Network Applications Research Articles

ℓp-Sphere Covering and Approximating Nuclear p-Norm

The spectral p-norm and nuclear p-norm of matrices and tensors appear in various applications, albeit both are NP-hard to compute. The former sets a foundation of [Formula: see text]-sphere-constrained polynomial optimization problems, and the latter has been found in many rank minimization problems in machine learning. We study approximation algorithms of the tensor nuclear p-norm with an aim to establish the approximation bound matching the best one of its dual norm, the tensor spectral p-norm. Driven by the application of sphere covering to approximate both tensor spectral and nuclear norms ([Formula: see text]), we propose several types of hitting sets that approximately represent the [Formula: see text]-sphere with adjustable parameters for different levels of approximations and cardinalities, providing an independent toolbox for decision making on [Formula: see text]-spheres. Using the idea in robust optimization and second-order cone programming, we obtain the first polynomial-time algorithm with an [Formula: see text]-approximation bound for the computation of the matrix nuclear p-norm when [Formula: see text] is a rational, paving a way for applications in modeling with the matrix nuclear p-norm. These two new results enable us to propose various polynomial-time approximation algorithms for the computation of the tensor nuclear p-norm using tensor partitions, convex optimization, and duality theory, attaining the same approximation bound to the best one of the tensor spectral p-norms. Effective performance of the proposed algorithms for the tensor nuclear p-norm is shown by numerical implementations. We believe the ideas of [Formula: see text]-sphere covering with its applications in approximating nuclear p-norm would be useful for tackling optimization problems on other sets, such as the binary hypercube with its applications in graph theory and neural networks and the nonnegative sphere with its applications in copositive programming and nonnegative matrix factorization. Funding: This work was supported by the National Natural Science Foundation of China [Grants 71825003, 72394360, 72394364, 72171141, 72192830, and 72192832], and the program for Innovative Research Team of Shanghai University of Finance and Economics.

Acoustic Sensors data transmission integrity and endurance with IoT-enabled location-aware framework

Environmental monitoring and disaster mitigation are critical applications of underwater acoustic sensor networks (UASNs). However, UASNs face significant challenges, including high latency, limited bandwidth, and energy constraints. This study introduces an Internet of Things (IoT)-driven location-aware framework (ILAF) designed to enhance UASN performance by utilizing non-GPS geographic coordinates for determining the location of sensor and sink nodes, identifying their neighbors based on coordinates and transmission range, and optimizing node placement and routing without the need for GPS modems. The framework is compared with several state-of-the-art protocols, including Bald Eagle Search inspired optimized energy efficient routing protocol (BES-OEERP) and IoT-enabled depth-based routing technique (IDBR), demonstrating superior performance. Specifically, ILAF achieved a packet delivery ratio (PDR) of 99%, which outperforms energy-efficient region-based source distributed routing algorithm (EERSDRA) (98%) and energy-efficient geo-opportunistic routing protocols (EEGORP) (96%). Additionally, ILAF reduced energy consumption by 20% compared to these existing protocols. These improvements result in a more energy-efficient network with fewer dead nodes (12 after 1,000 rounds) and higher throughput (5.7 kbps at 1,000 rounds), making ILAF suitable for real-time underwater applications. Future research will explore integrating lightweight IoT protocols like Message Queue Telemetry Transport (MQTT) and Constrained Application Protocol (CoAP) to enhance the framework’s performance and reliability further.

Retraction notice: AI-federated novel delay-aware link-scheduling for industry 4.0 applications in IoT networks

Retraction notice: AI-federated novel delay-aware link-scheduling for industry 4.0 applications in IoT networks

Compact multiband cuff button antenna for WBAN application

Abstract A compact dual layer conformal wearable quad band antenna is proposed for wireless body area network applications. The proposed button like patch antenna resonates at 2.5 GHz (industrial, scientific, and medical bands)/3.6 GHz sub six 5G band/5.75 GHz (wireless local area network/ISM band)/ and 9.8 GHz (X band) frequencies. The circular textile antenna is constructed with jean and polydimethylsiloxane substrate having a slotted ground of radius 10 mm and thickness 1.5 mm. The simulated gains obtained at the operating bands are 1.85/2.03/1.49/3.27 dBi, respectively. The designed antenna’s directed radiation pattern assures reduced backward radiation to body tissue. The specific absorption rate (SAR) analysis for the antenna at multiple resonant frequencies has also been reported, which are well below the SAR threshold of 1.6 W/kg for 1 gm of tissue, indicating that the model works adequately for wearable applications. The experimental characterization on- and off-body of the fabricated antenna validates the simulated results.

