Computational Network Research Articles

Memristors with Tunable Volatility for Reconfigurable Neuromorphic Computing.

Neuromorphic computing promises an energy-efficient alternative to traditional digital processors in handling data-heavy tasks, primarily driven by the development of both volatile (neuronal) and nonvolatile (synaptic) resistive switches or memristors. However, despite their energy efficiency, memristor-based technologies presently lack functional tunability, thus limiting their competitiveness with arbitrarily programmable (general purpose) digital computers. This work introduces a two-terminal bilayer memristor, which can be tuned among neuronal, synaptic, and hybrid behaviors. The varying behaviors are accessed via facile control over the filament formed within the memristor, enabled by the interplay between the two active ionic species (oxygen vacancies and metal cations). This solution is unlike single-species ion migration employed in most other memristors, which makes their behavior difficult to control. By reconfiguring a single crossbar array of hybrid memristors, two different applications that usually require distinct types of devices are demonstrated - reprogrammable heterogeneous reservoir computing and arbitrary non-Euclidean graph networks. Thus, this work outlines a potential path toward functionally reconfigurable postdigital computers.

Adaptive Scheduling of High-Availability Drone Swarms for Congestion Alleviation in Connected Automated Vehicles

The Intelligent Transportation System (ITS) serves as a pivotal element within urban networks, offering decision support to users and connected automated vehicles (CAVs) through comprehensive information gathering, sensing, device control, and data processing. Presently, ITS predominantly relies on sensors embedded in fixed infrastructure, notably Roadside Units (RSUs). However, RSUs are confined by coverage limitations and may encounter challenges in prompt emergency responses. On-demand resources, such as drones, present a viable option to supplement these deficiencies effectively. This paper introduces an approach where Software-Defined Networking (SDN) and Mobile Edge Computing (MEC) technologies are integrated to formulate a high-availability drone swarm control and communication infrastructure framework, comprising the cloud layer, edge layer, and device layer. Drones confront limitations in flight duration attributed to battery limitations, posing a challenge in sustaining continuous monitoring of road conditions over extended periods. Effective drone scheduling stands as a promising solution to overcome these constraints. To tackle this issue, we initially utilized Graph WaveNet, a specialized graph neural network structure tailored for spatial-temporal graph modeling, for training a congestion prediction model using real-world dataset inputs. Building upon this, we further propose an algorithm for drone scheduling based on congestion prediction. Our simulation experiments using real-world data demonstrate that, compared to the baseline method, the proposed scheduling algorithm not only yielded superior scheduling gains but also mitigated drone idle rates.

Development and Research of Chinese-English Slang Translation Retrieval System under Internet Environment

Slang plays an important role in cross-cultural communication. It is frequently used in spoken language and constantly updated. Under the drive of new needs, intelligent integrated retrieval system came into being. Based on information platforms such as the Internet, big data network and cloud computing, intelligent retrieval technology classifies and integrates English slang and develops an "English slang translation retrieval system", which greatly reduces the search cost of users and provides convenience for English learners and cross-cultural communicators.

Cooperative Service Caching in Vehicular Edge Computing Networks Based on Transportation Correlation Analysis

Cooperative Service Caching in Vehicular Edge Computing Networks Based on Transportation Correlation Analysis

Marine Diesel Engine Fault Detection Based on Xilinx ZYNQ SoC

Marine diesel engines are the preferred power equipment for ships and are the most important component among the numerous electromechanical devices on board. Accidents involving these engines can potentially cause immeasurable damage to the vessel, making fault detection in marine diesel engines crucial. This design enables the detection and reporting of faults in marine diesel engines at the earliest possible time through the computation of convolutional neural networks, which is of great significance for ensuring the safe navigation of ships. For this functionality, the Xilinx ZYNQ-7000 XC7Z010 is selected as the main control chip, and the LoRa wireless network is used as the transmission module. The FreeRTOS embedded operating system is ported, with sensor data collection completed on the PS side of the ZYNQ chip and algorithm acceleration calculations on the PL side. Data are then transmitted to the host computer via the LoRa module paired with a custom protocol. Experimental test results show that the program provides stable data transmission, with each module of the algorithm generally accelerating by more than 95% and an accuracy rate of 92.86%. Additionally, the host computer can display the received data in real time. The custom protocol’s header also allows for precise judgments about the completeness and origin of messages, facilitating the expansion of other SOC’s message uplink and the host computer’s message downlink.

