Network Function Research Articles

Characteristics and Neural Mechanisms of Sleep-Wake Disturbances After Traumatic Brain Injury.

Sleep-wake disturbances (SWDs) are one of the most common complaints following traumatic brain injury (TBI). The high prevalence and socioeconomic burden of SWDs post-TBI have only been recognized in the past decade. Common SWDs induced by TBI include excessive daytime sleepiness (EDS), hypersomnia, insomnia, obstructive sleep apnea (OSA), and circadian rhythm sleep disorders. Sleep disturbances can significantly compromise quality of life, strain interpersonal relationships, diminish work productivity, exacerbate other clinical conditions, and impede the rehabilitation process of TBI patients. Consequently, the prompt regulation and enhancement of sleep homeostasis in TBI patients is of paramount importance. Although studies have shown that abnormal neural network function, neuroendocrine changes, disturbance of sleep-wake regulators, and immune inflammatory responses related to brain structural damage induced by TBI are involved in the development of SWDs, the exact neuropathological mechanisms are still poorly understood. Therefore, we systematically review the current clinical and experimental studies on the characteristics and possible neural mechanisms of post-TBI SWDs. Elucidating the neural underpinnings of post-TBI SWDs holds the potential to diversify and enhance therapeutic approaches for these conditions. Such advancements could hasten the recuperation of TBI patients and ameliorate their overall quality of life. It is our aspiration that departments specializing in neurosurgery, rehabilitation, and neuropsychiatry will be able to recognize and address these conditions promptly, thereby facilitating the healing journey of affected individuals.

Mathematical Model of the Process of Data Transmission over the Radio Channel of Cyber-Physical Systems

This article introduces a refined mathematical model to evaluate the quality of mobile radio channels within cyber-physical systems, employing the topological transformation of stochastic networks. The operation of the radio channel is conceptualized as a stochastic network, enabling the derivation of critical metrics such as an equivalent function, mathematical expectation, variance, and the time distribution function of the implemented processes. The model uses the Gamma distribution for the initial distribution functions of random variables, enhancing its analytical precision. A significant advancement of this study is the development of a comprehensive model that describes the data transmission process through phases of connection establishment, information transmission, and connection maintenance. The innovative aspect of this research lies in applying an equivalent function to a stochastic network that includes a logical “AND” node with gamma-distributed incoming branches. The stochastic network presented in the article, which includes a logical “AND” node, helps to elucidate the mechanism for obtaining an equivalent function for such networks, allowing the application area of the GERT method to be expanded. This methodological enhancement extends the previously limited scope of topological transformation methods, which only applied to exponential distribution models for the timing of branch inputs. By integrating a Gamma distribution, the model simplifies the equivalent function and reduces the computational complexity required to assess the radio channel’s quality, ensuring the accuracy needed for engineering calculations. Moreover, the proposed method requires 25–40% fewer series members than the traditional Taylor series decomposition, while maintaining comparable computational complexity for the typical series members. Furthermore, the maximum absolute error in the calculations is capped at 9 × 10−3, which is well within acceptable limits for engineering purposes. Primarily designed for radio channels in cyber-physical systems, the model’s applicability extends to wireless communications, providing a valuable tool for evaluating channel efficiency and security in the face of increasing cyber threats.

Regulation of mitochondrial network architecture and function in mesenchymal stem cells by micropatterned surfaces

Abstract Mitochondrial network architecture, which is closely related to mitochondrial function, is mechanically sensitive and regulated by multiple stimuli. However, the effects of microtopographic cues on mitochondria remain poorly defined. Herein, polycaprolactone (PCL) surfaces were used as models to investigate how micropatterns regulate mitochondrial network architecture and function in rat adipose-derived stem cells (rASCs). It was found that large pit (LP) induced rASCs to form larger and more complex mitochondrial networks. Consistently, the expression of key genes related to mitochondrial dynamics revealed that mitochondrial fusion (MFN1 and MFN2) and midzone fission (DRP1 and MFF) were increased in rASCs on LP. In contrast, the middle pit (MP) enhanced mitochondrial biogenesis, as evidenced by the larger mitochondrial area and higher expression of PGC-1. Both LP and MP promoted ATP production in rASCs. It is likely that LP increased ATP levels through modulating mitochondrial network architecture while MP stimulated mitochondria biogenesis to do so. Our study clarified the regulation of micropatterned surfaces on mitochondria, highlighting the potential of LP and MP as a simple platform to stimulate mitochondria and the subsequent cellular function of MSCs.