Ultrathin, Wavelength‐Multiplexed and Integrated Holograms and Optical Neural Networks Based on 2D Perovskite Nanofilms

AbstractHolography, as a technique for coherent wavefront reconstruction, is extensively used in numerous optical applications such as optical imaging, 3D display, photolithography, and optical artificial intelligence. In order to achieve highly compact and functional integration with optoelectronic devices, the hologram needs to possess ultrathin thickness as well as multicolor functionality. However, its thickness is typically limited to optical wavelength ranges due to the requirement for pronounced amplitude or phase modulation, and it generally operates at a single wavelength band without wavelength‐multiplexed channels. Here, the hologram is decreased thickness to sub‐ten nanometers by exploiting the large refractive index and strong exciton absorption of 2D perovskites. Ultrathin perovskite holograms and holographic neural networks with high stability are successfully developed by using femtosecond laser direct writing, and their operation wavelength can be rationally tuned from 400–515 nm through halide anion engineering. Consequently, the wavelength can be multiplexed with low cross‐talks by stacked perovskite nanolayers for applications of holographic display and neural networks without the usages of complex optical structures or filters. This work provides a feasible and promising technical route for integrating ultrathin, high pixel density, and multiplexed holographic structures with flat optoelectronic devices for next‐generation integrated optical systems.

A Review of Research on Super-resolution Image Reconstruction Based on Deep Learning

Super-resolution image reconstruction (SRIR) endeavors to restore high-resolution (HR) images with enhanced detail from corresponding low-resolution (LR) inputs. With the rapid development of deep learning, integrating deep learning methods provides new solutions for the super-resolution (SR) field. This paper first reviews the background and significance of SR, development process, and the technical value of applying deep learning to SR. Next, SR methods based on deep learning are categorized according to different network types, with a focus on analyzing and comparing the applications of Convolutional Neural Networks (CNNs), Residual Networks (ResNet), Generative Adversarial Networks (GANs), and Diffusion Models in SR. The paper also introduces key evaluation metrics and problem-solving strategies, followed by a performance comparison of mainstream methods on publicly available datasets. Finally, a summary of SR algorithms based on deep learning is provided, along with an outlook on future development trends in the field and explore the possible next research directions in the field of image super-resolution.

Enhancing neural network applications in phonetic classification through population-based incremental learning

Significant progress has been achieved in the field of Automatic Speech Recognition (ASR) thanks to the development of powerful algorithms. Research based on simplified biological models has led to the emergence of a new class called Estimation of Distribution Algorithms (EDA), which preserves significant partial solutions. Population-Based Incremental Learning (PBIL) is a technique that combines stochastic search and optimization. It is a statistical approach with evolutionary computation similar to EDAs, aimed at adapting recognition systems based on artificial Neural Networks (NN). Our main contribution lies in the improvement achieved by PBIL, which outperforms Genetic Algorithms (GA) by 16% and Evolutionary Strategies (ES) by 9.93%.

Observation of Cartesian light propagation through a three-dimensional cavity superlattice in a silicon photonic band gap crystal

We experimentally investigate peculiar light propagation inside a three-dimensional (3D) superlattice of resonant cavities that are confined within a 3D photonic band gap. To this end, we fabricated 3D diamondlike photonic crystals from silicon with a broad 3D band gap in the near-infrared and doped them with a periodic array of point defects. In position-resolved reflectivity and scattering microscopy, we observe narrow spectral features that match well with superlattice bands in band structures computed with the plane-wave expansion. The cavities are coupled in all three dimensions when they are closely spaced (aSL≤3a), and uncoupled when they are further apart. The superlattice bands correspond to light that hops in high-symmetry directions in 3D (“Cartesian light”) that opens applications in 3D photonic networks, 3D Anderson localization of light, and future 3D quantum photonic networks. Published by the American Physical Society 2024