Quantum-empowered federated learning and 6G wireless networks for IoT security: Concept, challenges and future directions

The Internet of Things (IoT) has revolutionized various sectors by enabling seamless device interaction. However, the proliferation of IoT devices has also raised significant security and privacy concerns. Traditional security measures often fail to address these concerns due to the unique characteristics of IoT networks, such as heterogeneity, scalability, and resource constraints. This survey paper adopts a thematic exploration approach for a comprehensive analysis to investigate the convergence of quantum computing, federated learning, and 6G wireless networks. This novel intersection is explored to significantly improve security and privacy within the IoT ecosystem. Quantum computing can enhance encryption algorithms to make IoT data more secure for intelligent IoT applications. Federated learning, a decentralized machine learning approach, allows IoT devices to learn a shared model while keeping all the training data on the original device, thereby enhancing privacy. This synergy becomes even more crucial when integrated with the high-speed, low-latency capabilities of 6G networks, which can facilitate real-time, secure data processing and communication among many IoT devices. Second, we discuss the latest developments, offering an up-to-date overview of advanced solutions, available datasets, and key performance metrics and summarizing the vital insights, challenges, and trends in securing IoT systems. Third, we design a conceptual framework for integrating quantum computing in federated learning, adapted for 6G networks. Finally, we highlight the future advancements in quantum technologies and 6G networks and summarize the implications for IoT security, paving the way for researchers and practitioners in the field of IoT security.

Parallel photonic chip for nanosecond end-to-end image processing, transmission, and reconstruction

Image processing, transmission, and reconstruction constitute a major proportion of information technology. The rapid expansion of ubiquitous edge devices and data centers has led to substantial demands on the bandwidth and efficiency of image processing, transmission, and reconstruction. The frequent conversion of serial signals between the optical and electrical domains, coupled with the gradual saturation of electronic processors, has become the bottleneck of end-to-end machine vision. Here, we present an optical parallel computational array chip (OPCA chip) for end-to-end processing, transmission, and reconstruction of optical intensity images. By proposing constructive and destructive computing modes on the large-bandwidth resonant optical channels, a parallel computational model is constructed to implement end-to-end optical neural network computing. The OPCA chip features a measured response time of 6 ns and an optical bandwidth of at least 160 nm. Optical image processing can be efficiently executed with minimal energy consumption and latency, liberated from the need for frequent optical–electronic and analog–digital conversions. The proposed optical computational sensor opens the door to extremely high-speed processing, transmission, and reconstruction of visible contents with nanoseconds response time and terahertz bandwidth.

Learning to Read Connections—Sensitivity to Collocation Frequency Links Vocabulary Size and Reading Comprehension in Middle Childhood

AbstractThe collocation frequency of words in the language environment contributes to early vocabulary development. Vocabulary size, in turn, predicts children's reading comprehension skills later in development. Both collocation frequency and reading comprehension have been connected to inferential reasoning at different time points in development. Here, it was hypothesized that 8‐year‐old children's (N = 147; 76 female) sensitivity to collocation frequency would be related to vocabulary size and reading comprehension skills of varying complexity. Participants completed an auditory thematic judgment task to assess their sensitivity to collocation frequency (response accuracy or speed). In the task, children were presented with a short sentence containing a reference word (e.g., “John sees the cloud.”) and asked to judge which of two subsequent words best fit the sentence (e.g., “rain” or “lip”). Semantic relatedness between reference words and test words was operationalized in three levels (strong, weak, and distant) based on a corpus‐based analysis of collocation frequency. Multilevel and mediation analyses confirmed that thematic judgment responses were related to corpus‐based measures of collocation frequency and were associated with vocabulary size and reading comprehension skills at the sentence and text level. Furthermore, thematic judgment predicted vocabulary size and reading comprehension when the relation of decoding and reading comprehension was taken into account. The study highlights sensitivity to collocation frequency as a link between early language comprehension development (i.e., lexical retrieval and inferential reasoning) and reading comprehension in middle childhood. It also integrates theoretical approaches from computational network or distributional semantics studies and behavioral experimental studies.