Cycle-Star Motifs: Network Response to Link Modifications

Understanding efficient modifications to improve network functionality is a fundamental problem of scientific and industrial interest. We study the response of network dynamics against link modifications on a weakly connected directed graph consisting of two strongly connected components: an undirected star and an undirected cycle. We assume that there are directed edges starting from the cycle and ending at the star (master–slave formalism). We modify the graph by adding directed edges of arbitrarily large weights starting from the star and ending at the cycle (opposite direction of the cutset). We provide criteria (based on the sizes of the star and cycle, the coupling structure, and the weights of cutset and modification edges) that determine how the modification affects the spectral gap of the Laplacian matrix. We apply our approach to understand the modifications that either enhance or hinder synchronization in networks of chaotic Lorenz systems as well as Rössler. Our results show that the hindrance of collective dynamics due to link additions is not atypical as previously anticipated by modification analysis and thus allows for better control of collective properties.

DECENTRALIZED QUANTUM COMPILATION FRAMEWORK: EMPOWERING DISTRIBUTED QUANTUM COMPUTING THROUGH MODULARITY

Quantum algorithms require large resources in terms of qubit number, much larger than those available with current NISQ processors. With the network and communication functionalities provided by the Quantum Internet, Distributed Quantum Computing (DQC) is considered as a scalable approach for increasing the number of available qubits for computational tasks. For DQC to be effective and efficient, a quantum compiler must find the best partitioning for the quantum algorithm and then perform smart remote operation scheduling to optimize EPR pair consumption. At the same time, the quantum compiler should also find the best local transformation for each partition. In this paper we present a modular quantum compilation framework for DQC that takes into account both network and device constraints and characteristics. We implemented and tested a quantum compiler based on the proposed framework with some circuits of interest, such as the VQE and QFT ones, considering different network topologies, with quantum processors characterized by heavy hexagon coupling maps. We also devised a strategy for remote scheduling that can exploit both TeleGate and TeleData operations and tested the impact of using either only TeleGates or both. The evaluation results show that TeleData operations may have a positive impact on the number of consumed EPR pairs, while choosing a more connected network topology helps reduce the number of layers dedicated to remote operations. Keywords— Distributed quantum computing (DQC), quantum compilation, quantum Internet

Activation Functions for Neural Networks: Application and Performance-based Comparison

Past decade has seen explosive growth of Deep Learning (DL) algorithms based on Artificial Neural Networks (ANNs) and its applications in vast emerging domains to solve real world complex problems. The DL architecture uses Activation Functions (AFs), to perform the task of finding relationship between the input feature and the output. Essential building blocks of any ANN are AFs which bring the required non-linearity of the output in the Output layer of network. Layers of ANNs are combinations of linear and nonlinear AFs. Most extensively used AFs are Sigmoid, Hyperbolic Tangent (Tanh), Rectified Linear Unit (ReLU) etc to name a few. Choosing an AF for a particular AF depends on various factors such as Nature of Application, Design of ANN, Optimizers used in the network, Complexity of Data etc. This paper presents a survey on most widely used AFs along with the important consideration while selecting an AF on a specific problem domain. A broad guideline on selecting an AF based on the literature survey has been presented to help researchers in employing suitable AF in their problem domain.

GANSharp: High-definition image reconstruction using generative adversarial networks

In the realm of digital imaging, enhancing low-resolution images to high-definition quality is a pivotal challenge, particularly crucial for applications in medical imaging, security, and remote sensing. Traditional methods, primarily relying on basic interpolation techniques, often result in images that lack detail and fidelity. GANSharp introduces an innovative GAN-based framework that substantially improves the generator network, incorporating adversarial and perceptual loss functions for enhanced image reconstruction. The core issue addressed is the loss of critical information during down-sampling processes. To counteract this, we proposed a GAN-based method leveraging deep learning algorithms, trained using sets of both low- and high-resolution images. Our approach, which focuses on expanding the generator network’s size and depth and integrating adversarial and perceptual loss, was thoroughly evaluated on various benchmark datasets. The experimental results showed remarkable outcomes. On the Set5 dataset, our method achieved a PSNR of 34.18 dB and a SSIM of 0.956. Comparatively, on the Set14 dataset, it yielded a PSNR of 31.16 dB and an SSIM of 0.920, and on the B100 dataset, it achieved a PSNR of 30.51 dB and an SSIM of 0.912. These results were superior or comparable to those of existing advanced algorithms, demonstrating the proposed method’s potential in generating high-quality, high-resolution images. Our research underscores the potency of GANs in image super-resolution, making it a promising tool for applications spanning medical diagnostics, security systems, and remote sensing. Future exploration could extend to the utilization of alternative loss functions and novel training techniques, aiming to further refine the efficacy of GAN-based image restoration algorithms.