A Mobility Handover Decision Method Based on Multi-Topology

With the emergence of new applications in mobile networks, users demand higher network stability and lower data transmission delays. When the network address of a mobile user changes, the data transmission path in the wired network may need to be switched to maintain service continuity. Traditional mobility support methods typically rely on a single switching path for all mobile data flows. However, if this path cannot meet the requirements of all the flows, it may lead to network congestion or a decline in user experience. To overcome this limitation, this paper proposes a mobility handover decision method based on multi-topology. It enables the dynamic allocation of mobile data flows across different switching paths within multiple logical topologies. The method models a multi-topology selection problem aimed at minimizing average packet transmission delay and packet loss rate, while considering network conditions and the Quality of Service (QoS) requirements for each flow. By solving the dual problem of the original optimization, a near-optimal solution is achieved. The proposed scheme and algorithm were implemented and tested using the Mininet network simulator. Results show that the proposed approach achieves low average packet transmission delay, low average packet loss rate, and high throughput, compared to traditional single-path switching methods and existing multipath routing methods.

A TVD neural network closure and application to turbulent combustion

Trained neural networks (NN) have attractive features for closing governing equations. There are many methods that are showing promise, but all can fail in cases when small errors consequentially violate physical reality, such as a solution boundedness condition. A NN formulation is introduced to preclude spurious oscillations that violate solution boundedness or positivity. It is embedded in the discretized equations as a machine learning closure and strictly constrained, inspired by total variation diminishing (TVD) methods for hyperbolic conservation laws. The constraint is exactly enforced during gradient-descent training by rescaling the NN parameters, which maps them onto an explicit feasible set. Demonstrations show that the constrained NN closure model usefully recovers linear and nonlinear hyperbolic phenomena and anti-diffusion while enforcing the non-oscillatory property. Finally, the model is applied to subgrid-scale (SGS) modeling of a turbulent reacting flow, for which it suppresses spurious oscillations in scalar fields that otherwise violate the solution boundedness. It outperforms a simple penalization of oscillations in the loss function.

A Priority based Self-Organised MAC Protocol for Real Time Wireless Sensor Network Applications

Wireless Sensor Networks (WSNs) are expressively utilized in various real-time control and monitoring applications. WSNs have been expanded considering the necessities in industrial time-bounded applications to support the dependable and time-bound delivery of data. Recently, Machine Learning (ML) algorithms have been used to address various WSN-related issues. The use of ML techniques supports dynamically modifying MAC settings based on traffic patterns and network conditions. In WSNs to control the communication between a large numbers of tiny, low-power sensor nodes while preserving energy and reducing latency, effective MAC protocols are essential. This paper addresses the ML centered priority-based self-organized MAC (ML-MAC) protocol to provide a priority-based transmission system to ensure the timely delivery of critical data packets. In this research, depending upon the predictions of the ML model, the MAC parameters are dynamically adjusted to find priority-based channel access and the optimal routing path to meet the deadline of critical data packets. From the result analysis, the average throughput and delay of the proposed ML-MAC algorithm outperforms the existing I-MAC protocol.

A GCN-LSTM framework for link prediction in dynamic SIoT networks

The Social Internet of Things (SIoT) paradigm combines the Internet of Things (IoT) with social networking principles, enabling autonomous device interactions. However, the dynamic, heterogeneous, and temporal nature of SIoT networks presents significant challenges for link prediction. While existing models, such as SIoTPredict (Aljubairy et al., 2020), exploits social network analysis and machine learning, they primarily focus only on certain aspects of social relationships between devices, lacking consideration of temporal dynamics, environmental factors, and device heterogeneity. In contrast, we propose a novel framework that integrates Graph Convolutional Networks (GCNs) with Long Short-Term Memory (LSTM) networks and a Multi-Head Attention mechanism, further enhanced by a dynamic feature scheduling strategy, to accurately capture the spatial and temporal dependencies in SIoT environments. Additionally, our work introduces a MATLAB-based SIoT Simulator, providing a robust platform for generating realistic dynamic scenarios and evaluating complex Social Object Relationships. Unlike SIoTPredict, which is optimized for real-time applications but focuses narrowly on social aspects, our approach incorporates a broader range of factors, enabling better predictive accuracy in scenarios with high temporal variability. Extensive co-simulations with MATLAB and PyTorch demonstrate that our framework significantly outperforms existing methods in terms of predictive accuracy, adaptability, and robustness. By bridging critical gaps in current methodologies, this work establishes a comprehensive foundation for future research and practical applications in dynamic SIoT networks.