TLPGNN: A Lightweight Two-level Parallelism Paradigm for Graph Neural Network Computation on Single and Multiple GPUs

Graph Neural Networks (GNNs) are an emerging class of deep learning models specifically designed for graph-structured data. They have been effectively employed in a variety of real-world applications, including recommendation systems, drug development, and analysis of social networks. The GNN computation includes regular neural network operations and general graph convolution operations, which take most of the total computation time. Though several recent works have been proposed to accelerate the computation for GNNs, they face the limitations of heavy pre-processing, low efficiency atomic operations, and unnecessary kernel launches. In this article, we designTLPGNN, a lightweight two-level parallelism paradigm for GNN computation. First, we conduct a systematic analysis of the hardware resource usage of GNN workloads to understand the characteristics of GNN workloads deeply. With the insightful observations, we then divide the GNN computation into two levels, i.e.,vertex parallelismfor the first level andfeature parallelismfor the second. Next, we employ a novel hybrid dynamic workload assignment to address the imbalanced workload distribution. Furthermore, we fuse the kernels to reduce the number of kernel launches and cache the frequently accessed data into registers to avoid unnecessary memory traffic. To scaleTLPGNNto multi-GPU environments, we propose an edge-aware row-wise 1-D partition method to ensure a balanced workload distribution across different GPU devices. Experimental results on various benchmark datasets demonstrate the superiority of our approach, achieving substantial performance improvement over state-of-the-art GNN computation systems, including Deep Graph Library (DGL), GNNAdvisor, and FeatGraph, with speedups of 6.1×, 7.7×, and 3.0×, respectively, on average. Evaluations of multiple-GPUTLPGNNalso demonstrate that our solution achieves both linear scalability and a well-balanced workload distribution.

Machine Learning Based Intelligent Management System for Energy Storage Using Computing Application

INTRODUCTION: Cloud computing, a still emerging technology, allows customers to pay for services based on usage. It provides internet-based services, whilst virtualization optimizes a PC’s available resources. OBJECTIVES: The foundation of cloud computing is the data center, comprising networked computers, cables, electricity components, and various other elements that host and store corporate data. In cloud data centres, high performance has always been a critical concern, but this often comes at the cost of increased energy consumption. METHODS: The most problematic factor is reducing power consumption while maintaining service quality and performance to balance system efficiency and energy use. Our proposed approach requires a comprehensive understanding of energy usage patterns within the cloud environment. RESULTS: We examined power consumption trends to demonstrate that with the application of the right optimization principles based on energy consumption models, significant energy savings can be made in cloud data centers. During the prediction phase, tablet optimization, with its 97 % accuracy rate, enables more accurate future cost forecasts. CONCLUSION: Energy consumption is a major concern for cloud data centers. To handle incoming requests with the fewest resources possible, given the increasing demand and widespread adoption of cloud computing, it is essential to maintain effective and efficient data center strategies.

PHSI-RTDETR: A Lightweight Infrared Small Target Detection Algorithm Based on UAV Aerial Photography