Critical complex network structures in animal gastrointestinal tract microbiomes

BackgroundLiving things from microbes to their hosts (plants, animals and humans) interact with each other, and their relationships may be described with complex network models. The present study focuses on the critical network structures, specifically the core/periphery nodes and backbones (paths of high-salience skeletons) in animal gastrointestinal microbiomes (AGMs) networks. The core/periphery network (CPN) mirrors nearly ubiquitous nestedness in ecological communities, particularly dividing the network as densely interconnected core-species and periphery-species that only sparsely linked to the core. Complementarily, the high-salience skeleton network (HSN) mirrors the pervasive asymmetrical species interactions (strictly microbial species correlations), particularly forming heterogenous pathways in AGM networks with both “backbones” and “rural roads” (regular or weak links). While the cores and backbones can act as critical functional structures, the periphery nodes and weak links may stabilize network functionalities through redundancy.ResultsHere, we build and analyze 36 pairs of CPN/HSN for the AGMs based on 4903 gastrointestinal-microbiome samples containing 473,359 microbial species collected from 318 animal species covering all vertebrate and four major invertebrate classes. The network analyses were performed at host species, order, class, phylum, kingdom scales and diet types with selected and comparative taxon pairs. Besides diet types, the influence of host phylogeny, measured with phylogenetic (evolutionary) timeline or “age”, were integrated into the analyses. For example, it was found that the evolutionary trends of three primary microbial phyla (Bacteroidetes/Firmicutes/Proteobacteria) and their pairwise abundance-ratios in animals do not mirror the patterns in modern humans phylogenetically, although they are consistent in terms of diet types.ConclusionsOverall, the critical network structures of AGMs are qualitatively and structurally similar to those of the human gut microbiomes. Nevertheless, it appears that the critical composition (the three phyla of Bacteroidetes, Firmicutes, and Proteobacteria) in human gut microbiomes has broken the evolutionary trend from animals to humans, possibly attributable to the Anthropocene epoch and reflecting the far-reaching influences of agriculture and industrial revolution on the human gut microbiomes. The influences may have led to the deviations between modern humans and our hunter-gather ancestors and animals.

Bidirectional Service Function Chain Embedding for Interactive Applications in Mobile Edge networks

Bidirectional service function chain (BSFC) consists of multiple virtual network functions (VNFs). Through VNF deployment and link mapping, BSFCs can be embedded into resource-constrained mobile edge networks to provide low-latency network function services to users participating in interactive applications such as multi-player online games. Data from these users are routed through BSFCs to the edge node where the application is located for interaction and then returned to the users through the BSFCs, thus enabling synchronization among multiple users. However, the edge nodes or links have limited computing or bandwidth resources to serve only a fraction of users simultaneously. Therefore, the embedding decisions among different users can affect each other. In this paper, we propose a novel BSFC embedding strategy for interactive applications with the goal of minimizing computing and bandwidth resources while satisfying users' latency requirements. We first model the BSFC embedding problem as an integer nonlinear programming problem. Then, by closely examining the complexity of the problem, we propose a distributed algorithm based on game theory. We theoretically analyze the properties of the proposed algorithm and show that it can obtain a solution with a worst-case performance bound. Finally, extensive experiments show that the proposed algorithm outperforms several existing algorithms.

Availability Aware Online Virtual Network Function Backup in Edge Environments

With the rapid advancement of edge computing and network function virtualization, it is promising to provide flexible and low-latency network services at the edge. However, due to the vulnerability of edge services and the volatility of edge computing system states, i.e., service request rates, failure rates, and resource prices, it is challenging to minimize the online service cost while providing the availability guarantee. This paper considers the problem of online virtual network function backup under availability constraints (OVBAC) for cost minimization in edge environments. We formulate the problem based on the characteristics of the volatility system states derived from real-world data and show the hardness of the formulated problem. We use an online backup deployment scheme named Drift-Plus-Penalty (DPP) with provable near-optimal performance for the AVBAC problem. In particular, DPP needs to solve an integer programming problem at the beginning of each time slot. We propose a dynamic programming-based algorithm that can optimally solve the problem in pseudo-polynomial time. Extensive real-world data-driven simulations demonstrate that DPP significantly outperforms popular baselines used in practice.