A comparative measurement study of cross-layer 5G performance under different mobility scenarios

The 5G technology is expected to revolutionize various applications with stringent latency and throughput requirements, such as augmented reality and cloud gaming. Despite the rapid 5G deployment, it is still a puzzle whether current commercial 5G networks can meet the strict requirements and deliver the expected quality of experience (QoE) of these applications. Especially in mobile scenarios, as user mobility (e.g., walking and driving) plays a critical role in both network performance and application QoE, it becomes more challenging to provide high performance stably and continuously. To solve this puzzle, in this paper, we present a comprehensive cross-layer measurement study of current commercial 5G networks under five mobility scenarios typically seen in our daily lives. Specifically, under these mobility scenarios, we cover (1) the impact of physical layer metrics on network performance, (2) general network performance at the network layer, (3) comparison of four congestion control algorithms at the transport layer, and (4) application QoE at the application layer. Our measurement results show that the achievable network performance and application QoE under current commercial 5G networks falls behind expectations. We further reveal some insights that could be leveraged to improve the QoE of these applications under mobility scenarios.

Artificial intelligence and the quality of accounting information in Palestinian industrial companies

Purpose This study aims to identify the impact of adopting different techniques of artificial intelligence including (expert systems, machine learning, neural networks and algorithms) in improving the quality of accounting information characteristics such as; appropriateness, faithful representation and verifiability in Palestinian industrial enterprises. Design/methodology/approach Employees from 13 companies registered on the Palestine Stock Exchange for 2023 were selected. Moreover, the sample included 326 randomly chosen participants. A questionnaire was distributed to participants to collect data, and a descriptive-analytical approach was followed to achieve the study’s aim and examine its hypotheses. Findings The results showed that the use of artificial intelligence techniques (expert systems, machine learning, neural networks and algorithms) has a positive effect on improving the quality of accounting information characteristics (relevance, faithful representation and verifiability). Expert systems, neural network applications and algorithms contribute to developing solutions to various problems in industrial companies; discovering fraudulent practices in financial statements; and obtaining more accurate, faster and more reliable results. Machine learning also links the company’s systems together simultaneously and in an integrated and effective manner. Research limitations/implications The research relied on the industrial sector only because expanding society is difficult due to the general conditions in Palestine, and the results may vary between different sectors due to the nature of their work and activity. Practical implications Industrial companies’ efforts to benefit from artificial intelligence applications in their work increase the quality of accounting information, which in turn reflects the company’s real situation and helps in making the necessary decisions efficiently and effectively. Originality/value This study contributes to directing the attention of financiers and accountants working in Palestinian industrial companies to the importance of applying artificial intelligence techniques to ensure the highest quality characteristics of accounting information through the preparation of accounting programmes that rely on artificial intelligence to operate, thus achieving the maximum degree of advantage in compiling financial data from its sources, operation and conversion into useful financial information for its users.

AI-Based Supply Chain Risk Management

As the complexity of global supply chains increases, supply chain risk management becomes increasingly important. The development of artificial intelligence (AI) technology provides new tools and methods for managing supply chain risks. This paper aims to review the application of AI in supply chain risk management, exploring current research progress, challenges, and future development trends. Through a systematic literature search and analysis, this paper examines relevant papers from databases such as Google Scholar, Web of Science, EI, and Scopus, discussing the specific applications of machine learning, deep learning, neural networks, fuzzy logic, genetic algorithms, and evolutionary algorithms in supply chain risk management. The study finds that these AI technologies demonstrate significant advantages in risk prediction, anomaly detection, image recognition, text mining, supply chain optimization, and emergency strategy formulation. However, issues related to data privacy and security, technical complexity, and implementation difficulties remain major challenges in current applications. In the future, as AI technology advances and interdisciplinary integration develops, supply chain risk management will have more opportunities. This study provides specific application suggestions for enterprises and decision-makers and points the way for future research.