To address the issues of low model accuracy caused by complex ground environments and uneven target scales and high computational complexity in unmanned aerial vehicle (UAV) aerial infrared image target detection, this study proposes a lightweight UAV aerial infrared small target detection algorithm called PHSI-RTDETR. Initially, an improved backbone feature extraction network is designed using the lightweight RPConv-Block module proposed in this paper, which effectively captures small target features, significantly reducing the model complexity and computational burden while improving accuracy. Subsequently, the HiLo attention mechanism is combined with an intra-scale feature interaction module to form an AIFI-HiLo module, which is integrated into a hybrid encoder to enhance the focus of the model on dense targets, reducing the rates of missed and false detections. Moreover, the slimneck-SSFF architecture is introduced as the cross-scale feature fusion architecture of the model, utilizing GSConv and VoVGSCSP modules to enhance adaptability to infrared targets of various scales, producing more semantic information while reducing network computations. Finally, the original GIoU loss is replaced with the Inner-GIoU loss, which uses a scaling factor to control auxiliary bounding boxes to speed up convergence and improve detection accuracy for small targets. The experimental results show that, compared to RT-DETR, PHSI-RTDETR reduces model parameters by 30.55% and floating-point operations by 17.10%. Moreover, detection precision and speed are increased by 3.81% and 13.39%, respectively, and mAP50, impressively, reaches 82.58%, demonstrating the great potential of this model for drone infrared small target detection.

Deep neural network model for predicting thermal-hydraulic performance of a solar air heater with artificial roughness: Sensitivity, generalization capacity, and computational efficiency

A novel coupled computational fluid dynamics-deep neural network approach is proposed to accurately predict the performance of an artificially roughened solar air heater. Computational fluid dynamics data sets are used to develop an optimized neural network model for the prediction of thermal-hydraulic performance factor. The optimized neural network model with softmax transfer function in hidden layers has an architecture of 3‐37‐37‐1 and it predicts the thermal-hydraulic performance factor of the artificially roughened solar air heater with maximum, mean, and minimum error of 2.54 %, 0.245 %, and 0.0009 %, respectively. The concept of Shapley values is adopted to evaluate the global sensitivity analysis of the optimized deep neural network model and it is found that rib height is the most influential design parameter for the artificially roughened solar air heater. The generalization capacity of the neural network model is evaluated by comparing its predictions with experimental data, demonstrating superior predictive performance over traditional computational fluid dynamics simulations. The optimized artificial neural network model achieves a computational time gain of approximately 100 % against computational fluid dynamics.

Split Learning with Differential Privacy for Integrated Terrestrial and Non-Terrestrial Networks

Integrated terrestrial and non-terrestrial networks (TNTNs) have become promising architecture for enabling ubiquitous connectivity. Smart remote sensing is one of the typical applications of TNTNs that collects and analyzes various dimensions of remote sensing data by deploying Internet of Things (IoT) sensors and edge computing in terrestrial, space, aerial, and underwater networks. To improve the analysis accuracy of remote sensing data, the owners of different networks should conduct collaborative learning on different dimensions of data, while data and label privacy should be jointly considered. However, the existing collaborative learning paradigms are difficult to meet this demand. In this article, we propose a paradigm of split learning (SL), where the data owner and the label owner train different parts of the deep learning model and only exchange the intermediate data (i.e., smashed data and cut layer gradients). We explore the potential privacy attacks that recover the raw data and label information based on the intermediate data and propose the differential privacy (DP) based defense mechanisms that inject randomly generated Laplace noise into the intermediate data to disturb the attack performance. We also conduct a simulation study based on a real-world satellite remote sensing dataset to validate that the SL paradigm with defense mechanisms can effectively balance the performance of the collaborative model training and the protection of the data and label privacy. Finally, we discuss the main challenges and potential research directions of the privacy-preserving SL paradigm for smart remote sensing over TNTNs.