Reinforcement learning based blockchain model for revoking unauthorized access in Virtualized Network Functions‐based Internet of Things Mobile Edge Computing

AbstractVNFs boost data processing efficiency in Mobile Edge Computing (MEC)‐driven Internet of Things (IoT) for healthcare, smart cities, and industrial automation. VNF‐based IoT MEC systems encounter a significant security threat due to unauthorized access, posing risks to data privacy and system integrity. Existing approaches struggle to adapt to dynamic environments and lack tamper‐proof enforcement mechanisms. In this work, we propose a novel system combining Reinforcement Learning (RL) and blockchain technology to revoke unauthorized access in VNF‐based IoT MEC. We introduce the Integrated Action‐selection DRL Algorithm for Unauthorized Access Revocation (IASDRL‐UAR), a novel RL approach that excels in dynamic environments by handling both continuous and discrete actions, enabling real‐time optimization of security risk, execution time, and energy consumption. A behavior control contract (BCC) is proposed and integrated into the RL system, automating behavior checks and enforcement, streamlining security management, and reducing manual intervention. RL feedback plays a pivotal role in steering dynamic security adjustments, gaining valuable perspectives from user behavior via trust scores in the behavior contract. The security features of the proposed method are analyzed. Performance comparisons reveal a substantial improvement, with the proposed system outperforming existing methods by 30% in terms of throughput, 21.7% in system stability, and 26% in access revocation latency. Additionally, the system demonstrates a higher security index, energy efficiency, and scalability.

Joint Network Function Placement and Routing Optimization in Dynamic Software-Defined Satellite-Terrestrial Integrated Networks

Joint Network Function Placement and Routing Optimization in Dynamic Software-Defined Satellite-Terrestrial Integrated Networks

Energy-Aware Adaptive Scaling of Server Farms for NFV With Reliability Requirements

Auto-scaling techniques aim to keep the right number of active servers for the current load: if this number is too small we risk service disruption, but if it is too large we waste resources. Despite the interest in the efficient operation of this type of systems, no prior work has addressed auto-scaling techniques for Network Function Virtualization (NFV) with stringent reliability requirements such as those envisioned in 5G (5 or 6 nines). To achieve such levels of reliability, we need to account for both the activation delay until servers become available (i.e., the wake-up or activation time) and the fallible nature of servers (which may fail with some probability). In this paper, we build on control theory to design an auto-scaling technique for a server farm for NFV that guarantees certain reliability while minimizing the number of active resources. We show that the use of well-established tools from control theory results in convergence times much shorter than those obtained with state-of-the-art reinforcement learning techniques. This shows that, despite the current trend to apply machine learning to all sorts of networking problems, there may be some cases where other techniques (such as control theory) can be more suitable.

Aberrant cortical activity, functional connectivity, and neural assembly architecture after photothrombotic stroke in mice.

Despite substantial progress in mapping the trajectory of network plasticity resulting from focal ischemic stroke, the extent and nature of changes in neuronal excitability and activity within the peri-infarct cortex of mice remains poorly defined. Most of the available data have been acquired from anesthetized animals, acute tissue slices, or infer changes in excitability from immunoassays on extracted tissue, and thus may not reflect cortical activity dynamics in the intact cortex of an awake animal. Here, in vivo two-photon calcium imaging in awake, behaving mice was used to longitudinally track cortical activity, network functional connectivity, and neural assembly architecture for 2 months following photothrombotic stroke targeting the forelimb somatosensory cortex. Sensorimotor recovery was tracked over the weeks following stroke, allowing us to relate network changes to behavior. Our data revealed spatially restricted but long-lasting alterations in somatosensory neural network function and connectivity. Specifically, we demonstrate significant and long-lasting disruptions in neural assembly architecture concurrent with a deficit in functional connectivity between individual neurons. Reductions in neuronal spiking in peri-infarct cortex were transient but predictive of impairment in skilled locomotion measured in the tapered beam task. Notably, altered neural networks were highly localized, with assembly architecture and neural connectivity relatively unaltered a short distance from the peri-infarct cortex, even in regions within 'remapped' forelimb functional representations identified using mesoscale imaging with anaesthetized preparations 8 weeks after stroke. Thus, using longitudinal two-photon microscopy in awake animals, these data show a complex spatiotemporal relationship between peri-infarct neuronal network function and behavioral recovery. Moreover, the data highlight an apparent disconnect between dramatic functional remapping identified using strong sensory stimulation in anaesthetized mice compared to more subtle and spatially restricted changes in individual neuron and local network function in awake mice during stroke recovery.

