ADAM) optimization algorithm. For each requested service, the network slices are categorized as massive machine-type communications (mMTC), enhanced mobile broadband (eMBB), and ultra-reliable low-latency communications (uRLLC). After network slicing, resources are provided to the services that have been requested. In order to maximize the total user access rate and resource efficiency, Dijkstra’s algorithm is adopted for resource allocation that determines the shortest path between nodes in the substrate network. The simulation output shows that the present model allocates optimum slices to the requested services with high resource efficiency and reduced total bandwidth utilization.
The network slicing of physical infrastructure is required for fifth-generation mobile networks to make significant changes in how service providers deliver and defend services in the face of evolving end-user performance requirements. To perform this, a fast and secure slicing technique is employed for node allocation and connection establishment, which necessitates the usage of a large number of domain applications across the network. PROMETHEE-II and SLE algorithms were used in this study’s approach to network design for node allocation and link construction, respectively. The PROMETHEE-II approach takes into account a variety of node characteristics while constructing a node importance rank array (NIRA), including the node capacity, bandwidth of neighboring connections, degree of the node, and proximity centrality among others. The SLE method is proposed to record all possible link configurations for the network slice request (NSR) nodes to guarantee that the shortest path array (SPA) of the NSR has a high acceptance rate. Performance metrics such as the service revenue and acceptance ratio were considered to evaluate the effectiveness of the suggested approach. The effectiveness of network slicing has been further examined under different infrastructure models to determine whether a small-world network structure is beneficial to 5G network. For each scenario, simulations were carried out and the results were compared to previously published findings from other sources.
Facial stimuli are relevant social cues for humans and essential signals for adequate social interaction. Impairments in face processing are well-documented in schizophrenia and linked to symptomatology, yet the underlying neural dynamics remain unclear. Here, we investigated the processing and underlying neural temporal dynamics of task-irrelevant emotional face stimuli using combined EEG/fMRI in 14 individuals with schizophrenia and 14 matched healthy controls. Specifically, fMRI-informed region-of-interests were subjected to EEG-Dynamic Causal Modeling (DCM) analyses. Among six fMRI-informed EEG-DCM models, alterations in effective connectivity emerged between the primary visual cortex (V1) and the left occipital fusiform gyrus (lOFG). Specifically, individuals with schizophrenia showed enhanced backward connectivity from the lOFG to V1 for stimuli preceded by fearful (but not happy or neutral) faces. Connectivity strength was strongly correlated with self-reported difficulties in comprehending, processing, or articulating emotions (as assessed by the Toronto Alexithymia Scale-20) in individuals with schizophrenia but not in healthy controls. Enhanced backward connectivity from the lOFG to V1 potentially indicates heightened attention towards fearful surroundings and a propensity to assign salience to these stimuli in individuals with schizophrenia. The link to TAS-20 scores indicates that this neural deficit has real-world implications for how individuals with schizophrenia perceive and relate to their emotions and the external world, potentially contributing to the social and cognitive difficulties observed in the disorder.
Network slicing is crucial to the 5G architecture because it enables the virtualization of network resources into a logical network. Network slices are created, isolated, and managed using software-defined networking (SDN) and network function virtualization (NFV). The virtual network function (VNF) manager must devise strategies for all stages of network slicing to ensure optimal allocation of physical infrastructure (PI) resources to high-acceptance virtual service requests (VSRs). This paper investigates two independent network slicing frameworks named as dual-slice isolation and management strategy (D-SIMS) and recommends the best of the two based on performance measurements. D-SIMS places VNFs for network slicing using self-sustained resource reservation (SSRR) and master-sliced resource reservation (MSRR), with some flexibility for the VNF manager to choose between them based on the degree to which the underlying physical infrastructure has been sliced. The present research work consists of two phases: the first deals with the creation of slices, and the second with determining the most efficient way to distribute resources among them. A deep neural network (DNN) technique is used in the first stage to generate slices for both PI and VSR. Then, in the second stage, we propose D-SIMS for resource allocation, which uses both the fuzzy-PROMETHEE method for node mapping and Dijkstra’s algorithm for link mapping. During the slice creation phase, the proposed DNN training method’s classification performance is evaluated using accuracy, precision, recall, and F1 score measures. To assess the success of resource allocation, metrics such as acceptance rate and resource effectiveness are used. The performance benefit is investigated under various network conditions and VSRs. Finally, to demonstrate the importance of the proposed work, we compare the simulation results to those in the academic literature.