Toward efficient resource utilization at edge nodes in federated learning

Federated learning (FL) enables edge nodes to collaboratively contribute to constructing a global model without sharing their data. This is accomplished by devices computing local, private model updates that are then aggregated by a server. However, computational resource constraints and network communication can become a severe bottleneck for larger model sizes typical for deep learning (DL) applications. Edge nodes tend to have limited hardware resources (RAM, CPU), and the network bandwidth and reliability at the edge is a concern for scaling federated fleet applications. In this paper, we propose and evaluate a FL strategy inspired by transfer learning in order to reduce resource utilization on devices, as well as the load on the server and network in each global training round. For each local model update, we randomly select layers to train, freezing the remaining part of the model. In doing so, we can reduce both server load and communication costs per round by excluding all untrained layer weights from being transferred to the server. The goal of this study is to empirically explore the potential trade-off between resource utilization on devices and global model convergence under the proposed strategy. We implement the approach using the FL framework FEDn. A number of experiments were carried out over different datasets (CIFAR-10, CASA, and IMDB), performing different tasks using different DL model architectures. Our results show that training the model partially can accelerate the training process, efficiently utilizes resources on-device, and reduce the data transmission by around 75% and 53% when we train 25%, and 50% of the model layers, respectively, without harming the resulting global model accuracy. Furthermore, our results demonstrate a negative correlation between the number of participating clients in the training process and the number of layers that need to be trained on each client’s side. As the number of clients increases, there is a decrease in the required number of layers. This observation highlights the potential of the approach, particularly in cross-device use cases.

Towards an Automated Transformation of an nD Urban Data Model to a Computational Ontology Network: From UML to OWL, From CityGML 3.0 to “CityOWL”

Towards an Automated Transformation of an nD Urban Data Model to a Computational Ontology Network: From UML to OWL, From CityGML 3.0 to “CityOWL”

A Review of Fog Computing Concept, Architecture, Application, Parameters and Challenges

The Internet of Things (IoT) has become an integral part of our daily lives, growing exponentially from a facility to a necessity. IoT has been utilized extensively through cloud computing and has proven an excellent technology for deploying in various fields. The data generated by the IoT devices gets transmitted to the cloud for processing and storage. However, with this approach, there are specific issues like latency, energy, computation resources availability, bandwidth, heterogeneity, storage, and network failure. To overcome these obstacles, fog computing is utilized as a middle tier. Fog computing gathers and processes the generated data closer to the user end before transmitting it to the cloud. This paper aims to conduct a structured review of the current state of fog computing and its architectures deployed across multiple industries. This paper also focuses on the implementation and critical parameters for introducing fog computing in IoT-cloud architecture. A detailed comparative analysis has been carried out for 5 different architectures considering various crucial parameters to identify how the quality of service and quality of experience for end users can be optimized. Finally, this paper looks at the multiple challenges that fog computing faces in a structured six-level approach. These challenges will also lead the way for future research in resource management, green computing, and security.

An event-based distributed least square linear equation solver employing network flow

In this article, we study a distributed, second-order, event-triggered network flow for solving linear algebraic equations described by the form z=Hy in the sense of least squares. An undirected graph is utilized to describe the distributed computation network. In the network, each node broadcasts its dynamic states to its neighbors in an asynchronous fashion, and updates the flow at the isolated event times. We construct a specific trigger function to determine the event times, in which an exponential decay function is introduced as a comparison term. We show that if the linear algebraic equation has a unique least squares solution, all nodes states converge to this unique solution exponentially fast, when the applied network is connected and the decay rate of the comparison term satisfies certain bounds determined jointly by the topology and the linear equations information. We obtain a strictly positive lower bound on the time interval between consecutive events for time t∈[0,∞), and therefore the event-triggered system does not exhibit Zeno behavior. We provide numerical examples to verify the effectiveness of the proposed event-based network flow. In addition, we illustrate the importance of the strictly positive inter-event time interval, in comparison with the case that the inter-event time interval may converge to zero when time t goes to infinity.