Aberrant cortical activity, functional connectivity, and neural assembly architecture after photothrombotic stroke in mice

Despite substantial progress in mapping the trajectory of network plasticity resulting from focal ischemic stroke, the extent and nature of changes in neuronal excitability and activity within the peri-infarct cortex of mice remains poorly defined. Most of the available data have been acquired from anesthetized animals, acute tissue slices, or infer changes in excitability from immunoassays on extracted tissue, and thus may not reflect cortical activity dynamics in the intact cortex of an awake animal. Here, in vivo two-photon calcium imaging in awake, behaving mice was used to longitudinally track cortical activity, network functional connectivity, and neural assembly architecture for 2 months following photothrombotic stroke targeting the forelimb somatosensory cortex. Sensorimotor recovery was tracked over the weeks following stroke, allowing us to relate network changes to behavior. Our data revealed spatially restricted but long-lasting alterations in somatosensory neural network function and connectivity. Specifically, we demonstrate significant and long-lasting disruptions in neural assembly architecture concurrent with a deficit in functional connectivity between individual neurons. Reductions in neuronal spiking in peri-infarct cortex were transient but predictive of impairment in skilled locomotion measured in the tapered beam task. Notably, altered neural networks were highly localized, with assembly architecture and neural connectivity relatively unaltered a short distance from the peri-infarct cortex, even in regions within ‘remapped’ forelimb functional representations identified using mesoscale imaging with anaesthetized preparations 8 weeks after stroke. Thus, using longitudinal two-photon microscopy in awake animals, these data show a complex spatiotemporal relationship between peri-infarct neuronal network function and behavioral recovery. Moreover, the data highlight an apparent disconnect between dramatic functional remapping identified using strong sensory stimulation in anaesthetized mice compared to more subtle and spatially restricted changes in individual neuron and local network function in awake mice during stroke recovery.

Construction of ecological network in Qujing city based on MSPA and MCR models.

With the rapid advancement of urbanization and industrialization, ecological patches within cities and towns are fragmented and ecological corridors are cut off, regional ecological security is threatened and sustainable development is hindered. Building an ecological network that conforms to regional realities can connect fragmented patches, protect biodiversity and regional characteristics, and provide scientific reference for regional ecological protection and ecological network planning. By taking Qilin District, the main urban area of Qujing City as an example, and using geospatial data as the main data source, based on morphological spatial pattern analysis (MSPA) and minimum cumulative resistance (MCR), this study identified ecological source areas, extracted ecological corridors, and build & optimize ecological networks. (1) All landscape types are identified based on MSPA, the proportion of core area was the highest among all landscape types, which was 80.69%, combined with the connectivity evaluation, 14 important ecological source areas were selected. (2) 91 potential ecological corridors were extracted through MCR and gravity models, there were 16 important ones. (3) The network connectivity analysis method is used to calculate the α, β, and γ indexes of the ecological network before optimization, which were 2.36, 6.5, and 2.53, while after optimization, α, β and γ indices were 3.8, 9.5 and 3.5, respectively. The combined application of MSPA-MCR model and ecological network connectivity analysis evaluation is conducive to improving the structure and functionality of ecological network.

Characteristics of urban network and city functions in the Yangtze River Delta Region: A multi-scale perspective

The development of cities and regions emerges from the complex associations at various spatial levels, highlighting the importance of a multi-scale approach to analyzing regional urban networks. This study attempts to establish a new analysis framework encompassing national, regional, and local dimensions by employing a population flow network in the Yangtze River Delta in China. It explores the inter-city connections and spatial structures of regional urban networks as well as the correlations and differentiations of urban functions under multi-scale interaction. The results indicate that: (1) Regional network demonstrates notable multi-scale interactions with an explicit hierarchical structure; (2) The roles and positions of different cities vary significantly across scales due to economic, administrative, locational, and transportation differences; (3) Different city types can drive their evolution by navigating through rescaling in a diverse multi-scale environment; (4) A positive correlation is observed when comparing the functional behaviors of cities across various scales. This study provides insights for cities to identify their strategic roles and adapt development strategies within the wider network framework, offering theoretical and practical contributions to multi-scale urban networks analysis.