Rumus Umum Pelabelan L(2, 1) pada Graf Koprima Grup Bilangan Bulat Modulo m

Groups are nonempty sets equipped with binary operations and fulfill certain conditions. One example of a group is the group of integers modulo . A coprime graph of a group is a graph whose vertices are elements in and any two vertices in are directly connected if and only if the greatest common factor of the orders x and y are relatively prime. labeling has important applications in wireless telecommunication networks, where there are limited radio frequencies available and adjacent transmitters cannot use the same frequency. To overcome this problem, frequency assignment is done using the concept of labeling, where transmitters are symbolized as vertices connected by edges. labeling is a graph labeling technique that assigns non-negative integer labels to graph vertices with the rule that two directly connected vertices must have a minimum label difference of two, and two vertices that are two apart must have a minimum label difference of one. The purpose of this research is to find out the general formula for the labeling on the coprime graph of the group of integers modulo and the general formula for the minimum value of the largest label of the labeling. The steps taken in this research are to determine the coprime graph form of the group of integers modulo . Then label each vertex with a non-negative label. Then label each vertex with labeling rule. From the result of this research, it can be concluded that the coprime graph of integer group modulo has a labeling with .

The Application of National Security Algorithm in Wireless Networks for Industrial Automation Process Automation (WIA-PA) Network Data Security Transmission

Industrial wireless communication technology is the key to promoting the development of factory intelligence and automation. However, wireless network data security has hindered the development of industrial intelligence. Therefore, to solve the security issues of industrial wireless networks, a network data secure transmission technology based on the national security algorithm is proposed based on industrial wireless network standard protocols. Firstly, to address the vulnerability of network node identity authentication to attacks, the national security algorithm is used to construct a node authentication model. Secondly, a data security transmission model is constructed based on the improved national security algorithm, which can securely transmit industrial wireless networks by encrypting network application layer data. In network node identity authentication, when the step size was 50, the identity authentication average accuracy of the research mode reached over 98.95%, which was better than other models. When the step size was 50, the average accuracy of identity authentication in the research model was over 98.95%, showing the best performance among similar models. In the attack test of illegal client C, when the interaction history data was within 500, the node identity authentication was higher than 99.56%. However, when the interaction history data exceeded 500, the overall performance of the research model was still the best. In the comparison of node code storage and content usage overhead, when the code quantity was 15000, the storage overhead of the research model was 87356 bytes, with more node code storage and lower memory usage. The overall performance of the research model is better. From this, the research method performs the best in both identity recognition accuracy and security in network data security. The research content will provide technical support for the security management and data transmission of industrial wireless technology.

The Spatial Conflict Life Cycle in Africa

The growing availability of geospatial data that document both how violent actors are connected and where their attacks take place offers a unique opportunity to produce a more integrated approach to the evolution of armed conflicts. The goal of this article is to contribute to this agenda, by introducing the concept of the spatial conflict life cycle. This new concept allows for spatializing conflict networks over time by bringing together three approaches that have been developed separately: spatial analysis, network analysis, and temporal analysis. After reviewing the literature, we note that applications of space, networks, and time have been limited to combinations in pairs. The article then discusses how the concept of spatial conflict life cycle can conceptually bring them all together and how it can be applied to study the evolution of armed conflicts in Africa using disaggregated data from the Armed Conflict Location & Event Data (ACLED) Project. Our results suggest that African armed conflicts express regularities in the way violence is spatially and temporally distributed. Conflicts tend to follow a certain number of common temporal stages in their geography that resemble a cycle, from the moment they emerge in specific regions, until they end.

Applications of artificial neural network to solve the nonlinear Cassava mosaic disease model

Applications of artificial neural network to solve the nonlinear Cassava mosaic disease model

Field-free spin–orbit torque devices for logic and neural network applications

Field-free spin–orbit torque devices for logic and neural network applications