A simplified GNSS/LEO joint orbit determination method

Joint orbit determination (JOD) of Global Navigation Satellite Systems (GNSS) satellites and low Earth orbit (LEO) satellites has been substantiated as an efficacious approach to compensate for the ground station geometry. In the traditional JOD, the precise orbit determination (POD) of LEO satellite is mainly processed by the reduced-dynamic approach, however, this approach involves complex calculations and the credibility of the determined positions diminishes when LEO satellites undergo orbital maneuvers. Therefore, a simplified JOD method is designed that employs kinematic approach to determine the LEO satellites orbit. To verify the effectiveness of the proposed method, the orbit of GPS satellites and LEO satellites are jointly estimated utilizing the regional and global networks. 8 LEO satellites, including GRACE-C/D, SWARM-A/B/C, SENTINEL-3A/B, and JASON-3, are chosen for JOD. The comparative analysis between the proposed method and traditional method are achieved in terms of GPS orbit accuracy, LEO orbit accuracy, computation time and the JOD performance during LEO maneuvers. Under regional station scenario, the GPS orbit accuracy determined using the proposed method and the traditional method is 3.64 cm and 2.52 cm, respectively. In the case of global station scenario, the accuracies are 1.71 cm and 1.64 cm. Additionally, the traditional method yields superior enhancement and higher accuracy of the LEO orbits. However, it exhibits a noticeable increase in computation time compared to the proposed method and the performance of JOD declines significantly when LEO satellites undergo orbital maneuvers. Alternatively, although the accuracy of the LEO orbits using the proposed method is comparatively lower, it offers a substantial reduction in the overall network computation time compared to traditional method. Moreover, the proposed method based on LEO kinematic precise orbit determination (KPOD) is nearly unaffected by orbital maneuvers of LEO satellites, presenting unique advantages in practical data processing.

An integrated investigation combining network pharmacology and computer simulation dissects the potential mechanism of anti-obesity of Monascus pigments (MPs)

Monascus pigments (MPs), the secondary metabolites of Monascus-fermented foods, have been widely studied for their anti-obesity effects. However, the specific targets and potential mechanism of MPs for anti-obesity remain unclear. In this study, we applied network pharmacology and computer simulation to investigate the anti-obesity potential and action mechanism of MPs. Based on public databases, 117 potential therapeutic obesity targets of MPs were predicted. Five key targets (STAT3, ESR1, BCL2, PPARG, and MMP9) were obtained by protein-protein interaction (PPI) analysis and microarray data validation. The enrichment results showed that MPs exerted anti-obesity effects through multiple targets and multiple pathways, especially insulin resistance. Molecular docking demonstrated the binding of five key targets to MPs ligands through hydrophobic interactions and hydrogen bonding. Molecular dynamics simulation and binding free energy analysis revealed a higher stability in the binding of ESR1, BCL2, and PPARG targets with MPs ligands. In addition, free energy landscape (FEL) and independent gradient model (IGM) analysis showed that van der Waals forces were also the main driving force in stabilizing the binding of key targets and MPs ligands. This study systematically illustrated the potential anti-obesity mechanism of MPs and established the foundation for the development and application of MPs as anti-obesity functional additives.

Development of a Stress-Free Algorithm for Control of Running Platforms Based on Neural Network Technologies

The article discusses the task of predicting human speed using neural network technologies and computer vision to minimize lags in treadmill control systems, which pose a health risk to the user. To solve this problem, a stress-free algorithm has been developed, including: predicting the position and speed of the user on the treadmill; calculating the treadmill speed based on the analysis of the user's position and movement characteristics; data collection and processing schemes for training neural network methods; and determining the necessary number of predicted frames to eliminate lags. The scientific novelty of the research lies in the development of a treadmill control algorithm that combines: computer vision technologies for recognizing the user's body model on the platform; neural networks; and machine learning methods to determine the final human speed based on combining data on the person's position in the frame and the current and predicted speed of the person. The proposed algorithm is implemented using Python libraries, and its validation was conducted during experimental studies analyzing the preceding 10 and 15 frames to predict the next 10 and 15 frames. Comparing machine learning algorithms (linear regression, decision tree, random forest, multilayer, convolutional, and recurrent neural networks) at different lengths of analyzed and predicted frames, the RandomForestRegressor algorithm showed the best accuracy in predicting position, while dense multilayer neural networks performed best in determining current speed. Experimental research has been conducted on applying the developed algorithm and models to determine human speed (achieving accuracy when forecasting in the range of 10-15 frames) as well as integrating them into treadmill control systems. Trials have shown the effectiveness of the proposed approach and the correctness of system operation under real conditions. The developed algorithm allows for not using noise-sensitive sensors that require attachment to the user's body but rather forecasting user actions through analyzing all points of the person's body to reduce lags in various human-machine systems.