Investigating Sea-Level Brain Predictors for Acute Mountain Sickness: A Multimodal MRI Study before and after High-Altitude Exposure.

Acute mountain sickness is a series of brain-centered symptoms that occur when rapidly ascending to high altitude. Predicting acute mountain sickness before high-altitude exposure is crucial for protecting susceptible individuals. The present study aimed to evaluate the feasibility of predicting acute mountain sickness after high-altitude exposure by using multimodal brain MR imaging features measured at sea level. We recruited 45 healthy sea-level residents who flew to the Qinghai-Tibet Plateau (3650 m). We conducted T1-weighted structural MR imaging, resting-state fMRI, and arterial spin-labeling perfusion MR imaging both at sea level and high altitude. Acute mountain sickness was diagnosed for 5 days using Lake Louise Scoring. Logistic regression with Least Absolute Shrinkage and Selection Operator logistic regression was performed for predicting acute mountain sickness using sea-level MR imaging features. We also validated the predictors by using MR images obtained at high altitude. The incidence rate of acute mountain sickness was 80.0%. The model achieved an area under the receiver operating characteristic curve of 86.4% (sensitivity = 77.8%, specificity = 100.0%, and P < .001) in predicting acute mountain sickness At sea level, valid predictors included fractional amplitude of low-frequency fluctuations (fALFF) and degree centrality from resting-state fMRI, mainly distributed in the somatomotor network. We further learned that the acute mountain sickness group had lower levels of fALFF in the somatomotor network at high altitude, associated with smaller changes in CSF volume and higher Lake Louise Scoring, specifically relating to fatigue and clinical function. Our study found that the somatomotor network function detected by sea-level resting-state fMRI was a crucial predictor for acute mountain sickness and further validated its pathophysiologic impact at high altitude. These findings show promise for pre-exposure prediction, particularly for individuals in need of rapid ascent, and they offer insight into the potential mechanism of acute mountain sickness.

Comprehensive fault diagnosis for multiple coupled SFCs based on deep learning

Service Function Chains (SFCs) are deployed and executed in a complex network environment, where multiple SFCs are coupled by sharing various types of network functions and transmission links. As a result, diagnosing the state of these SFCs and accurately locating network fault becomes a challenge and plays a fundamental role in SFC management. In this paper, we introduce a comprehensive fault diagnosis mechanism for multiple coupled SFCs by applying the deep learning technique. By formulating the involved network nodes and transmission links into a heterogeneous graph model, we propose the Rendered Service Path Heterogeneous Graph Attention Network (RSP-HAN) model to comprehensively estimate the state of every network node and link. Typically, RSP-HAN first applies Bi-directional Long Short-Term Memory (Bi-LSTM) to normalize features from different types of network entities, then obtains the embedding results through intra-RSP and inter-RSP attention mechanisms. Finally, Multi-Layer Perceptron (MLP) is utilized to estimate the state of these network entities. We also setup an experiment platform and obtain extensive datasets to evaluate our RSP-HAN model. Experimental results show that RSP-HAN performs better in fault diagnosis for various types of network entities than several traditional methods and two deep learning-based baselines, the Graph Convolutional Network (GCN) and the Graph Attention Network (GAT).

Non-symmetric over-time pooling using pseudo-grouping functions for convolutional neural networks

Convolutional Neural Networks (CNNs) are a family of networks that have become state-of-the-art in several fields of artificial intelligence due to their ability to extract spatial features. In the context of natural language processing, they can be used to build text classification models based on textual features between words. These networks fuse local features to generate global features in their over-time pooling layers. These layers have been traditionally built using the maximum function or other symmetric functions such as the arithmetic mean. It is important to note that the order of input local features is significant (i.e. the symmetry is not an inherent characteristic of the model). While this characteristic is appropriate for image-oriented CNNs, where symmetry might make the network robust to image rigid transformations, it seems counter-productive for text processing, where the order of the words is certainly important. Our proposal is, hence, to use non-symmetric pooling operators to replace the maximum or average functions. Specifically, we propose to perform over-time pooling using pseudo-grouping functions, a family of non-symmetric aggregation operators that generalize the maximum function. We present a construction method for pseudo-grouping functions and apply different examples of this family to over-time pooling layers in text-oriented CNNs. Our proposal is tested on seven different models and six different datasets in the context of engineering applications, e.g. text classification. The results show an overall improvement of the models when using non-symmetric pseudo-grouping functions over the traditional pooling function.